---
title: "ATLAS — paper by Wu et al. (2026) — summary and ideas"
description: "As both LLMs and external tools multiply, choosing which model should handle a query and with which… 76 references, cited by 8 papers here."
authors: ["Jinyang Wu", "Guocheng Zhai", "Ruihan Jin", "Jiahao Yuan", "Yuhao Shen", "Shuai Zhang", "Zhengqi Wen", "Jianhua Tao"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.867/"
doi: "10.18653/v1/2026.findings-acl.867"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wu-2026-atlas-orchestrating-heterogeneous-models-tools/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2026-atlas-orchestrating-heterogeneous-models-tools/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/2/) / ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

# ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

**Authors:** [Jinyang Wu](https://md.research.elamur.ai/free/en/authors/jinyang-wu/), Guocheng Zhai, Ruihan Jin, Jiahao Yuan, [Yuhao Shen](https://md.research.elamur.ai/free/en/authors/yuhao-shen/), [Shuai Zhang](https://md.research.elamur.ai/free/en/authors/shuai-zhang/), [Zhengqi Wen](https://md.research.elamur.ai/free/en/authors/zhengqi-wen/) and [Jianhua Tao](https://md.research.elamur.ai/free/en/authors/jianhua-tao/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.867/) · [PDF](https://aclanthology.org/2026.findings-acl.867.pdf) · [DOI 10.18653/v1/2026.findings-acl.867](https://doi.org/10.18653/v1/2026.findings-acl.867) · [OpenAlex](https://openalex.org/W7166870625)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [8](https://md.research.elamur.ai/free/en/papers/wu-2026-atlas-orchestrating-heterogeneous-models-tools/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
As both LLMs and external tools multiply, choosing which model should handle a query and with which tool becomes a large combinatorial search problem. Existing routers pick only a model and ignore tools. Tool-use systems tend to follow fixed calling logic. RL approaches usually tune one component on its own. ATLAS (Adaptive Tool-LLM Alignment and Synergistic Invocation) treats the model and the tool as one joint choice and resolves it in two ways. For familiar domains, a training-free router embeds queries, groups them into semantic clusters, and selects the model-tool pair with the best accuracy-cost profile in the nearest cluster, using historical statistics. For unfamiliar tasks, a policy LLM trained with PPO routes over several steps, calling model-tool pairs in a loop until it produces an answer. Across 15 benchmarks covering 9 task types, ATLAS beats GPT-4o and prior routers, with larger gains out of distribution. It also helps on visual reasoning by coordinating multimodal tools. The work argues that orchestrating an ecosystem of models and tools can rival simply scaling a single model.

## Key points
- The search space is the Cartesian product of candidate LLMs and tools. The cluster router estimates per-cluster success rates and token-based costs for each pair. The RL reward combines three terms: format, outcome, and model selection.
- Compared with existing routing methods such as RouterDC, MLPRouter and BertRouter, ATLAS gains +10.1% in-distribution and +13.1% out-of-distribution. Benchmarks include AIME24/25, AMC, HumanEval, MBPP, NQ, WebQ and GPQA.
- RL training lifts pass@1 from 36.4% to 59.4%. Pass@16 reaches 63.1%, which suggests the policy is close to its capacity ceiling.
- A Wilcoxon signed-rank test against RouterDC gives p = 9.7×10⁻⁴ in-distribution, and the OOD setting is also significant (p \< 0.05). Across three runs, ATLAS (Cluster) scores 82.5±2.5 on AMC and 91.5±1.6 on HumanEval.
- The number of API calls adapts to the task: hard tasks like AIME25 and GPQA get more calls, while retrieval tasks like NQ and WebQ get few. Audio and video are not covered, and the system depends on reliable API access.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 333 works · 87,019 citations
- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 172 works · 12,988 citations
- [East China Normal University](https://md.research.elamur.ai/free/en/universities/east-china-normal-university/) — University, Shanghai, China · 50 works · 2,174 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen and Jianhua Tao. 2026. ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wu2026atlas,
  title = {{ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning}},
  author = {Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen and Jianhua Tao},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.867},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.867}
}
```

- [← previous Anthropocentric Bias in Language Model Evaluation](https://md.research.elamur.ai/free/en/papers/milliere-2026-anthropocentric-bias-language-model-evaluation/)
- [next → CTPD: Cross Tokenizer Preference Distillation](https://md.research.elamur.ai/free/en/papers/nguyen-2026-ctpd-cross-tokenizer-preference-distillation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/2/)

## References

76 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Manoj Acharya, Kushal Kafle, and Christopher Kanan. 2019. Tallyqa: Answering complex counting questions. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 8076–8084. [find](https://scholar.google.com/scholar?q=Manoj+Acharya%2C+Kushal+Kafle%2C+and+Christopher+Kanan%2E+2019%2E+Tallyqa%3A+Answering+complex+counting+questions%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+intelligence%2C+volume+33%2C+pages+8076%E2%80%938084%2E)
2. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, et al. 2021. [Program synthesis with large language models](https://md.research.elamur.ai/free/en/papers/austin-2021-program-synthesis-large-language-models/). arXiv preprint arXiv:2108.07732.
3. Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. [Semantic parsing on Freebase from question-answer pairs](https://md.research.elamur.ai/free/en/papers/berant-2013-semantic-parsing-freebase-question-answer/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1533–1544, Seattle, Washington, USA. Association for Computational Linguistics.
4. Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, et al. 2024. [Internlm2 technical report](https://md.research.elamur.ai/free/en/papers/cai-2024-internlm2-technical-report/). arXiv preprint arXiv:2403.17297.
5. Cong Chen, Kaixiang Ji, Hao Zhong, Muzhi Zhu, Anzhou Li, Guo Gan, Ziyuan Huang, Cheng Zou, Jiajia Liu, Jingdong Chen, et al. 2025a. Gui-shepherd: Reliable process reward and verification for long-sequence gui tasks. arXiv preprint arXiv:2509.23738. — [arXiv:2509.23738](https://arxiv.org/abs/2509.23738) [find](https://scholar.google.com/scholar?q=Cong+Chen%2C+Kaixiang+Ji%2C+Hao+Zhong%2C+Muzhi+Zhu%2C+Anzhou+Li%2C+Guo+Gan%2C+Ziyuan+Huang%2C+Cheng+Zou%2C+Jiajia+Liu%2C+Jingdong+Chen%2C+et+al%2E+2025a%2E+Gui%2Dshepherd%3A+Reliable+process+reward+and+verification+for+long%2Dsequ)
6. Guoxin Chen, Zhong Zhang, Xin Cong, Fangda Guo, Yesai Wu, Yankai Lin, Wenzheng Feng, and Yasheng Wang. 2025b. Learning evolving tools for large language models. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Guoxin+Chen%2C+Zhong+Zhang%2C+Xin+Cong%2C+Fangda+Guo%2C+Yesai+Wu%2C+Yankai+Lin%2C+Wenzheng+Feng%2C+and+Yasheng+Wang%2E+2025b%2E+Learning+evolving+tools+for+large+language+models%2E+In+The+Thirteenth+International+Confere)
7. Lingjiao Chen, Matei Zaharia, and James Zou. 2023. [Frugalgpt: How to use large language models while reducing cost and improving performance](https://md.research.elamur.ai/free/en/papers/chen-2023-frugalgpt-use-large-language-models/). Transactions on Machine Learning Research.
8. Mark Chen. 2021. [Evaluating large language models trained on code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/). arXiv preprint arXiv:2107.03374.
9. Shuhao Chen, Weisen Jiang, Baijiong Lin, James Kwok, and Yu Zhang. 2024. Routerdc: Query-based router by dual contrastive learning for assembling large language models. Advances in Neural Information Processing Systems, 37:66305–66328. [find](https://scholar.google.com/scholar?q=Shuhao+Chen%2C+Weisen+Jiang%2C+Baijiong+Lin%2C+James+Kwok%2C+and+Yu+Zhang%2E+2024%2E+Routerdc%3A+Query%2Dbased+router+by+dual+contrastive+learning+for+assembling+large+language+models%2E+Advances+in+Neural+Information+)
10. Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Rühle, Laks V. S. Lakshmanan, and Ahmed Hassan Awadallah. 2024. Hybrid LLM: Cost-efficient and quality-aware query routing. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Dujian+Ding%2C+Ankur+Mallick%2C+Chi+Wang%2C+Robert+Sim%2C+Subhabrata+Mukherjee%2C+Victor+R%C3%BChle%2C+Laks+V%2E+S%2E+Lakshmanan%2C+and+Ahmed+Hassan+Awadallah%2E+2024%2E+Hybrid+LLM%3A+Cost%2Defficient+and+quality%2Daware+query+routin)
11. Guanting Dong, Yifei Chen, Xiaoxi Li, Jiajie Jin, Hongjin Qian, Yutao Zhu, Hangyu Mao, Guorui Zhou, Zhicheng Dou, and Ji-Rong Wen. 2025. Tool-star: Empowering llm-brained multi-tool reasoner via reinforcement learning. arXiv preprint arXiv:2505.16410. — [arXiv:2505.16410](https://arxiv.org/abs/2505.16410) [find](https://scholar.google.com/scholar?q=Guanting+Dong%2C+Yifei+Chen%2C+Xiaoxi+Li%2C+Jiajie+Jin%2C+Hongjin+Qian%2C+Yutao+Zhu%2C+Hangyu+Mao%2C+Guorui+Zhou%2C+Zhicheng+Dou%2C+and+Ji%2DRong+Wen%2E+2025%2E+Tool%2Dstar%3A+Empowering+llm%2Dbrained+multi%2Dtool+reasoner+via+reinf)
12. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv e-prints, pages arXiv–2407.
13. Jiazhan Feng, Shijue Huang, Xingwei Qu, Ge Zhang, Yujia Qin, Baoquan Zhong, Chengquan Jiang, Jinxin Chi, and Wanjun Zhong. 2025a. Retool: Reinforcement learning for strategic tool use in llms. arXiv preprint arXiv:2504.11536. [find](https://scholar.google.com/scholar?q=Jiazhan+Feng%2C+Shijue+Huang%2C+Xingwei+Qu%2C+Ge+Zhang%2C+Yujia+Qin%2C+Baoquan+Zhong%2C+Chengquan+Jiang%2C+Jinxin+Chi%2C+and+Wanjun+Zhong%2E+2025a%2E+Retool%3A+Reinforcement+learning+for+strategic+tool+use+in+llms%2E+arXiv+p)
14. Tao Feng, Yanzhen Shen, and Jiaxuan You. 2025b. Graphrouter: A graph-based router for LLM selections. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Tao+Feng%2C+Yanzhen+Shen%2C+and+Jiaxuan+You%2E+2025b%2E+Graphrouter%3A+A+graph%2Dbased+router+for+LLM+selections%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations%2E)
15. Guo Gan, Yuxuan Ding, Cong Chen, Yuwei Ren, Yin Huang, and Hong Zhou. 2026. [Android coach: Improve online agentic training efficiency with single state multiple actions](https://md.research.elamur.ai/free/en/papers/gan-2026-android-coach-improve-online-agentic/). arXiv preprint arXiv:2604.07277.
16. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
17. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. [Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing](https://md.research.elamur.ai/free/en/papers/he-2021-debertav3-improving-deberta-using-electra/). In The Eleventh International Conference on Learning Representations.
18. Qitian Jason Hu, Jacob Bieker, Xiuyu Li, Nan Jiang, Benjamin Keigwin, Gaurav Ranganath, Kurt Keutzer, and Shriyash Kaustubh Upadhyay. 2024. Routerbench: A benchmark for multi-LLM routing system. In Agentic Markets Workshop at ICML 2024. [find](https://scholar.google.com/scholar?q=Qitian+Jason+Hu%2C+Jacob+Bieker%2C+Xiuyu+Li%2C+Nan+Jiang%2C+Benjamin+Keigwin%2C+Gaurav+Ranganath%2C+Kurt+Keutzer%2C+and+Shriyash+Kaustubh+Upadhyay%2E+2024%2E+Routerbench%3A+A+benchmark+for+multi%2DLLM+routing+system%2E+In+Ag)
19. Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Keming Lu, et al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186. — [Qwen2.5-Coder Technical Report](https://md.research.elamur.ai/free/en/papers/hui-2024-qwen2-5-coder-technical-report/)
20. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan O Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025a. [Search-r1: Training LLMs to reason and leverage search engines with reinforcement learning](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/). In Second Conference on Language Modeling.
21. Ruihan Jin, Pengpeng Shao, Zhengqi Wen, Jinyang Wu, Mingkuan Feng, Shuai Zhang, and Jianhua Tao. 2025b. Radialrouter: Structured representation for efficient and robust large language models routing. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 14587–14600, Suzhou,… [find](https://scholar.google.com/scholar?q=Ruihan+Jin%2C+Pengpeng+Shao%2C+Zhengqi+Wen%2C+Jinyang+Wu%2C+Mingkuan+Feng%2C+Shuai+Zhang%2C+and+Jianhua+Tao%2E+2025b%2E+Radialrouter%3A+Structured+representation+for+efficient+and+robust+large+language+models+routing%2E+)
22. Yoonsik Kim, Moonbin Yim, and Ka Yeon Song. 2024. Tablevqa-bench: A visual question answering benchmark on multiple table domains. arXiv preprint arXiv:2404.19205. — [arXiv:2404.19205](https://arxiv.org/abs/2404.19205) [find](https://scholar.google.com/scholar?q=Yoonsik+Kim%2C+Moonbin+Yim%2C+and+Ka+Yeon+Song%2E+2024%2E+Tablevqa%2Dbench%3A+A+visual+question+answering+benchmark+on+multiple+table+domains%2E+arXiv+preprint+arXiv%3A2404%2E19205%2E+%E2%80%94+%5BarXiv%3A2404%2E19205%5D%28https%3A%2F%2Farxiv%2Eo)
23. Yilun Kong, Jingqing Ruan, Yihong Chen, Bin Zhang, Tianpeng Bao, Shi Shiwei, Xiaoru Hu, Hangyu Mao, Ziyue Li, Xingyu Zeng, et al. 2024. Tptu-v2: Boosting task planning and tool usage of large language model-based agents in real-world industry systems. In Proceedings of the 2024 conference on empiric… [find](https://scholar.google.com/scholar?q=Yilun+Kong%2C+Jingqing+Ruan%2C+Yihong+Chen%2C+Bin+Zhang%2C+Tianpeng+Bao%2C+Shi+Shiwei%2C+Xiaoru+Hu%2C+Hangyu+Mao%2C+Ziyue+Li%2C+Xingyu+Zeng%2C+et+al%2E+2024%2E+Tptu%2Dv2%3A+Boosting+task+planning+and+tool+usage+of+large+language)
24. Samuel Kotz and Norman L. Johnson, editors. 1992. Breakthroughs in Statistics: Methodology and Distribution. Springer New York, New York, NY. [find](https://scholar.google.com/scholar?q=Samuel+Kotz+and+Norman+L%2E+Johnson%2C+editors%2E+1992%2E+Breakthroughs+in+Statistics%3A+Methodology+and+Distribution%2E+Springer+New+York%2C+New+York%2C+NY%2E)
25. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al. 2019. [Natural questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Linguistic…
26. Harrison Lee, Samrat Phatale, Hassan Mansoor, Thomas Mesnard, Johan Ferret, Kellie Lu, Colton Bishop, Ethan Hall, Victor Carbune, Abhinav Rastogi, et al. 2023. Rlaif vs. rlhf: Scaling reinforcement learning from human feedback with ai feedback. arXiv preprint arXiv:2309.00267. [find](https://scholar.google.com/scholar?q=Harrison+Lee%2C+Samrat+Phatale%2C+Hassan+Mansoor%2C+Thomas+Mesnard%2C+Johan+Ferret%2C+Kellie+Lu%2C+Colton+Bishop%2C+Ethan+Hall%2C+Victor+Carbune%2C+Abhinav+Rastogi%2C+et+al%2E+2023%2E+Rlaif+vs%2E+rlhf%3A+Scaling+reinforcement+le)
27. Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Chunkit Chan, Yankai Chen, Zhongfen Deng, Yinghui Li, Hai-Tao Zheng, Dongyuan Li, Renhe Jiang, Ming Zhang, Yangqiu Song, and Philip S. Yu. 2025. A survey of RAG-reasonin… [find](https://scholar.google.com/scholar?q=Yangning+Li%2C+Weizhi+Zhang%2C+Yuyao+Yang%2C+Wei%2DChieh+Huang%2C+Yaozu+Wu%2C+Junyu+Luo%2C+Yuanchen+Bei%2C+Henry+Peng+Zou%2C+Xiao+Luo%2C+Yusheng+Zhao%2C+Chunkit+Chan%2C+Yankai+Chen%2C+Zhongfen+Deng%2C+Yinghui+Li%2C+Hai%2DTao+Zheng%2C+)
28. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In The Twelfth International Conference on Learning Representations.
