---
title: "Chaining the Evidence — paper by Zhang et al. (2026)"
description: "They propose Citation-aware Rubric Rewards (CaRR). 40 references. Among them: 0."
authors: ["Jiajie Zhang", "Xin Lv", "Ling Feng", "Lei Hou", "Juanzi Li"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.950/"
doi: "10.18653/v1/2026.acl-long.950"
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/zhang-2026-chaining-evidence-robust-reinforcement-learning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-chaining-evidence-robust-reinforcement-learning/)

[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/26/) / Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

# Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

**Authors:** [Jiajie Zhang](https://md.research.elamur.ai/free/en/authors/jiajie-zhang/), [Xin Lv](https://md.research.elamur.ai/free/en/authors/xin-lv/), [Ling Feng](https://md.research.elamur.ai/free/en/authors/ling-feng/), [Lei Hou](https://md.research.elamur.ai/free/en/authors/lei-hou/) and [Juanzi Li](https://md.research.elamur.ai/free/en/authors/juanzi-li/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.950/) · [PDF](https://aclanthology.org/2026.acl-long.950.pdf) · [DOI 10.18653/v1/2026.acl-long.950](https://doi.org/10.18653/v1/2026.acl-long.950) · [OpenAlex](https://openalex.org/W7166877411)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Deep search agents built on LLMs are usually trained with reinforcement learning using a binary reward: the final answer is either right or wrong. The authors argue that this signal ignores how the answer was reached. Agents can be rewarded for skipping constraints in the question or for guessing correctly despite hallucinated evidence.

They propose Citation-aware Rubric Rewards (CaRR). An LLM splits a synthetic multi-hop question into single-hop factual statements, each containing hidden entities. A judge LLM then counts a statement as satisfied only if three conditions hold:
- the agent names the hidden entities in its response;
- the cited web pages support the statement;
- the statement links to the final answer through a chain of other supported statements.

The reward is the share of satisfied rubrics. C-GRPO extends GRPO by adding this rubric score, weighted by α, only to rollouts whose answer is already correct.

Experiments on 4B and 30B DeepDive models show consistent gains over outcome-only GRPO on four deep search benchmarks. The trained agents also transfer to open-ended report writing, which suggests that rewarding the reasoning process makes agents more robust and factual.

## Key points
- The rubric score is computed in three steps: hidden-entity identification, citation-based rubric judgment, and an evidence connectivity check. Incorrect rollouts receive no rubric bonus, because the authors found that rewarding near-misses can mislead optimization.
- With DeepDive-4B-SFT, the best weight is α=0.3. It scores 17.5 / 24.7 / 54.0 / 50.2 on BC / BC-ZH / xbench-DS / GAIA. With α=0 (outcome reward only), the scores are 14.7 / 17.5 / 41.3 / 41.1. Performance falls again at α=0.5.
- On DeepResearch Bench, which is judged by Gemini-2.5-Pro-preview, the 30B C-GRPO agent reaches 41.99 overall. This compares with 39.30 for GRPO, 36.12 for E-GRPO and 37.51 for SFT. The 30B agent also beats Tongyi-DeepResearch (40.46) and Grok-Deeper-Search (38.22).
- Unlike E-GRPO, CaRR does not need gold annotations of the intermediate entities.
- Limitation: building the rubrics relies on synthetic multi-hop questions being composed of chained single-hop facts. It may not carry over directly to open-ended QA, where some requirements are not stated in the question.

*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 · 415 works · 94,028 citations
- [Zhipu AI](https://md.research.elamur.ai/free/en/companies/zhipu-ai/) — Company, Beijing, China · 24 works · 2,453 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

