---
title: "Mitigating Context Interference for Reliable and Efficient Search"
description: "Based on this, the authors build a distilled dataset that pairs retrieved documents with condensed versions keeping only the… 59 references."
authors: ["Boyang Xue", "Bin Wu", "Shuofei Qiao", "Sheng Wang", "Rui Wang", "Yiming Du", "Hongru Wang", "Jeff Z. Pan", "Emine Yilmaz", "Kam-Fai Wong", "Aldo Lipani"]
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.160/"
doi: "10.18653/v1/2026.acl-long.160"
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/xue-2026-mitigating-context-interference-reliable-efficient/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xue-2026-mitigating-context-interference-reliable-efficient/)

[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/41/) / Mitigating Context Interference for Reliable and Efficient Search Agents

# Mitigating Context Interference for Reliable and Efficient Search Agents

**Authors:** [Boyang Xue](https://md.research.elamur.ai/free/en/authors/boyang-xue/), [Bin Wu](https://md.research.elamur.ai/free/en/authors/bin-wu/), [Shuofei Qiao](https://md.research.elamur.ai/free/en/authors/shuofei-qiao/), [Sheng Wang](https://md.research.elamur.ai/free/en/authors/sheng-wang/), [Rui Wang](https://md.research.elamur.ai/free/en/authors/rui-wang/), [Yiming Du](https://md.research.elamur.ai/free/en/authors/yiming-du/), [Hongru Wang](https://md.research.elamur.ai/free/en/authors/hongru-wang/), [Jeff Z. Pan](https://md.research.elamur.ai/free/en/authors/jeff-z-pan/), [Emine Yilmaz](https://md.research.elamur.ai/free/en/authors/emine-yilmaz/), [Kam-Fai Wong](https://md.research.elamur.ai/free/en/authors/kam-fai-wong/) and [Aldo Lipani](https://md.research.elamur.ai/free/en/authors/aldo-lipani/) · **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.160/) · [PDF](https://aclanthology.org/2026.acl-long.160.pdf) · [DOI 10.18653/v1/2026.acl-long.160](https://doi.org/10.18653/v1/2026.acl-long.160) · [OpenAlex](https://openalex.org/W7166880248)

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

## Summary
Multi-turn LLM search agents repeatedly query a retriever and add the returned documents to their working context. Much of that material is noise, and it can pull the model toward wrong facts. The authors call this effect "context interference." They study it on closed-book QA benchmarks covering single-hop tasks (NQ, TriviaQA, PopQA) and multi-hop tasks (HotpotQA, Musique, Bamboogle).

Masking different parts of the agent's history shows that the most recently retrieved documents cause most of the harm. Earlier queries and documents contribute only a little. Based on this, the authors build a distilled dataset that pairs retrieved documents with condensed versions keeping only the information relevant to the query. They use it to train a context refiner that cleans each new retrieval before the agent reasons over it.

They then add the refiner to GRPO-based RL training, a method they call CRRL. This gives higher Exact Match than the baselines, along with fewer retrievals, shorter contexts and faster inference. The work argues for a "refine context, then generate" design for AI agents.

## Key points
- **Source of interference:** it comes mainly from the latest retrieved documents. In a PopQA example, refining a 1,287-token document down to 143 tokens corrects the agent's answer.
- **Training setup:**
  - RL data: 40k examples sampled from NQ and HotpotQA training sets.
  - Evaluation: seven QA sets, both in-domain and out-of-domain.
  - Implementation: GRPO built on Verl.
  - Base models: Qwen2.5-7b and Qwen2.5-3b.
- **Baselines:**
  - Retrieval-free: SFT and GRPO.
  - Retrieval-based: RFT via rejection sampling, Search-GRPO, Search-o1 and IRCoT.
- **Efficiency on Qwen2.5-7b (CRRL vs. Search-GRPO vs. IRCoT):**
  - Average retrievals: 1.6 vs. 2.1 vs. 2.6.
  - Average context length: 0.7k vs. 0.9k vs. 2.3k.
  - Time per question: 16.9s vs. 17.7s vs. 22.4s.
- **Code:** released at github.com/AmourWaltz/CRRL.
- **Limitations:** the refiner is an external add-on module, and other agent tasks such as tool use or planning are not studied.