29. Hanmeng Liu, Jian Liu, Leyang Cui, Zhiyang Teng, Nan Duan, Ming Zhou, and Yue Zhang. 2023. Logiqa 2.0—an improved dataset for logical reasoning in natural language understanding. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:2947–2962. [find](https://scholar.google.com/scholar?q=Hanmeng+Liu%2C+Jian+Liu%2C+Leyang+Cui%2C+Zhiyang+Teng%2C+Nan+Duan%2C+Ming+Zhou%2C+and+Yue+Zhang%2E+2023%2E+Logiqa+2%2E0%E2%80%94an+improved+dataset+for+logical+reasoning+in+natural+language+understanding%2E+IEEE%2FACM+Transactions)
30. Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, and Jingren Zhou. 2024. Routing to the expert: Efficient reward-guided ensemble of large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Huma… [find](https://scholar.google.com/scholar?q=Keming+Lu%2C+Hongyi+Yuan%2C+Runji+Lin%2C+Junyang+Lin%2C+Zheng+Yuan%2C+Chang+Zhou%2C+and+Jingren+Zhou%2E+2024%2E+Routing+to+the+expert%3A+Efficient+reward%2Dguided+ensemble+of+large+language+models%2E+In+Proceedings+of+the+)
31. Pan Lu, Ran Gong, Shibiao Jiang, Liang Qiu, Siyuan Huang, Xiaodan Liang, and Song-Chun Zhu. 2021. [Inter-GPS: Interpretable geometry problem solving with formal language and symbolic reasoning](https://md.research.elamur.ai/free/en/papers/lu-2021-inter-gps-interpretable-geometry-problem/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int…
32. Zhengxi Lu, Yuxiang Chai, Yaxuan Guo, Xi Yin, Liang Liu, Hao Wang, Han Xiao, Shuai Ren, Pengxiang Zhao, Guangyi Liu, et al. 2026a. Ui-r1: Enhancing efficient action prediction of gui agents by reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages… [find](https://scholar.google.com/scholar?q=Zhengxi+Lu%2C+Yuxiang+Chai%2C+Yaxuan+Guo%2C+Xi+Yin%2C+Liang+Liu%2C+Hao+Wang%2C+Han+Xiao%2C+Shuai+Ren%2C+Pengxiang+Zhao%2C+Guangyi+Liu%2C+et+al%2E+2026a%2E+Ui%2Dr1%3A+Enhancing+efficient+action+prediction+of+gui+agents+by+reinfor)
33. Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, and Yongliang Shen. 2026b. Skill0: In-context agentic reinforcement learning for skill internalization. arXiv preprint arXiv:2604.02268. — [arXiv:2604.02268](https://arxiv.org/abs/2604.02268) [find](https://scholar.google.com/scholar?q=Zhengxi+Lu%2C+Zhiyuan+Yao%2C+Jinyang+Wu%2C+Chengcheng+Han%2C+Qi+Gu%2C+Xunliang+Cai%2C+Weiming+Lu%2C+Jun+Xiao%2C+Yueting+Zhuang%2C+and+Yongliang+Shen%2E+2026b%2E+Skill0%3A+In%2Dcontext+agentic+reinforcement+learning+for+skill+i)
34. Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, et al. 2025. Ui-s1: Advancing gui automation via semi-online reinforcement learning. arXiv preprint arXiv:2509.11543. — [arXiv:2509.11543](https://arxiv.org/abs/2509.11543) [find](https://scholar.google.com/scholar?q=Zhengxi+Lu%2C+Jiabo+Ye%2C+Fei+Tang%2C+Yongliang+Shen%2C+Haiyang+Xu%2C+Ziwei+Zheng%2C+Weiming+Lu%2C+Ming+Yan%2C+Fei+Huang%2C+Jun+Xiao%2C+et+al%2E+2025%2E+Ui%2Ds1%3A+Advancing+gui+automation+via+semi%2Donline+reinforcement+learning%2E)
35. Zexiong Ma, Chao Peng, Qunhong Zeng, Pengfei Gao, Yanzhen Zou, and Bing Xie. 2025. Tool-integrated reinforcement learning for repo deep search. arXiv preprint arXiv:2508.03012. — [arXiv:2508.03012](https://arxiv.org/abs/2508.03012) [find](https://scholar.google.com/scholar?q=Zexiong+Ma%2C+Chao+Peng%2C+Qunhong+Zeng%2C+Pengfei+Gao%2C+Yanzhen+Zou%2C+and+Bing+Xie%2E+2025%2E+Tool%2Dintegrated+reinforcement+learning+for+repo+deep+search%2E+arXiv+preprint+arXiv%3A2508%2E03012%2E+%E2%80%94+%5BarXiv%3A2508%2E03012%5D%28ht)
36. MAA. 2024. American invitational mathematics examination - aime. In American Invitational Mathematics Examination - AIME 2024. [find](https://scholar.google.com/scholar?q=MAA%2E+2024%2E+American+invitational+mathematics+examination+%2D+aime%2E+In+American+Invitational+Mathematics+Examination+%2D+AIME+2024%2E)
37. MAA. 2025. American invitational mathematics examination - aime. In American Invitational Mathematics Examination - AIME 2025. [find](https://scholar.google.com/scholar?q=MAA%2E+2025%2E+American+invitational+mathematics+examination+%2D+aime%2E+In+American+Invitational+Mathematics+Examination+%2D+AIME+2025%2E)
38. Ahmed Masry, Xuan Long Do, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022. [Chartqa: A benchmark for question answering about charts with visual and logical reasoning](https://md.research.elamur.ai/free/en/papers/masry-2022-chartqa-benchmark-question-answering-about/). In Findings of the association for computational linguistics: ACL 2022, pages 2263– 2279.