## Cite

Cite as: Jiajie Zhang, Xin Lv, Ling Feng, Lei Hou and Juanzi Li. 2026. Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{zhang2026chaining,
  title = {{Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards}},
  author = {Jiajie Zhang, Xin Lv, Ling Feng, Lei Hou and Juanzi Li},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.950},
  url = {https://doi.org/10.18653/v1/2026.acl-long.950}
}
```

- [← previous Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents](https://md.research.elamur.ai/free/en/papers/xu-2026-chain-memory-lightweight-memory-construction/)
- [next → CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs](https://md.research.elamur.ai/free/en/papers/lu-2026-chairo-contextual-hierarchical-analogical-induction/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/)

## References

40 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rahul K. Arora, Jason Wei, Rebecca Soskin Hicks, Preston Bowman, Joaquin Quiñonero Candela, Foivos Tsimpourlas, Michael Sharman, Meghan Shah, Andrea Vallone, Alex Beutel, Johannes Heidecke, and Karan Singhal. 2025. [Healthbench: Evaluating large language models towards improved human health](https://md.research.elamur.ai/free/en/papers/arora-2025-healthbench-evaluating-large-language-models/). CoRR, ab…
2. Akari Asai, Jacqueline He, Rulin Shao, Weijia Shi, Amanpreet Singh, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Sergey Feldman, Mike D’Arcy, David Wadden, Matt Latzke, Minyang Tian, Pan Ji, Shengyan Liu, Hao Tong, Bohao Wu, Yanyu Xiong, Luke Zettlemoyer, and 6 others. 2024. [Openscholar: Synthesizing…](https://md.research.elamur.ai/free/en/papers/asai-2024-openscholar-synthesizing-scientific-literature/)
3. DeepSeek. 2025. Deepseek-v3.1 release. [find](https://scholar.google.com/scholar?q=DeepSeek%2E+2025%2E+Deepseek%2Dv3%2E1+release%2E)
4. Guanting Dong, Licheng Bao, Zhongyuan Wang, Kangzhi Zhao, Xiaoxi Li, Jiajie Jin, Jinghan Yang, Hangyu Mao, Fuzheng Zhang, Kun Gai, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, and Zhicheng Dou. 2025a. Agentic entropy-balanced policy optimization. CoRR, abs/2510.14545. — [arXiv:2510.14545](https://arxiv.org/abs/2510.14545) [find](https://scholar.google.com/scholar?q=Guanting+Dong%2C+Licheng+Bao%2C+Zhongyuan+Wang%2C+Kangzhi+Zhao%2C+Xiaoxi+Li%2C+Jiajie+Jin%2C+Jinghan+Yang%2C+Hangyu+Mao%2C+Fuzheng+Zhang%2C+Kun+Gai%2C+Guorui+Zhou%2C+Yutao+Zhu%2C+Ji%2DRong+Wen%2C+and+Zhicheng+Dou%2E+2025a%2E+Agentic)
5. Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, and Jingren Zhou. 2025b. Self-play with execution feedback: Improving instruction-following capabilities of large language models. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, A… [find](https://scholar.google.com/scholar?q=Guanting+Dong%2C+Keming+Lu%2C+Chengpeng+Li%2C+Tingyu+Xia%2C+Bowen+Yu%2C+Chang+Zhou%2C+and+Jingren+Zhou%2E+2025b%2E+Self%2Dplay+with+execution+feedback%3A+Improving+instruction%2Dfollowing+capabilities+of+large+language+mod)
6. Guanting Dong, Hangyu Mao, Kai Ma, Licheng Bao, Yifei Chen, Zhongyuan Wang, Zhongxia Chen, Jiazhen Du, Huiyang Wang, Fuzheng Zhang, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, and Zhicheng Dou. 2025c. Agentic reinforced policy optimization. CoRR, abs/2507.19849. — [arXiv:2507.19849](https://arxiv.org/abs/2507.19849) [find](https://scholar.google.com/scholar?q=Guanting+Dong%2C+Hangyu+Mao%2C+Kai+Ma%2C+Licheng+Bao%2C+Yifei+Chen%2C+Zhongyuan+Wang%2C+Zhongxia+Chen%2C+Jiazhen+Du%2C+Huiyang+Wang%2C+Fuzheng+Zhang%2C+Guorui+Zhou%2C+Yutao+Zhu%2C+Ji%2DRong+Wen%2C+and+Zhicheng+Dou%2E+2025c%2E+Agenti)
