Mitigating Context Interference for Reliable and Efficient Search Agents
Open accessAbstract
Boyang Xue, Bin Wu, Shuofei Qiao, Sheng Wang, Rui Wang, Yiming Du, Hongru Wang, Jeff Z. Pan, Emine Yilmaz, Kam-Fai Wong, Aldo Lipani. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Exploratory sub-tasks often retrieve information-intensive chunks that quickly bloat the context window, leading to severe decision distortion in subsequent steps.
“More critically, exploratory sub-tasks often retrieve information-intensive chunks that quickly bloat the context window, leading to severe decision distortion in subsequent steps (Liu et al., 2024;Xue et al., 2026).”
From MS-Eval: Benchmarking Sub-Agent Delegation and Orchestration in MCP-Intensive Working Scenarios (2026) · cites this paper as Xue et al., 2026
The Introduction says retrieved context can distract search agents and degrade subsequent generation quality; the CoT Prompt passage says documents accumulated over several turns introduce noise. These passages support the general interference claim, but do not establish that exploratory sub-tasks quickly bloat the context window or cause severe decision distortion. (LLM, conf=0.84)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · cited 4× · see citing works
“A variety of RL algorithms have been introduced, like PPO (Schulman et al., 2017) and GRPO (Shao et al., 2024).”
InfluentialReinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972 · cited 2× · see citing works
“Reinforcement learning (RL) (Kaelbling et al., 1996) has emerged as a paradigm for search agent training (Song et al., 2025; Jin et al., 2025; Chen et al., 2025) using PPO (Schulman et al., 2017) and GRPO (Shao et al., 2024).”
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505 · see citing works
Dense passage retrieval for open-domain question answering
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575 · cited 1× · see citing works
“For retrieval, we leverage E5 (Wang et al., 2024) as the retriever E and 2018 Wikipedia dump (Karpukhin et al., 2020) as the knowledge base K b respectively.”
Training Language Models to Follow Instructions with Human Feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2011 · Cited by 3,117 · cited 1× · see citing works
“Reinforcement Learning (RL) (Kaelbling et al., 1996) has emerged as a paradigm for LLM post-training or alignment (Ouyang et al., 2022).”
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101 · cited 1× · see citing works
“A common paradigm is retrieval-augmented generation (RAG) (Gao et al., 2024; Lewis et al., 2020), in which a search engine retrieves documents relevant to the search query and feeds them into LLMs.”
Natural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069 · cited 2× · see citing works
“Single-hop QA includes: Natural Questions (NQ) (Kwiatkowski et al., 2019), TriviaQA (Joshi et al., 2017), and PopQA (Mallen et al., 2023).”
Efficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J., Zhang, H., & Stoica, I. (2023) · Proceedings of the 29th Symposium on Operating Systems Principles · doi:10.1145/3600006.3613165 · Cited by 1,817 · cited 1× · see citing works
“For efficient LLM rollouts, we adopt vLLM (Kwon et al., 2023) with a tensor parallel size of 1 and GPU memory utilization ratio of 0.7.”
InfluentialHotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., & Manning, C. D. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1259 · Cited by 1,804 · cited 4× · see citing works
“Multi-hop QA includes: 1) HotpotQA (Yang et al., 2018), the first large-scale dataset requiring reasoning across multiple Wikipedia paragraphs; 2) 2WikiMultiHopQA (2Wiki) (Ho et al., 2020), which provides evidence information containing a reasoning path for multi-hop questions; 3) MuSiQue (Trivedi et al., 2022), which…”
InfluentialLüderitz, B. (1999) · Journal of interventional cardiac electrophysiology · doi:10.1023/a:1009863214233 · Cited by 1,709 · see citing works
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D., & Zettlemoyer, L. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1147 · Cited by 1,690 · cited 3× · see citing works
“Single-hop QA includes: Natural Questions (NQ) (Kwiatkowski et al., 2019), TriviaQA (Joshi et al., 2017), and PopQA (Mallen et al., 2023).”
Toolformer: language models can teach themselves to use tools
Schick, T., Dwivedi-Yu, J., Dessi, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2997 · Cited by 1,150 · see citing works
Retrieval-Augmented Generation for Large Language Models: A Survey
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876 · see citing works
Self-citationReAct: Synergizing Reasoning and Acting in Language Models
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.03629 · Cited by 608 · cited 1× · see citing works
“Approaches such as IRCoT (Trivedi et al., 2023b) and ReAct (Yao et al., 2023) employ prompting to interleave reasoning with iterative search calls.”