*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

- [University of Edinburgh](https://md.research.elamur.ai/free/en/universities/university-of-edinburgh/) — University, Edinburgh, United Kingdom · 381 works · 80,747 citations
- [University College London](https://md.research.elamur.ai/free/en/universities/university-college-london/) — University, London, United Kingdom · 107 works · 22,924 citations
- [Chinese University of Hong Kong](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/) — University, Hong Kong, China · 159 works · 16,154 citations
- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 224 works · 13,587 citations
- [University of Hong Kong](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/) — University, Pok Fu Lam, China · 118 works · 13,496 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: Boyang Xue, Bin Wu, Shuofei Qiao, Sheng Wang, Rui Wang, Yiming Du, Hongru Wang, Jeff Z. Pan, Emine Yilmaz, Kam-Fai Wong and Aldo Lipani. 2026. Mitigating Context Interference for Reliable and Efficient Search Agents. 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{xue2026mitigating,
  title = {{Mitigating Context Interference for Reliable and Efficient Search Agents}},
  author = {Boyang Xue, Bin Wu, Shuofei Qiao, Sheng Wang, Rui Wang, Yiming Du, Hongru Wang, Jeff Z. Pan, Emine Yilmaz, Kam-Fai Wong and Aldo Lipani},
  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.160},
  url = {https://doi.org/10.18653/v1/2026.acl-long.160}
}
```

- [← previous Mitigating Causal Bias in LLMs via Potential Outcomes Framework and Actual Causality Theory](https://md.research.elamur.ai/free/en/papers/zhao-2026-mitigating-causal-bias-llms-potential/)
- [next → Mitigating Coordinate Prediction Bias from Positional Encoding Failures](https://md.research.elamur.ai/free/en/papers/tao-2026-mitigating-coordinate-prediction-bias-positional/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/)

## References

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

1. Mingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z. Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou, and Weipeng Chen. 2025. [Research: Learning to reason with search for llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/chen-2025-research-learning-reason-search-llms/). Preprint, arXiv:2503.19470.
2. Eric Nuertey Coleman, Julio Hurtado, and Vincenzo Lomonaco. 2023. In-context interference in chat-based large language models. Preprint, arXiv:2309.12727. — [arXiv:2309.12727](https://arxiv.org/abs/2309.12727) [find](https://scholar.google.com/scholar?q=Eric+Nuertey+Coleman%2C+Julio+Hurtado%2C+and+Vincenzo+Lomonaco%2E+2023%2E+In%2Dcontext+interference+in+chat%2Dbased+large+language+models%2E+Preprint%2C+arXiv%3A2309%2E12727%2E+%E2%80%94+%5BarXiv%3A2309%2E12727%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F23)
3. DeepSeek-AI. 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/). Preprint, arXiv:2501.12948.
4. Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Ji-Rong Wen, and Zhicheng Dou. 2025. Understand what llm needs: Dual preference alignment for retrieval-augmented generation. In Proceedings of the ACM on Web Conference 2025, WWW ’25, page 4206–4225, New York, NY, USA. Association for Computing… [find](https://scholar.google.com/scholar?q=Guanting+Dong%2C+Yutao+Zhu%2C+Chenghao+Zhang%2C+Zechen+Wang%2C+Ji%2DRong+Wen%2C+and+Zhicheng+Dou%2E+2025%2E+Understand+what+llm+needs%3A+Dual+preference+alignment+for+retrieval%2Daugmented+generation%2E+In+Proceedings+of+t)
5. Tianqing Fang, Zhisong Zhang, Xiaoyang Wang, Rui Wang, Can Qin, Yuxuan Wan, Jun-Yu Ma, Ce Zhang, Jiaqi Chen, Xiyun Li, Hongming Zhang, Haitao Mi, and Dong Yu. 2025. Cognitive kernel-pro: A framework for deep research agents and agent foundation models training. Preprint, arXiv:2508.00414. — [arXiv:2508.00414](https://arxiv.org/abs/2508.00414) [find](https://scholar.google.com/scholar?q=Tianqing+Fang%2C+Zhisong+Zhang%2C+Xiaoyang+Wang%2C+Rui+Wang%2C+Can+Qin%2C+Yuxuan+Wan%2C+Jun%2DYu+Ma%2C+Ce+Zhang%2C+Jiaqi+Chen%2C+Xiyun+Li%2C+Hongming+Zhang%2C+Haitao+Mi%2C+and+Dong+Yu%2E+2025%2E+Cognitive+kernel%2Dpro%3A+A+framework+f)
6. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2024. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). Preprint, arXiv:2312.10997.
7. Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Naik, Pengshan Cai, and Alfio Gliozzo. 2022. [Re2G: Retrieve, rerank, generate](https://md.research.elamur.ai/free/en/papers/glass-2022-re2g-retrieve-rerank-generate/). In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages…
8. Akash Gupta, Ivaxi Sheth, Vyas Raina, Mark Gales, and Mario Fritz. 2024. LLM task interference: An initial study on the impact of task-switch in conversational 3549 9 history. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14633–14652, Miami, Florida… [find](https://scholar.google.com/scholar?q=Akash+Gupta%2C+Ivaxi+Sheth%2C+Vyas+Raina%2C+Mark+Gales%2C+and+Mario+Fritz%2E+2024%2E+LLM+task+interference%3A+An+initial+study+on+the+impact+of+task%2Dswitch+in+conversational+3549+9+history%2E+In+Proceedings+of+the+20)
9. Leslie Pack Kaelbling, Michael L Littman, and Andrew W Moore. 1996. Reinforcement learning: A survey. Journal of artificial intelligence research, 4:237–285. [find](https://scholar.google.com/scholar?q=Leslie+Pack+Kaelbling%2C+Michael+L+Littman%2C+and+Andrew+W+Moore%2E+1996%2E+Reinforcement+learning%3A+A+survey%2E+Journal+of+artificial+intelligence+research%2C+4%3A237%E2%80%93285%2E)
10. Muhammad Haseeb. 2025. Context engineering for multi-agent llm code assistants using elicit, notebooklm, chatgpt, and claude code. Preprint, arXiv:2508.08322. — [arXiv:2508.08322](https://arxiv.org/abs/2508.08322) [find](https://scholar.google.com/scholar?q=Muhammad+Haseeb%2E+2025%2E+Context+engineering+for+multi%2Dagent+llm+code+assistants+using+elicit%2C+notebooklm%2C+chatgpt%2C+and+claude+code%2E+Preprint%2C+arXiv%3A2508%2E08322%2E+%E2%80%94+%5BarXiv%3A2508%2E08322%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
11. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. [Dense passage retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Onli…
12. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. [Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps](https://md.research.elamur.ai/free/en/papers/ho-2020-constructing-multi-hop-qa-dataset/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609–6625, Barcelona, Spain (Online). International Comm…
13. Ziyang Huang, Xiaowei Yuan, Yiming Ju, Jun Zhao, and Kang Liu. 2025. Reinforced internal-external knowledge synergistic reasoning for efficient adaptive search agent. Preprint, arXiv:2505.07596. — [arXiv:2505.07596](https://arxiv.org/abs/2505.07596) [find](https://scholar.google.com/scholar?q=Ziyang+Huang%2C+Xiaowei+Yuan%2C+Yiming+Ju%2C+Jun+Zhao%2C+and+Kang+Liu%2E+2025%2E+Reinforced+internal%2Dexternal+knowledge+synergistic+reasoning+for+efficient+adaptive+search+agent%2E+Preprint%2C+arXiv%3A2505%2E07596%2E+%E2%80%94+%5Bar)
14. Léo Jacqmin, Lina M. Rojas Barahona, and Benoit Favre. 2022. “do you follow me?”: A survey of recent approaches in dialogue state tracking. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 336–350, Edinburgh, UK. Association for Computational L… [find](https://scholar.google.com/scholar?q=L%C3%A9o+Jacqmin%2C+Lina+M%2E+Rojas+Barahona%2C+and+Benoit+Favre%2E+2022%2E+%E2%80%9Cdo+you+follow+me%3F%E2%80%9D%3A+A+survey+of+recent+approaches+in+dialogue+state+tracking%2E+In+Proceedings+of+the+23rd+Annual+Meeting+of+the+Special+Int)
15. Xinda Jia, Jinpeng Li, Zezhong Wang, Jingjing Li, Xingshan Zeng, Yasheng Wang, Weinan Zhang, Yong Yu, and Weiwen Liu. 2025. Fast, slow, and tool-augmented thinking for llms: A review. Preprint, arXiv:2508.12265. — [arXiv:2508.12265](https://arxiv.org/abs/2508.12265) [find](https://scholar.google.com/scholar?q=Xinda+Jia%2C+Jinpeng+Li%2C+Zezhong+Wang%2C+Jingjing+Li%2C+Xingshan+Zeng%2C+Yasheng+Wang%2C+Weinan+Zhang%2C+Yong+Yu%2C+and+Weiwen+Liu%2E+2025%2E+Fast%2C+slow%2C+and+tool%2Daugmented+thinking+for+llms%3A+A+review%2E+Preprint%2C+arXiv%3A)
16. Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023. [LLMLingua: Compressing prompts for accelerated inference of large language models](https://md.research.elamur.ai/free/en/papers/jiang-2023-llmlingua-compressing-prompts-accelerated-inference/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13358–13376, Singapore. Association for Compu…
17. Ming Jiang, Tingting Huang, Biao Guo, Yao Lu, and Feng Zhang. 2025. Enhancing robustness in large language models: Prompting for mitigating the impact of irrelevant information. Preprint, arXiv:2408.10615. — [arXiv:2408.10615](https://arxiv.org/abs/2408.10615) [find](https://scholar.google.com/scholar?q=Ming+Jiang%2C+Tingting+Huang%2C+Biao+Guo%2C+Yao+Lu%2C+and+Feng+Zhang%2E+2025%2E+Enhancing+robustness+in+large+language+models%3A+Prompting+for+mitigating+the+impact+of+irrelevant+information%2E+Preprint%2C+arXiv%3A2408%2E1)
18. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. [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/). Preprint, arXiv:2503.09516.
19. Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. 2017. [TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611, Vancouver…
20. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, and 1 others. 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 Lin…
21. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
22. Philippe Laban, Hiroaki Hayashi, Yingbo Zhou, and Jennifer Neville. 2025. [Llms get lost in multi-turn conversation](https://md.research.elamur.ai/free/en/papers/laban-2025-llms-get-lost-multi-turn/). Preprint, arXiv:2505.06120.
23. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
24. Mukai Li, Qingcheng Zeng, Tianqing Fang, Zhenwen Liang, Linfeng Song, Qi Liu, Haitao Mi, and Dong Yu. 2026. Verified critical step optimization for LLM agents. CoRR, abs/2602.03412. [find](https://scholar.google.com/scholar?q=Mukai+Li%2C+Qingcheng+Zeng%2C+Tianqing+Fang%2C+Zhenwen+Liang%2C+Linfeng+Song%2C+Qi+Liu%2C+Haitao+Mi%2C+and+Dong+Yu%2E+2026%2E+Verified+critical+step+optimization+for+LLM+agents%2E+CoRR%2C+abs%2F2602%2E03412%2E)
25. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025a. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 5420–5438, Suzhou, China. Asso…
26. Yinheng Li, Shaofei Wang, Han Ding, and Hang Chen. 2023. Large language models in finance: A survey. In Proceedings of the Fourth ACM International Conference on AI in Finance, ICAIF ’23, page 374–382, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Yinheng+Li%2C+Shaofei+Wang%2C+Han+Ding%2C+and+Hang+Chen%2E+2023%2E+Large+language+models+in+finance%3A+A+survey%2E+In+Proceedings+of+the+Fourth+ACM+International+Conference+on+AI+in+Finance%2C+ICAIF+%E2%80%9923%2C+page+374%E2%80%93382)
27. Yubo Li, Xiaobin Shen, Xinyu Yao, Xueying Ding, Yidi Miao, Ramayya Krishnan, and Rema Padman. 2025b. Beyond single-turn: A survey on multi-turn interactions with large language models. Preprint, arXiv:2504.04717. 3550 10 — [arXiv:2504.04717](https://arxiv.org/abs/2504.04717) [find](https://scholar.google.com/scholar?q=Yubo+Li%2C+Xiaobin+Shen%2C+Xinyu+Yao%2C+Xueying+Ding%2C+Yidi+Miao%2C+Ramayya+Krishnan%2C+and+Rema+Padman%2E+2025b%2E+Beyond+single%2Dturn%3A+A+survey+on+multi%2Dturn+interactions+with+large+language+models%2E+Preprint%2C+arXiv)
28. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (V… [find](https://scholar.google.com/scholar?q=Alex+Mallen%2C+Akari+Asai%2C+Victor+Zhong%2C+Rajarshi+Das%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+When+not+to+trust+language+models%3A+Investigating+effectiveness+of+parametric+and+non%2Dparametric+mem)
29. Thang Nguyen, Peter Chin, and Yu-Wing Tai. 2025. [Ma-rag: Multi-agent retrieval-augmented generation via collaborative chain-of-thought reasoning](https://md.research.elamur.ai/free/en/papers/nguyen-2025-ma-rag-multi-agent-retrieval/). Preprint, arXiv:2505.20096.