7. Lang Feng, Zhenghai Xue, Tingcong Liu, and Bo An. 2025. [Group-in-group policy optimization for LLM agent training](https://md.research.elamur.ai/free/en/papers/feng-2025-group-group-policy-optimization-llm/). CoRR, abs/2505.10978.
8. Jiaxuan Gao, Wei Fu, Minyang Xie, Shusheng Xu, Chuyi He, Zhiyu Mei, Banghua Zhu, and Yi Wu. 2025. Beyond ten turns: Unlocking long-horizon agentic search with large-scale asynchronous RL. CoRR, abs/2508.07976. — [arXiv:2508.07976](https://arxiv.org/abs/2508.07976) [find](https://scholar.google.com/scholar?q=Jiaxuan+Gao%2C+Wei+Fu%2C+Minyang+Xie%2C+Shusheng+Xu%2C+Chuyi+He%2C+Zhiyu+Mei%2C+Banghua+Zhu%2C+and+Yi+Wu%2E+2025%2E+Beyond+ten+turns%3A+Unlocking+long%2Dhorizon+agentic+search+with+large%2Dscale+asynchronous+RL%2E+CoRR%2C+abs%2F25)
9. Google. 2025. Gemini 2.5 pro preview: even better coding performance. [find](https://scholar.google.com/scholar?q=Google%2E+2025%2E+Gemini+2%2E5+pro+preview%3A+even+better+coding+performance%2E)
10. Anisha Gunjal, Anthony Wang, Elaine Lau, Vaskar Nath, Bing Liu, and Sean Hendryx. 2025. [Rubrics as rewards: Reinforcement learning beyond verifiable domains](https://md.research.elamur.ai/free/en/papers/gunjal-2025-rubrics-rewards-reinforcement-learning-verifiable/). CoRR, abs/2507.17746.
11. Bowen Jin, Hansi Zeng, Zhenrui Yue, 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/). CoRR, abs/2503.09516.
12. Bowen Jin, Hansi Zeng, Zhenrui Yue, Dong Wang, Hamed Zamani, and Jiawei Han. 2025b. [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/). CoRR, abs/2503.09516.
13. Kimi. 2025. Kimi-researcher: End-to-end rl training for emerging agentic capabilities. [find](https://scholar.google.com/scholar?q=Kimi%2E+2025%2E+Kimi%2Dresearcher%3A+End%2Dto%2Dend+rl+training+for+emerging+agentic+capabilities%2E)
14. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, and 4 other… — [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://md.research.elamur.ai/free/en/papers/lambert-2024-tulu-3-pushing-frontiers-open/)
15. Kuan Li, Zhongwang Zhang, Huifeng Yin, Rui Ye, Yida Zhao, Liwen Zhang, Litu Ou, Dingchu Zhang, Xixi Wu, Jialong Wu, Xinyu Wang, Zile Qiao, Zhen Zhang, Yong Jiang, Pengjun Xie, Fei Huang, and Jingren Zhou. 2025a. Websailor-v2: Bridging the chasm to proprietary agents via synthetic data and scalable r… — [arXiv:2509.13305](https://arxiv.org/abs/2509.13305) [find](https://scholar.google.com/scholar?q=Kuan+Li%2C+Zhongwang+Zhang%2C+Huifeng+Yin%2C+Rui+Ye%2C+Yida+Zhao%2C+Liwen+Zhang%2C+Litu+Ou%2C+Dingchu+Zhang%2C+Xixi+Wu%2C+Jialong+Wu%2C+Xinyu+Wang%2C+Zile+Qiao%2C+Zhen+Zhang%2C+Yong+Jiang%2C+Pengjun+Xie%2C+Fei+Huang%2C+and+Jingren+Z)
16. Kuan Li, Zhongwang Zhang, Huifeng Yin, Liwen Zhang, Litu Ou, Jialong Wu, Wenbiao Yin, Baixuan Li, Zhengwei Tao, Xinyu Wang, Weizhou Shen, Junkai Zhang, Dingchu Zhang, Xixi Wu, Yong Jiang, Ming Yan, Pengjun Xie, Fei Huang, and Jingren Zhou. 2025b. Websailor: Navigating super-human reasoning for web a… [find](https://scholar.google.com/scholar?q=Kuan+Li%2C+Zhongwang+Zhang%2C+Huifeng+Yin%2C+Liwen+Zhang%2C+Litu+Ou%2C+Jialong+Wu%2C+Wenbiao+Yin%2C+Baixuan+Li%2C+Zhengwei+Tao%2C+Xinyu+Wang%2C+Weizhou+Shen%2C+Junkai+Zhang%2C+Dingchu+Zhang%2C+Xixi+Wu%2C+Yong+Jiang%2C+Ming+Yan%2C+Pe)
17. Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, and 1 others. 2025a. [Deepseek-v3](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/). 2: Pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556.