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, Guo, D., Yang, D., Zhang, H., Song, J., Wang, P., Zhu, Q., Xu, R., Zhang, R., Ma, S., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.12948 · Cited by 538 · see citing works
Self-citationA study of generative large language model for medical research and healthcare
Peng, C., Yang, X., Chen, A., Smith, K. E., PourNejatian, N., Costa, A. B., Martin, C., Flores, M. G., Zhang, Y., Magoc, T., et al. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00958-w · Cited by 408 · see citing works
Murakami, C., Barrera, J., & Most, S. P. (2009) · Archives of Facial Plastic Surgery · doi:10.1001/archfaci.2008.536 · Cited by 372
Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
Trivedi, H., Balasubramanian, N., Khot, T., & Sabharwal, A. (2022) · arXiv · doi:10.48550/arxiv.2212.10509 · Cited by 349 · cited 1× · see citing works
“For retrieval-based settings of search agents, we employ Information Retrieval with CoT ( IRCoT ) (Trivedi et al., 2023a), which enables LLMs to actively call the retriever for questions beyond their knowledge scope after thinking.”
Mallen, A., Asai, A., Zhong, V., Das, R., Khashabi, D., & Hajishirzi, H. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.546 · Cited by 340 · cited 4× · see citing works
“Single-hop QA includes: Natural Questions (NQ) (Kwiatkowski et al., 2019), TriviaQA (Joshi et al., 2017), and PopQA (Mallen et al., 2023).”
InfluentialLarge Language Models in Finance: A Survey
Li, Y., Wang, S., Ding, H., & Chen, H. (2023) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3604237.3626869 · Cited by 334 · cited 1× · see citing works
“Although LLMs exhibit impressive capabilities, they often lack updated or domain-specific knowledge (Peng et al., 2023; Li et al., 2023), which undermines LLMs’ reliability.”
Self-citationMeasuring and Narrowing the Compositionality Gap in Language Models
Press, O., Zhang, M., Min, S., Schmidt, L., Smith, N. A., & Lewis, M. (2022) · arXiv · doi:10.48550/arxiv.2210.03350 · Cited by 294 · cited 3× · see citing works
“Multi-hop QA includes: 1) HotpotQA (Yang et al., 2018), the first large-scale dataset requiring reasoning across multiple Wikipedia paragraphs; 2) 2WikiMultiHopQA (2Wiki) (Ho et al., 2020), which provides evidence information containing a reasoning path for multi-hop questions; 3) MuSiQue (Trivedi et al., 2022), which…”
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
Ho, X., Duong Nguyen, A.-K., Sugawara, S., & Aizawa, A. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.580 · Cited by 287 · cited 2× · see citing works
“…1) HotpotQA (Yang et al., 2018), the first large-scale dataset requiring reasoning across multiple Wikipedia paragraphs; 2) 2WikiMultiHopQA (2Wiki) (Ho et al., 2020), which provides evidence information containing a reasoning path for multi-hop questions; 3) MuSiQue (Trivedi et al., 2022), which…”
♫ MuSiQue: Multihop Questions via Single-hop Question Composition
Trivedi, H., Balasubramanian, N., Khot, T., & Sabharwal, A. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00475 · Cited by 283 · see citing works
Dense Text Retrieval Based on Pretrained Language Models: A Survey
Zhao, W. X., Liu, J., Ren, R., & Wen, J.-R. (2024) · ACM Transactions on Information Systems · doi:10.1145/3637870 · Cited by 211 · see citing works
A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems
Yi, Z., Ouyang, J., Xu, Z., Liu, Y., Liao, T., Luo, H., & Shen, Y. (2025) · ACM Computing Surveys · doi:10.1145/3771090 · Cited by 136 · cited 1× · see citing works
“…state tracking (Jacqmin et al., 2022) or RAG reranking (Glass et al., 2022; Nguyen et al., 2025; Yu et al., 2024); (2) Compression method condenses lengthy input sequences into summaries or latent states to weaken noise (Jiang et al., 2023; Yi et al., 2025; Li et al., 2025b (Rajeev et al., 2025).”