39. Kai Mei, Wujiang Xu, Shuhang Lin, and Yongfeng Zhang. 2025. Omnirouter: Budget and performance controllable multi-llm routing. arXiv preprint arXiv:2502.20576. — [arXiv:2502.20576](https://arxiv.org/abs/2502.20576) [find](https://scholar.google.com/scholar?q=Kai+Mei%2C+Wujiang+Xu%2C+Shuhang+Lin%2C+and+Yongfeng+Zhang%2E+2025%2E+Omnirouter%3A+Budget+and+performance+controllable+multi%2Dllm+routing%2E+arXiv+preprint+arXiv%3A2502%2E20576%2E+%E2%80%94+%5BarXiv%3A2502%2E20576%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
40. Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E Gonzalez, M Waleed Kadous, and Ion Stoica. 2024. Routellm: Learning to route llms from preference data. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Isaac+Ong%2C+Amjad+Almahairi%2C+Vincent+Wu%2C+Wei%2DLin+Chiang%2C+Tianhao+Wu%2C+Joseph+E+Gonzalez%2C+M+Waleed+Kadous%2C+and+Ion+Stoica%2E+2024%2E+Routellm%3A+Learning+to+route+llms+from+preference+data%2E+In+The+Thirteenth+I)
41. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744.
42. Roni Paiss, Ariel Ephrat, Omer Tov, Shiran Zada, Inbar Mosseri, Michal Irani, and Tali Dekel. 2023. Teaching clip to count to ten. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3170–3180. [find](https://scholar.google.com/scholar?q=Roni+Paiss%2C+Ariel+Ephrat%2C+Omer+Tov%2C+Shiran+Zada%2C+Inbar+Mosseri%2C+Michal+Irani%2C+and+Tali+Dekel%2E+2023%2E+Teaching+clip+to+count+to+ten%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Conference+on+Computer+V)
43. Zhihong Pan, Kai Zhang, Yuze Zhao, and Yupeng Han. 2025. Route to reason: Adaptive routing for llm and reasoning strategy selection. arXiv preprint arXiv:2505.19435. — [arXiv:2505.19435](https://arxiv.org/abs/2505.19435) [find](https://scholar.google.com/scholar?q=Zhihong+Pan%2C+Kai+Zhang%2C+Yuze+Zhao%2C+and+Yupeng+Han%2E+2025%2E+Route+to+reason%3A+Adaptive+routing+for+llm+and+reasoning+strategy+selection%2E+arXiv+preprint+arXiv%3A2505%2E19435%2E+%E2%80%94+%5BarXiv%3A2505%2E19435%5D%28https%3A%2F%2Farxiv)
44. Shishir G Patil, Huanzhi Mao, Fanjia Yan, Charlie Cheng-Jie Ji, Vishnu Suresh, Ion Stoica, and Joseph E. Gonzalez. 2025. The berkeley function calling leaderboard (BFCL): From tool use to agentic evaluation of large language models. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Shishir+G+Patil%2C+Huanzhi+Mao%2C+Fanjia+Yan%2C+Charlie+Cheng%2DJie+Ji%2C+Vishnu+Suresh%2C+Ion+Stoica%2C+and+Joseph+E%2E+Gonzalez%2E+2025%2E+The+berkeley+function+calling+leaderboard+%28BFCL%29%3A+From+tool+use+to+agentic+eval)
45. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in neural information processing systems, 36:53728–53741.
46. N Dinesh Reddy and Sudeep Pillai. 2025. Orion: A unified visual agent for multimodal perception, advanced visual reasoning and execution. arXiv preprint arXiv:2511.14210. — [arXiv:2511.14210](https://arxiv.org/abs/2511.14210) [find](https://scholar.google.com/scholar?q=N+Dinesh+Reddy+and+Sudeep+Pillai%2E+2025%2E+Orion%3A+A+unified+visual+agent+for+multimodal+perception%2C+advanced+visual+reasoning+and+execution%2E+arXiv+preprint+arXiv%3A2511%2E14210%2E+%E2%80%94+%5BarXiv%3A2511%2E14210%5D%28https%3A%2F%2F)
47. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. 2024. [Gpqa: A graduate-level google-proof q&a benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). In First Conference on Language Modeling.
48. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+2017%2E+Proximal+policy+optimization+algorithms%2E+arXiv+preprint+arXiv%3A1707%2E06347%2E)
49. Yuhao Shen, Tianyu Liu, Junyi Shen, Jinyang Wu, Quan Kong, Li Huan, and Cong Wang. 2026a. Double: Breaking the acceleration limit via double retrieval speculative parallelism. arXiv preprint arXiv:2601.05524. [find](https://scholar.google.com/scholar?q=Yuhao+Shen%2C+Tianyu+Liu%2C+Junyi+Shen%2C+Jinyang+Wu%2C+Quan+Kong%2C+Li+Huan%2C+and+Cong+Wang%2E+2026a%2E+Double%3A+Breaking+the+acceleration+limit+via+double+retrieval+speculative+parallelism%2E+arXiv+preprint+arXiv%3A260)
50. Yuhao Shen, Junyi Shen, Quan Kong, Tianyu Liu, Yao Lu, and Cong Wang. 2026b. Specbranch: Speculative decoding via hybrid drafting and rollback-aware branch parallelism. In The Fourteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yuhao+Shen%2C+Junyi+Shen%2C+Quan+Kong%2C+Tianyu+Liu%2C+Yao+Lu%2C+and+Cong+Wang%2E+2026b%2E+Specbranch%3A+Speculative+decoding+via+hybrid+drafting+and+rollback%2Daware+branch+parallelism%2E+In+The+Fourteenth+International)
51. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik R Narasimhan, and Shunyu Yao. 2023. [Reflexion: language agents with verbal reinforcement learning](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). In Thirty-seventh Conference on Neural Information Processing Systems.
52. Hunyuan Vision Team, Pengyuan Lyu, Xingyu Wan, Gengluo Li, Shangpin Peng, Weinong Wang, Liang Wu, Huawen Shen, Yu Zhou, Canhui Tang, et al. 2025. [Hunyuanocr technical report](https://md.research.elamur.ai/free/en/papers/team-2025-vision-hunyuanocr-technical-report/). arXiv preprint arXiv:2511.19575.
53. Chenxu Wang, Hao Li, Yiqun Zhang, Linyao Chen, Jianhao Chen, Ping Jian, Peng Ye, Qiaosheng Zhang, and Shuyue Hu. 2025. Icl-router: In-context learned model representations for llm routing. arXiv preprint arXiv:2510.09719. — [arXiv:2510.09719](https://arxiv.org/abs/2510.09719) [find](https://scholar.google.com/scholar?q=Chenxu+Wang%2C+Hao+Li%2C+Yiqun+Zhang%2C+Linyao+Chen%2C+Jianhao+Chen%2C+Ping+Jian%2C+Peng+Ye%2C+Qiaosheng+Zhang%2C+and+Shuyue+Hu%2E+2025%2E+Icl%2Drouter%3A+In%2Dcontext+learned+model+representations+for+llm+routing%2E+arXiv+prepr)
54. Fangzhi Xu, Hang Yan, Qiushi Sun, Jinyang Wu, Zixian Huang, Muye Huang, Jingyang Gong, Zichen Ding, Kanzhi Cheng, Yian Wang, et al. 2026. Odysseyarena: Benchmarking large language models for long-horizon, active and inductive interactions. arXiv preprint arXiv:2602.05843. — [arXiv:2602.05843](https://arxiv.org/abs/2602.05843) [find](https://scholar.google.com/scholar?q=Fangzhi+Xu%2C+Hang+Yan%2C+Qiushi+Sun%2C+Jinyang+Wu%2C+Zixian+Huang%2C+Muye+Huang%2C+Jingyang+Gong%2C+Zichen+Ding%2C+Kanzhi+Cheng%2C+Yian+Wang%2C+et+al%2E+2026%2E+Odysseyarena%3A+Benchmarking+large+language+models+for+long%2Dhori)
55. Hang Yan, Xinyu Che, Fangzhi Xu, Qiushi Sun, Zichen Ding, Kanzhi Cheng, Jian Zhang, Tao Qin, Jun Liu, and Qika Lin. 2026. Tide: Trajectory-based diagnostic evaluation of test-time improvement in llm agents. arXiv preprint arXiv:2602.02196. — [arXiv:2602.02196](https://arxiv.org/abs/2602.02196) [find](https://scholar.google.com/scholar?q=Hang+Yan%2C+Xinyu+Che%2C+Fangzhi+Xu%2C+Qiushi+Sun%2C+Zichen+Ding%2C+Kanzhi+Cheng%2C+Jian+Zhang%2C+Tao+Qin%2C+Jun+Liu%2C+and+Qika+Lin%2E+2026%2E+Tide%3A+Trajectory%2Dbased+diagnostic+evaluation+of+test%2Dtime+improvement+in+llm+a)
56. Jianhao Yan, Yafu Li, Zican Hu, Zhi Wang, Ganqu Cui, Xiaoye Qu, Yu Cheng, and Yue Zhang. 2025. Learning to reason under off-policy guidance. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Jianhao+Yan%2C+Yafu+Li%2C+Zican+Hu%2C+Zhi+Wang%2C+Ganqu+Cui%2C+Xiaoye+Qu%2C+Yu+Cheng%2C+and+Yue+Zhang%2E+2025%2E+Learning+to+reason+under+off%2Dpolicy+guidance%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information)
57. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
58. Jinyang Wu, Mingkuan Feng, Shuai Zhang, Fangrui Lv, Ruihan Jin, Feihu Che, Zengqi Wen, and Jianhua Tao. 2025a. Boosting multimodal reasoning with automated structured thinking. arXiv preprint arXiv:2502.02339. — [arXiv:2502.02339](https://arxiv.org/abs/2502.02339) [find](https://scholar.google.com/scholar?q=Jinyang+Wu%2C+Mingkuan+Feng%2C+Shuai+Zhang%2C+Fangrui+Lv%2C+Ruihan+Jin%2C+Feihu+Che%2C+Zengqi+Wen%2C+and+Jianhua+Tao%2E+2025a%2E+Boosting+multimodal+reasoning+with+automated+structured+thinking%2E+arXiv+preprint+arXiv%3A25)
59. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al. 2024a. Qwen2.5 technical report. arXiv preprint arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+et+al%2E+2024a%2E+Qwen2%2E5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115%2E)
60. Jinyang Wu, Chonghua Liao, Mingkuan Feng, Shuai Zhang, Zhengqi Wen, Haoran Luo, Ling Yang, Huazhe Xu, and Jianhua Tao. 2025b. [Templaterl: Structured template-guided reinforcement learning for llm reasoning](https://md.research.elamur.ai/free/en/papers/wu-2026-templaterl-structured-template-guided-reinforcement/). arXiv preprint arXiv:2505.15692.