18. Junteng Liu, Yunji Li, Chi Zhang, Jingyang Li, Aili Chen, Ke Ji, Weiyu Cheng, Zijia Wu, Chengyu Du, Qidi Xu, Jiayuan Song, Zhengmao Zhu, Wenhu Chen, Pengyu Zhao, and Junxian He. 2025b. Webexplorer: Explore and evolve for training long-horizon web agents. CoRR, abs/2509.06501. — [arXiv:2509.06501](https://arxiv.org/abs/2509.06501) [find](https://scholar.google.com/scholar?q=Junteng+Liu%2C+Yunji+Li%2C+Chi+Zhang%2C+Jingyang+Li%2C+Aili+Chen%2C+Ke+Ji%2C+Weiyu+Cheng%2C+Zijia+Wu%2C+Chengyu+Du%2C+Qidi+Xu%2C+Jiayuan+Song%2C+Zhengmao+Zhu%2C+Wenhu+Chen%2C+Pengyu+Zhao%2C+and+Junxian+He%2E+2025b%2E+Webexplorer%3A+Ex)
19. Rui Lu, Zhenyu Hou, Zihan Wang, Hanchen Zhang, Xiao Liu, Yujiang Li, Shi Feng, Jie Tang, and Yuxiao Dong. 2025. Deepdive: Advancing deep search agents with knowledge graphs and multi-turn RL. CoRR, abs/2509.10446. — [arXiv:2509.10446](https://arxiv.org/abs/2509.10446) [find](https://scholar.google.com/scholar?q=Rui+Lu%2C+Zhenyu+Hou%2C+Zihan+Wang%2C+Hanchen+Zhang%2C+Xiao+Liu%2C+Yujiang+Li%2C+Shi+Feng%2C+Jie+Tang%2C+and+Yuxiao+Dong%2E+2025%2E+Deepdive%3A+Advancing+deep+search+agents+with+knowledge+graphs+and+multi%2Dturn+RL%2E+CoRR%2C+ab)
20. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2024. [GAIA: a benchmark for general AI assistants](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/). In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net.
21. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). CoRR, abs/2402.03300.
22. GLM Team. 2025a. [GLM-4.5: agentic, reasoning, and coding (ARC) foundation models](https://md.research.elamur.ai/free/en/papers/team-2025-4-glm-4-5-agentic/). CoRR, abs/2508.06471.
23. Qwen Team. 2025b. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). CoRR, abs/2505.09388.
24. Tongyi DeepResearch Team, Baixuan Li, Bo Zhang, Dingchu Zhang, Fei Huang, Guangyu Li, Guoxin Chen, Huifeng Yin, Jialong Wu, Jingren Zhou, and 1 others. 2025. Tongyi deepresearch technical report. arXiv preprint arXiv:2510.24701. — [arXiv:2510.24701](https://arxiv.org/abs/2510.24701) [find](https://scholar.google.com/scholar?q=Tongyi+DeepResearch+Team%2C+Baixuan+Li%2C+Bo+Zhang%2C+Dingchu+Zhang%2C+Fei+Huang%2C+Guangyu+Li%2C+Guoxin+Chen%2C+Huifeng+Yin%2C+Jialong+Wu%2C+Jingren+Zhou%2C+and+1+others%2E+2025%2E+Tongyi+deepresearch+technical+report%2E+arXi)
25. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Jirong Wen. 2024. [A survey on large language model based autonomous agents](https://md.research.elamur.ai/free/en/papers/wang-2023-survey-large-language-model-based/). Frontiers Comput. Sci., 18(6):186345.
26. Jason Wei, Zhiqing Sun, Spencer Papay, Scott McKinney, Jeffrey Han, Isa Fulford, Hyung Won Chung, Alex Tachard Passos, William Fedus, and Amelia Glaese. 2025. [Browsecomp: A simple yet challenging benchmark for browsing agents](https://md.research.elamur.ai/free/en/papers/wei-2025-browsecomp-simple-yet-challenging-benchmark/). CoRR, abs/2504.12516.
27. Jialong Wu, Baixuan Li, Runnan Fang, Wenbiao Yin, Liwen Zhang, Zhengwei Tao, Dingchu Zhang, Zekun Xi, Yong Jiang, Pengjun Xie, Fei Huang, and Jingren Zhou. 2025a. [Webdancer: Towards autonomous information seeking agency](https://md.research.elamur.ai/free/en/papers/wu-2025-webdancer-towards-autonomous-information-seeking/). CoRR, abs/2505.22648.
28. OpenAI. 2025a. Deep research system card. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025a%2E+Deep+research+system+card%2E)
29. OpenAI. 2025b. Introducing gpt-5. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025b%2E+Introducing+gpt%2D5%2E)
30. OpenAI. 2025c. Introducing o3 and o4-mini. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025c%2E+Introducing+o3+and+o4%2Dmini%2E)