Text Embeddings by Weakly-Supervised Contrastive Pre-training
Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., & Wei, F. (2022) · arXiv · doi:10.48550/arxiv.2212.03533 · Cited by 135 · see citing works
Qwen, :, Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., et al. (2024) · arXiv · doi:10.48550/arxiv.2412.15115 · Cited by 128 · see citing works
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Shao, Z., Wang, P., Zhu, Q., Xu, R., Song, J., Bi, X., Zhang, H., Zhang, M., Li, Y. K., Wu, Y., et al. (2024) · arXiv · doi:10.48550/arxiv.2402.03300 · Cited by 101 · cited 12× · see citing works
“A variety of RL algorithms have been introduced, like PPO (Schulman et al., 2017) and GRPO (Shao et al., 2024).”
InfluentialBenchmarking Prompt Sensitivity in Large Language Models
Razavi, A., Soltangheis, M., Arabzadeh, N., Salamat, S., Zihayat, M., & Bagheri, E. (2025) · European Conference on Information Retrieval · doi:10.48550/arxiv.2502.06065 · Cited by 84 · cited 1×
“LLMs are highly sensitive to input contexts, leaving them vulnerable to noise or irrelevant content that can degrade output quality (Xie et al., 2024; Razavi et al., 2025; Wang et al., 2025b).”
HybridFlow: A Flexible and Efficient RLHF Framework
Sheng, G., Zhang, C., Ye, Z., Wu, X., Zhang, W., Zhang, R., Peng, Y., Lin, H., & Wu, C. (2025) · Proceedings of the Twentieth European Conference on Computer Systems · doi:10.1145/3689031.3696075 · Cited by 74 · cited 2× · see citing works
“For GRPO training, we set the policy LLM learning rate to 1e-6 and sample 4 responses per prompt, following the GRPO implementation in Verl (Sheng et al., 2025).”
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
Yu, Y., Ping, W., Liu, Z., Wang, B., You, J., Zhang, C., Shoeybi, M., & Catanzaro, B. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-3850 · Cited by 47 · cited 2× · see citing works
“…or relevant information in contents as in dialogue state tracking (Jacqmin et al., 2022) or RAG reranking (Glass et al., 2022; Nguyen et al., 2025; Yu et al., 2024); (2) Compression method condenses lengthy input sequences into summaries or latent states to weaken noise (Jiang et al., 2023; Yi et…”
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models TrainingPreprint
Fang, T., Zhang, Z.-S., Wang, X.-Y., Wang, R., Qin, C., Wan, Y., Ma, J., Zhang, C., Chen, J.-Q., Li, X.-Y., et al. (2025) · arXiv.org · doi:10.48550/arxiv.2508.00414 · Cited by 43 · cited 1× · see citing works
“More recent work treats search engines as interactive tools (Schick et al., 2023), prompting or fine-tuning LLMs to act as search agents (Xiong et al., 2025; Fang et al., 2025; Wang et al., 2025b; Li et al., 2026).”
Self-citationReinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent
Huang, Z.-Y., Yuan, X.-W., Ju, Y., Zhao, J., & Liu, K. (2025) · arXiv.org · doi:10.48550/arxiv.2505.07596 · Cited by 31 · cited 1×
“Recent work has further empowered them to invoke search engines to retrieve external knowledge, essentially training them as multi-turn search agents that iterate on retrieval and generation until tasks are solved (Wang et al., 2025a; Jia et al., 2025; Huang et al., 2025).”
Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning ModelsPreprint
Rajeev, M., Ramamurthy, R., Trivedi, P., Yadav, V., Bamgbose, O., Madhusudan, S., Zou, J., & Rajani, N. (2025) · arXiv.org · doi:10.48550/arxiv.2503.01781 · Cited by 30 · cited 1× · see citing works
“…state tracking (Jacqmin et al., 2022) or RAG reranking (Glass et al., 2022; Nguyen et al., 2025; Yu et al., 2024); (2) Compression method condenses lengthy input sequences into summaries or latent states to weaken noise (Jiang et al., 2023; Yi et al., 2025; Li et al., 2025b (Rajeev et al., 2025).”
Verified Critical Step Optimization for LLM Agents
Li, M.-K., Zeng, Q., Fang, T., Liang, Z.-W., Song, L.-F., Liu, Q., Mi, H.-T., & Yu, D. (2026) · Annual Meeting of the Association for Computational Linguistics · doi:10.48550/arxiv.2602.03412 · Cited by 28 · cited 1×
“More recent work treats search engines as interactive tools (Schick et al., 2023), prompting or fine-tuning LLMs to act as search agents (Xiong et al., 2025; Fang et al., 2025; Wang et al., 2025b; Li et al., 2026).”