61. An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, et al. 2024b. Qwen2. 5-math technical report: Toward mathematical expert model via self-improvement. arXiv preprint arXiv:2409.12122. — [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://md.research.elamur.ai/free/en/papers/yang-2024-qwen2-5-math-technical-report/)
62. Jinyang Wu, Shuo Yang, Changpeng Yang, Yuhao Shen, Shuai Zhang, Zhengqi Wen, and Jianhua Tao. 2026. [Spark: Strategic policy-aware exploration via dynamic branching for long-horizon agentic learning](https://md.research.elamur.ai/free/en/papers/wu-2026-spark-strategic-policy-aware-exploration/). arXiv preprint arXiv:2601.20209.
63. Jinyang Wu, Shuai Zhang, Feihu Che, Mingkuan Feng, Pengpeng Shao, and Jianhua Tao. 2025c. [Pandora’s box or aladdin’s lamp: A comprehensive analysis revealing the role of RAG noise in large language models](https://md.research.elamur.ai/free/en/papers/wu-2025-pandora-s-box-or-aladdin/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Vo…
64. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In The Eleventh International Conference on Learning Representations.
65. Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, and Gao Huang. 2025a. [Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model?](https://md.research.elamur.ai/free/en/papers/yue-2025-reinforcement-learning-really-incentivize-reasoning/) In The Thirty-ninth Annual Conference on Neural Information Processing Systems.
66. Shirley Wu, Shiyu Zhao, Qian Huang, Kexin Huang, Michihiro Yasunaga, Kaidi Cao, Vassilis Ioannidis, Karthik Subbian, Jure Leskovec, and James Y Zou. 2024. Avatar: Optimizing llm agents for tool usage via contrastive reasoning. Advances in Neural Information Processing Systems, 37:25981–26010. [find](https://scholar.google.com/scholar?q=Shirley+Wu%2C+Shiyu+Zhao%2C+Qian+Huang%2C+Kexin+Huang%2C+Michihiro+Yasunaga%2C+Kaidi+Cao%2C+Vassilis+Ioannidis%2C+Karthik+Subbian%2C+Jure+Leskovec%2C+and+James+Y+Zou%2E+2024%2E+Avatar%3A+Optimizing+llm+agents+for+tool+usage+)
67. Yanwei Yue, Guibin Zhang, Boyang Liu, Guancheng Wan, Kun Wang, Dawei Cheng, and Yiyan Qi. 2025b. [MasRouter: Learning to route LLMs for multi-agent systems](https://md.research.elamur.ai/free/en/papers/yue-2025-masrouter-learning-route-llms-multi/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15549–15572, Vienna, A…
68. Wenxun Wu, Yuanyang Li, Guhan Chen, Linyue Wang, and Hongyang Chen. 2025d. Tool-augmented policy optimization: Synergizing reasoning and adaptive tool use with reinforcement learning. arXiv preprint arXiv:2510.07038. — [arXiv:2510.07038](https://arxiv.org/abs/2510.07038) [find](https://scholar.google.com/scholar?q=Wenxun+Wu%2C+Yuanyang+Li%2C+Guhan+Chen%2C+Linyue+Wang%2C+and+Hongyang+Chen%2E+2025d%2E+Tool%2Daugmented+policy+optimization%3A+Synergizing+reasoning+and+adaptive+tool+use+with+reinforcement+learning%2E+arXiv+preprint+a)
69. Haozhen Zhang, Tao Feng, and Jiaxuan You. 2025a. Router-r1: Teaching llms multi-round routing and aggregation via reinforcement learning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Haozhen+Zhang%2C+Tao+Feng%2C+and+Jiaxuan+You%2E+2025a%2E+Router%2Dr1%3A+Teaching+llms+multi%2Dround+routing+and+aggregation+via+reinforcement+learning%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Pr)
70. Junlin Xie, Zhihong Chen, Ruifei Zhang, Xiang Wan, and Guanbin Li. 2024. Large multimodal agents: A survey. arXiv preprint arXiv:2402.15116. — [arXiv:2402.15116](https://arxiv.org/abs/2402.15116) [find](https://scholar.google.com/scholar?q=Junlin+Xie%2C+Zhihong+Chen%2C+Ruifei+Zhang%2C+Xiang+Wan%2C+and+Guanbin+Li%2E+2024%2E+Large+multimodal+agents%3A+A+survey%2E+arXiv+preprint+arXiv%3A2402%2E15116%2E+%E2%80%94+%5BarXiv%3A2402%2E15116%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2402%2E15116%29)