31. Hao Peng, Yunjia Qi, Xiaozhi Wang, Bin Xu, Lei Hou, and Juanzi Li. 2025. [Verif: Verification engineering for reinforcement learning in instruction following](https://md.research.elamur.ai/free/en/papers/peng-2025-verif-verification-engineering-reinforcement-learning/). CoRR, abs/2506.09942.
32. Mian Wu, Gavin Zhang, Sewon Min, Sergey Levine, and Aviral Kumar. 2025b. RLAC: reinforcement learning with adversarial critic for free-form generation tasks. CoRR, abs/2511.01758. — [arXiv:2511.01758](https://arxiv.org/abs/2511.01758) [find](https://scholar.google.com/scholar?q=Mian+Wu%2C+Gavin+Zhang%2C+Sewon+Min%2C+Sergey+Levine%2C+and+Aviral+Kumar%2E+2025b%2E+RLAC%3A+reinforcement+learning+with+adversarial+critic+for+free%2Dform+generation+tasks%2E+CoRR%2C+abs%2F2511%2E01758%2E+%E2%80%94+%5BarXiv%3A2511%2E01758%5D)
33. MohammadHossein Rezaei, Robert Vacareanu, Zihao Wang, Clinton Wang, Bing Liu, Yunzhong He, and Afra Feyza Akyürek. 2025. Online rubrics elicitation from pairwise comparisons. CoRR, abs/2510.07284. xAI Team. 2025. Grok agents: Combining reasoning and tool use. [https://x.ai/news/grok-3\#](https://x.ai/news/grok-3\#) grok-agents-co… — [arXiv:2510.07284](https://arxiv.org/abs/2510.07284) [↗](https://x.ai/news/grok-3\#)
34. Serper. 2025. Serper: Google search api. [find](https://scholar.google.com/scholar?q=Serper%2E+2025%2E+Serper%3A+Google+search+api%2E)
35. Rulin Shao, Akari Asai, Shannon Zejiang Shen, Hamish Ivison, Varsha Kishore, Jingming Zhuo, Xinran Zhao, Molly Park, Samuel G Finlayson, David Sontag, and 1 others. 2025a. [Dr tulu: Reinforcement learning with evolving rubrics for deep research](https://md.research.elamur.ai/free/en/papers/shao-2025-dr-tulu-reinforcement-learning-evolving/). arXiv preprint arXiv:2511.19399.
36. Zhihong Shao, Yuxiang Luo, Chengda Lu, ZZ Ren, Jiewen Hu, Tian Ye, Zhibin Gou, Shirong Ma, and Xiaokang Zhang. 2025b. [Deepseekmath-v2: Towards self-verifiable mathematical reasoning](https://md.research.elamur.ai/free/en/papers/shao-2025-deepseekmath-v2-self-verifiable/). arXiv preprint arXiv:2511.22570.
37. Xbench-Team. 2025. Xbench-deepsearch. [find](https://scholar.google.com/scholar?q=Xbench%2DTeam%2E+2025%2E+Xbench%2Ddeepsearch%2E)
38. 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, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net.
39. Yida Zhao, Kuan Li, Xixi Wu, Liwen Zhang, Dingchu Zhang, Baixuan Li, Maojia Song, Zhuo Chen, Chenxi Wang, Xinyu Wang, Kewei Tu, Pengjun Xie, Jingren Zhou, and Yong Jiang. 2025. Repurposing synthetic data for fine-grained search agent supervision. CoRR, abs/2510.24694. — [arXiv:2510.24694](https://arxiv.org/abs/2510.24694) [find](https://scholar.google.com/scholar?q=Yida+Zhao%2C+Kuan+Li%2C+Xixi+Wu%2C+Liwen+Zhang%2C+Dingchu+Zhang%2C+Baixuan+Li%2C+Maojia+Song%2C+Zhuo+Chen%2C+Chenxi+Wang%2C+Xinyu+Wang%2C+Kewei+Tu%2C+Pengjun+Xie%2C+Jingren+Zhou%2C+and+Yong+Jiang%2E+2025%2E+Repurposing+synthetic+d)
40. Peilin Zhou, Bruce Leon, Xiang Ying, Can Zhang, Yifan Shao, Qichen Ye, Dading Chong, Zhiling Jin, Chenxuan Xie, Meng Cao, Yuxin Gu, Sixin Hong, Jing Ren, Jian Chen, Chao Liu, and Yining Hua. 2025. Browsecomp-zh: Benchmarking web browsing ability of large language models in chinese. CoRR, abs/2504.19… — [arXiv:2504.19314](https://arxiv.org/abs/2504.19314) [find](https://scholar.google.com/scholar?q=Peilin+Zhou%2C+Bruce+Leon%2C+Xiang+Ying%2C+Can+Zhang%2C+Yifan+Shao%2C+Qichen+Ye%2C+Dading+Chong%2C+Zhiling+Jin%2C+Chenxuan+Xie%2C+Meng+Cao%2C+Yuxin+Gu%2C+Sixin+Hong%2C+Jing+Ren%2C+Jian+Chen%2C+Chao+Liu%2C+and+Yining+Hua%2E+2025%2E+Bro)

*Updated 2 November 2026*