Position: Agent Should Invoke External Tools ONLY When Epistemically NecessaryPreprint
Wang, H., Qian, C., Li, M.-L., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.00886 · Cited by 20 · see citing works
Self-citationAsk Again, Then Fail: Large Language Models’ Vacillations in Judgment
Xie, Q., Wang, Z., Feng, Y., & Xia, R. (2024) · Volume 1 · doi:10.18653/v1/2024.acl-long.577 · Cited by 19 · cited 1×
“LLMs are highly sensitive to input contexts, leaving them vulnerable to noise or irrelevant content that can degrade output quality (Xie et al., 2024; Razavi et al., 2025; Wang et al., 2025b).”
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Jin, B., Zeng, H., Yue, Z., Yoon, J., Arik, S., Wang, D., Zamani, H., & Han, J. (2025) · arXiv · doi:10.48550/arxiv.2503.09516 · Cited by 13 · cited 11× · see citing works
“A variety of RL algorithms have been introduced, like PPO (Schulman et al., 2017) and GRPO (Shao et al., 2024).”
InfluentialA Survey on Recent Advances in LLM-Based Multi-turn Dialogue SystemsPreprint
Yi, Z., Ouyang, J., Xu, Z., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.18013 · Cited by 11 · cited 1× · see citing works
“…state tracking (Jacqmin et al., 2022) or RAG reranking (Glass et al., 2022; Nguyen et al., 2025; Yu et al., 2024); (2) Compression method condenses lengthy input sequences into summaries or latent states to weaken noise (Jiang et al., 2023; Yi et al., 2025; Li et al., 2025b (Rajeev et al., 2025).”
Bhatti, M. H. (2025) · arXiv.org · doi:10.48550/arxiv.2508.08322 · Cited by 11 · cited 1× · see citing works
“This refers to context interference , which indicates “feeding too much irrelevant context may confuse LLMs to focus on wrong information (Coleman et al., 2023; Haseeb, 2025; Gupta et al., 2024; Jiang et al., 2025).””
LLMs Get Lost In Multi-Turn Conversation
Laban, P., Hayashi, H., Zhou, Y., & Neville, J. (2025) · arXiv · Cited by 10 · cited 1× · see citing works
“The context interference presented in each round may distract LLMs from irrelevant information and persistently degrade subsequent generation quality (Li et al., 2025b; Laban et al., 2025), thereby hindering the efficiency and reliability of search agents.”
Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Yuan, Z., Yuan, H., Li, C., Dong, G., Lu, K., Tan, C., Zhou, C., & Zhou, J. (2023) · arXiv · doi:10.48550/arxiv.2308.01825 · Cited by 10 · see citing works
Supervising the search process produces reliable and generalizable information-seeking agents
Xiong, G.-Z., Jin, Q., Wang, X., et al. (2025) · doi:10.48550/arxiv.2502.13957 · Cited by 10
Jiang, M., Huang, T.-H., Guo, B., Lu, Y., & Zhang, F. (2024) · arXiv.org · doi:10.48550/arxiv.2408.10615 · Cited by 10 · cited 1×
“This refers to context interference , which indicates “feeding too much irrelevant context may confuse LLMs to focus on wrong information (Coleman et al., 2023; Haseeb, 2025; Gupta et al., 2024; Jiang et al., 2025).””
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Song, H., Jiang, J., Min, Y., Chen, J., Chen, Z., Zhao, W. X., Fang, L., & Wen, J.-R. (2025) · arXiv · doi:10.48550/arxiv.2503.05592 · Cited by 7 · see citing works
Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language ModelsPreprint
Li, Y. X., Shen, X., Miao, Y., Yao, X., Ding, X., Krishnan, R., & Padman, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.04717 · Cited by 4 · see citing works
Fast, Slow, and Tool-augmented Thinking for LLMs: A ReviewPreprint
Jia, X.-D., Li, J.-P., Wang, Z., Li, J.-J., Zeng, X.-S., Wang, Y.-S., Zhang, W.-N., Yu, Y., & Liu, W. (2025) · arXiv.org · doi:10.48550/arxiv.2508.12265 · Cited by 3 · cited 1× · see citing works
“Recent work has further empowered them to invoke search engines to retrieve external knowledge, essentially training them as multi-turn search agents that iterate on retrieval and generation until tasks are solved (Wang et al., 2025a; Jia et al., 2025; Huang et al., 2025).”
MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
Nguyen, T., Chin, P., & Tai, Y.-W. (2025) · arXiv · doi:10.48550/arxiv.2505.20096 · Cited by 2 · see citing works
In-context Interference in Chat-based Large Language ModelsPreprint
Coleman, E. N., Hurtado, J., & Lomonaco, V. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.12727 · Cited by 2 · see citing works
Wang, R., Zhang, C., Ma, J.-Y., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.14438
Self-citationReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Chen, M., Sun, L., Li, T., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.19470
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
Yu, Y., Ping, W., Liu, Z., Wang, B., You, J., Zhang, C., Shoeybi, M., & Catanzaro, B. (2024) · arXiv · doi:10.48550/arxiv.2407.02485 · cited 2×
“…or relevant information in contents as in dialogue state tracking (Jacqmin et al., 2022) or RAG reranking (Glass et al., 2022; Nguyen et al., 2025; Yu et al., 2024); (2) Compression method condenses lengthy input sequences into summaries or latent states to weaken noise (Jiang et al., 2023; Yi et…”
Flagged first, then by citations
3 of the 55 references couldn’t be matched to a known paper.
Research works printed but not linked: 7
- Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Ji-Rong Wen, and Zhicheng Dou. 2025. Un- derstand 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 Machinery. · DOI
- Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Naik, Pengshan Cai, and Alfio Gliozzo. 2022. Re2G: Retrieve, rerank, generate. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, pages 2701-2715, Seattle, United States. Association for Computational Linguistics. · DOI
- 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 9 3549 history. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14633-14652, Miami, Florida, USA. Associa- tion for Computational Linguistics. · DOI · Paper page
- Léo Jacqmin, Lina M. Rojas Barahona, and Benoit Favre. 2022. "do you follow me?": A survey of recent approaches in dialogue state tracking. In Pro- ceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 336-350, Edinburgh, UK. Association for Computa- tional Linguistics. · DOI
- Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023. LLMLingua: Compressing prompts for accelerated inference of large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Process- ing, pages 13358-13376, Singapore. Association for Computational Linguistics. · DOI · Paper page
- Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yu- jia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025a. Search-o1: Agentic search-enhanced large reasoning models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Lan- guage Processing, pages 5420-5438, Suzhou, China. Association for Computational Linguistics. · DOI
- Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023b. Interleaving retrieval with chain-of-thought reasoning for knowledge- intensive multi-step questions. In Proceedings of the 61st Annual Meeting of the Association for Com- putational Linguistics (Volume 1: Long Papers), pages 10014-10037, Toronto, Canada. Association for Computational Linguistics. · DOI · Paper page
Cited by
Sorted by citations
MS-Eval: Benchmarking Sub-Agent Delegation and Orchestration in MCP-Intensive Working Scenarios
Ding, B., Wang, Q., Ruan, L., Lu, W., Ge, Q., Fang, R., & Lin, T. (2026) · arXiv · doi:10.48550/arxiv.2610.22869
“More critically, exploratory sub-tasks often retrieve information-intensive chunks that quickly bloat the context window, leading to severe decision distortion in subsequent steps (Liu et al., 2024; Xue et al., 2026).”
Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions
Zheng, Y.-X., Tian, L., & Rizoiu, M. (2026) · doi:10.48550/arxiv.2609.33065
“Recent studies show that models can search unnecessarily and that retrieved documents can introduce irrelevant information (Xie et al., 2026; Xue et al., 2026).”
- Authors
- Xue, B., Wu, B., Qiao, S., Wang, S., Wang, R., Du, Y., Wang, H., Pan, J. Z., Yilmaz, E., Wong, K.-F., & Lipani, A.
- Affiliations
- Chinese University of Hong Kong (HK)
- University College London (GB)
- Zhejiang University (CN)
- University of Hong Kong (HK)
- University of Edinburgh (GB)
- Venue
- Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2026
- Pages
- 3541-3558
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W7166880248
- Cited by
- 0
- References
- 55
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- search agents, large language models, retrieval-augmented generation, search reliability, search efficiency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