30. OpenAI. 2023. Gpt-4. Https://openai.com/index/gpt-4-research/. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2023%2E+Gpt%2D4%2E+Https%3A%2F%2Fopenai%2Ecom%2Findex%2Fgpt%2D4%2Dresearch%2F%2E)
31. OpenAI. 2025. Introducing gpt-5. Https://openai.com/index/introducing-gpt-5/. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Introducing+gpt%2D5%2E+Https%3A%2F%2Fopenai%2Ecom%2Findex%2Fintroducing%2Dgpt%2D5%2F%2E)
32. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 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.
33. Cheng Peng, Xi Yang, Aokun Chen, Kaleb E Smith, Nima PourNejatian, Anthony B Costa, Cheryl Martin, Mona G Flores, Ying Zhang, Tanja Magoc, and 1 others. 2023. A study of generative large language model for medical research and healthcare. NPJ digital medicine, 6(1):210. [find](https://scholar.google.com/scholar?q=Cheng+Peng%2C+Xi+Yang%2C+Aokun+Chen%2C+Kaleb+E+Smith%2C+Nima+PourNejatian%2C+Anthony+B+Costa%2C+Cheryl+Martin%2C+Mona+G+Flores%2C+Ying+Zhang%2C+Tanja+Magoc%2C+and+1+others%2E+2023%2E+A+study+of+generative+large+language+mode)
34. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah Smith, and Mike Lewis. 2023. Measuring and narrowing the compositionality gap in language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5687–5711, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ofir+Press%2C+Muru+Zhang%2C+Sewon+Min%2C+Ludwig+Schmidt%2C+Noah+Smith%2C+and+Mike+Lewis%2E+2023%2E+Measuring+and+narrowing+the+compositionality+gap+in+language+models%2E+In+Findings+of+the+Association+for+Computation)
35. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, and 1 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=Qwen%2C+%3A%2C+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+and+1+others%2E+2025%2E+Qwen2%2E5+technical+report%2E+Preprint%2C+arXiv%3A2412%2E15)
36. Meghana Rajeev, Rajkumar Ramamurthy, Prapti Trivedi, Vikas Yadav, Oluwanifemi Bamgbose, Sathwik Tejaswi Madhusudan, James Zou, and Nazneen Rajani. 2025. Cats confuse reasoning llm: Query agnostic adversarial triggers for reasoning models. Preprint, arXiv:2503.01781. — [arXiv:2503.01781](https://arxiv.org/abs/2503.01781) [find](https://scholar.google.com/scholar?q=Meghana+Rajeev%2C+Rajkumar+Ramamurthy%2C+Prapti+Trivedi%2C+Vikas+Yadav%2C+Oluwanifemi+Bamgbose%2C+Sathwik+Tejaswi+Madhusudan%2C+James+Zou%2C+and+Nazneen+Rajani%2E+2025%2E+Cats+confuse+reasoning+llm%3A+Query+agnostic+adve)
37. Amirhossein Razavi, Mina Soltangheis, Negar Arabzadeh, Sara Salamat, Morteza Zihayat, and Ebrahim Bagheri. 2025. Benchmarking prompt sensitivity in large language models. In Advances in Information Retrieval: 47th European Conference on Information Retrieval, ECIR 2025, Lucca, Italy, April 6–10, 202… [find](https://scholar.google.com/scholar?q=Amirhossein+Razavi%2C+Mina+Soltangheis%2C+Negar+Arabzadeh%2C+Sara+Salamat%2C+Morteza+Zihayat%2C+and+Ebrahim+Bagheri%2E+2025%2E+Benchmarking+prompt+sensitivity+in+large+language+models%2E+In+Advances+in+Information+Re)
38. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. [find](https://scholar.google.com/scholar?q=Timo+Schick%2C+Jane+Dwivedi%2DYu%2C+Roberto+Dess%C3%AC%2C+Roberta+Raileanu%2C+Maria+Lomeli%2C+Eric+Hambro%2C+Luke+Zettlemoyer%2C+Nicola+Cancedda%2C+and+Thomas+Scialom%2E+2023%2E)
39. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). Advances in Neural Information Processing Systems, 36:68539–68551.
40. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. 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+Preprint%2C+arXiv%3A1707%2E06347%2E)
41. Zhihong Shao, Peiyi Wang, Runxin Xu Qihao Zhu, 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/).
42. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2025. [Hybridflow: A flexible and efficient rlhf framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). In Proceedings of the Twentieth European Conference on Computer Systems, EuroSys ’25, page 1279–1297, New York, NY, USA. Assoc…
43. Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, and Ji-Rong Wen. 2025. [R1-searcher: Incentivizing the search capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/song-2025-r1-searcher-incentivizing-search/). Preprint, arXiv:2503.05592.
44. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. Musique: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 10:539–554. [find](https://scholar.google.com/scholar?q=Harsh+Trivedi%2C+Niranjan+Balasubramanian%2C+Tushar+Khot%2C+and+Ashish+Sabharwal%2E+2022%2E+Musique%3A+Multi%2Dhop+questions+via+single%2Dhop+question+composition%2E+Transactions+of+the+Association+for+Computational+Li)
45. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023a. [Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions](https://md.research.elamur.ai/free/en/papers/trivedi-2022-interleaving-retrieval-chain-thought-reasoning/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
46. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023b. [Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions](https://md.research.elamur.ai/free/en/papers/trivedi-2022-interleaving-retrieval-chain-thought-reasoning/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
47. Hongru Wang, Cheng Qian, Manling Li, Jiahao Qiu, Boyang Xue, Mengdi Wang, Heng Ji, and Kam-Fai Wong. 2025a. Toward a theory of agents as tool-use decision-makers. Preprint, arXiv:2506.00886. — [arXiv:2506.00886](https://arxiv.org/abs/2506.00886) [find](https://scholar.google.com/scholar?q=Hongru+Wang%2C+Cheng+Qian%2C+Manling+Li%2C+Jiahao+Qiu%2C+Boyang+Xue%2C+Mengdi+Wang%2C+Heng+Ji%2C+and+Kam%2DFai+Wong%2E+2025a%2E+Toward+a+theory+of+agents+as+tool%2Duse+decision%2Dmakers%2E+Preprint%2C+arXiv%3A2506%2E00886%2E+%E2%80%94+%5BarXiv%3A)
48. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2024. [Text embeddings by weakly-supervised contrastive pre-training](https://md.research.elamur.ai/free/en/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/). Preprint, arXiv:2212.03533.
49. Rui Wang, Ce Zhang, Jun-Yu Ma, Jianshu Zhang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, 3551 11 [find](https://scholar.google.com/scholar?q=Rui+Wang%2C+Ce+Zhang%2C+Jun%2DYu+Ma%2C+Jianshu+Zhang%2C+Hongru+Wang%2C+Yi+Chen%2C+Boyang+Xue%2C+Tianqing+Fang%2C+3551+11)
50. Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu, and Kam-Fai Wong. 2025b. Explore to evolve: Scaling evolved aggregation logic via proactive online exploration for deep research agents. Preprint, arXiv:2510.14438. — [arXiv:2510.14438](https://arxiv.org/abs/2510.14438) [find](https://scholar.google.com/scholar?q=Zhisong+Zhang%2C+Hongming+Zhang%2C+Haitao+Mi%2C+Dong+Yu%2C+and+Kam%2DFai+Wong%2E+2025b%2E+Explore+to+evolve%3A+Scaling+evolved+aggregation+logic+via+proactive+online+exploration+for+deep+research+agents%2E+Preprint%2C+ar)
51. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837.