71. Kaiyan Zhang, Sihang Zeng, Ermo Hua, Ning Ding, Zhang-Ren Chen, Zhiyuan Ma, Haoxin Li, Ganqu Cui, Biqing Qi, Xuekai Zhu, Xingtai Lv, Hu Jinfang, Zhiyuan Liu, and Bowen Zhou. 2024. Ultramedical: Building specialized generalists in biomedicine. In The Thirty-eight Conference on Neural Information Proc… [find](https://scholar.google.com/scholar?q=Kaiyan+Zhang%2C+Sihang+Zeng%2C+Ermo+Hua%2C+Ning+Ding%2C+Zhang%2DRen+Chen%2C+Zhiyuan+Ma%2C+Haoxin+Li%2C+Ganqu+Cui%2C+Biqing+Qi%2C+Xuekai+Zhu%2C+Xingtai+Lv%2C+Hu+Jinfang%2C+Zhiyuan+Liu%2C+and+Bowen+Zhou%2E+2024%2E+Ultramedical%3A+Buildi)
72. Yiqun Zhang, Hao Li, Chenxu Wang, Linyao Chen, Qiaosheng Zhang, Peng Ye, Shi Feng, Daling Wang, Zhen Wang, Xinrun Wang, Jia Xu, Lei Bai, Wanli Ouyang, and Shuyue Hu. 2025b. The avengers: A simple recipe for uniting smaller language models to challenge proprietary giants. arXiv preprint arXiv:2505.19… — [arXiv:2505.19797](https://arxiv.org/abs/2505.19797) [find](https://scholar.google.com/scholar?q=Yiqun+Zhang%2C+Hao+Li%2C+Chenxu+Wang%2C+Linyao+Chen%2C+Qiaosheng+Zhang%2C+Peng+Ye%2C+Shi+Feng%2C+Daling+Wang%2C+Zhen+Wang%2C+Xinrun+Wang%2C+Jia+Xu%2C+Lei+Bai%2C+Wanli+Ouyang%2C+and+Shuyue+Hu%2E+2025b%2E+The+avengers%3A+A+simple+reci)
73. Richard Zhuang, Tianhao Wu, Zhaojin Wen, Andrew Li, Jiantao Jiao, and Kannan Ramchandran. 2025. EmbedLLM: Learning compact representations of large language models. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Richard+Zhuang%2C+Tianhao+Wu%2C+Zhaojin+Wen%2C+Andrew+Li%2C+Jiantao+Jiao%2C+and+Kannan+Ramchandran%2E+2025%2E+EmbedLLM%3A+Learning+compact+representations+of+large+language+models%2E+In+The+Thirteenth+International+Con)
74. C.10 Statistical Significance and Variance Analysis . . . . . . . . . . . D Case Study E Additional Discussion E.1 Distinguishing ATLAS from Prior Routing and Tool Usage Methods E.2 Discussion on RL Reward Design E.3 When to Use Cluster-Based vs. RL-Based Routing . . . . . . . . E.4 Future Work . .… [find](https://scholar.google.com/scholar?q=C%2E10+Statistical+Significance+and+Variance+Analysis+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+D+Case+Study+E+Additional+Discussion+E%2E1+Distinguishing+ATLAS+from+Prior+Routing+and+Tool+Usage+Methods+E%2E2+Discussion+on+RL+R)
75. Yuxin Zuo, Kaiyan Zhang, Li Sheng, Shang Qu, Ganqu Cui, Xuekai Zhu, Haozhan Li, Yuchen Zhang, Xinwei Long, Ermo Hua, Biqing Qi, Youbang Sun, Zhiyuan Ma, Lifan Yuan, Ning Ding, and Bowen Zhou. 2025. TTRL: Test-time reinforcement learning. In The Thirty-ninth Annual Conference on Neural Information Pr… [find](https://scholar.google.com/scholar?q=Yuxin+Zuo%2C+Kaiyan+Zhang%2C+Li+Sheng%2C+Shang+Qu%2C+Ganqu+Cui%2C+Xuekai+Zhu%2C+Haozhan+Li%2C+Yuchen+Zhang%2C+Xinwei+Long%2C+Ermo+Hua%2C+Biqing+Qi%2C+Youbang+Sun%2C+Zhiyuan+Ma%2C+Lifan+Yuan%2C+Ning+Ding%2C+and+Bowen+Zhou%2E+2025%2E+TT)
76. Contents A Details of Methodology A.1 Complete Algorithm Implementations . . . . . . . . . . . . . . . . A.2 Detailed Specification of Reward Signals . . . . . . . . . . . . . . . B Additional Experimental Details B.1 Datasets . . . . . . . . . . . . . . B.2 Baselines . . . . . . . . . . . . . B.3 E… [find](https://scholar.google.com/scholar?q=Contents+A+Details+of+Methodology+A%2E1+Complete+Algorithm+Implementations+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+A%2E2+Detailed+Specification+of+Reward+Signals+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+%2E+B+Additional+Experim)

*Updated 30 October 2026*