52. Qiming Xie, Zengzhi Wang, Yi Feng, and Rui Xia. 2024. Ask again, then fail: Large language models’ vacillations in judgment. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10709–10745, Bangkok, Thailand. Association for Compu… [find](https://scholar.google.com/scholar?q=Qiming+Xie%2C+Zengzhi+Wang%2C+Yi+Feng%2C+and+Rui+Xia%2E+2024%2E+Ask+again%2C+then+fail%3A+Large+language+models%E2%80%99+vacillations+in+judgment%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Computatio)
53. Guangzhi Xiong, Qiao Jin, Xiao Wang, Yin Fang, Haolin Liu, Yifan Yang, Fangyuan Chen, Zhixing Song, Dengyu Wang, Minjia Zhang, Zhiyong Lu, and Aidong Zhang. 2025. Rag-gym: Systematic optimization of language agents for retrieval-augmented generation. Preprint, arXiv:2502.13957. — [arXiv:2502.13957](https://arxiv.org/abs/2502.13957) [find](https://scholar.google.com/scholar?q=Guangzhi+Xiong%2C+Qiao+Jin%2C+Xiao+Wang%2C+Yin+Fang%2C+Haolin+Liu%2C+Yifan+Yang%2C+Fangyuan+Chen%2C+Zhixing+Song%2C+Dengyu+Wang%2C+Minjia+Zhang%2C+Zhiyong+Lu%2C+and+Aidong+Zhang%2E+2025%2E+Rag%2Dgym%3A+Systematic+optimization+of+l)
54. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. [HotpotQA: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369…
55. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik 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 ICLR, page no, Kigali Rwanda. The Eleventh International Conference on Learning Representations.
56. Zihao Yi, Jiarui Ouyang, Zhe Xu, Yuwen Liu, Tianhao Liao, Haohao Luo, and Ying Shen. 2025. [A survey on recent advances in llm-based multi-turn dialogue systems](https://md.research.elamur.ai/free/en/papers/yi-2024-survey-recent-advances-llm-based/). Preprint, arXiv:2402.18013.
57. Yue Yu, Wei Ping, Zihan Liu, Boxin Wang, Jiaxuan You, Chao Zhang, Mohammad Shoeybi, and Bryan Catanzaro. 2024. Rankrag: Unifying context ranking with retrieval-augmented generation in llms. Preprint, arXiv:2407.02485. — [arXiv:2407.02485](https://arxiv.org/abs/2407.02485) [find](https://scholar.google.com/scholar?q=Yue+Yu%2C+Wei+Ping%2C+Zihan+Liu%2C+Boxin+Wang%2C+Jiaxuan+You%2C+Chao+Zhang%2C+Mohammad+Shoeybi%2C+and+Bryan+Catanzaro%2E+2024%2E+Rankrag%3A+Unifying+context+ranking+with+retrieval%2Daugmented+generation+in+llms%2E+Preprint%2C+)
58. Zheng Yuan, Hongyi Yuan, Chengpeng Li, Guanting Dong, Keming Lu, Chuanqi Tan, Chang Zhou, and Jingren Zhou. 2023. [Scaling relationship on learning mathematical reasoning with large language models](https://md.research.elamur.ai/free/en/papers/yuan-2023-scaling-relationship-learning-mathematical-reasoning/). Preprint, arXiv:2308.01825.
59. Wayne Xin Zhao, Jing Liu, Ruiyang Ren, and Ji-Rong Wen. 2024. Dense text retrieval based on pretrained language models: A survey. ACM Transactions on Information Systems, 42(4):1–60. [find](https://scholar.google.com/scholar?q=Wayne+Xin+Zhao%2C+Jing+Liu%2C+Ruiyang+Ren%2C+and+Ji%2DRong+Wen%2E+2024%2E+Dense+text+retrieval+based+on+pretrained+language+models%3A+A+survey%2E+ACM+Transactions+on+Information+Systems%2C+42%284%29%3A1%E2%80%9360%2E)

*Updated 2 November 2026*