ACL Findings2026
ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents
Yilun Yao, Shan Huang, Elsie Dai, Zhewen Tan, Zhenyu Duan, Shousheng Jia, Yanbing Jiang, Tong Yang
Abstract
Large language models are increasingly deployed as research agents for deep search and long-horizon information seeking, yet their performance often degrades as interaction histories grow. This degradation, known as context rot, reflects a failure to maintain coherent and task-relevant internal states over extended reasoning horizons. Existing approaches primarily manage context through raw accumulation or passive summarization, treating it as a static artifact and allowing early errors or misplaced emphasis to persist. Motivated by this perspective, we propose ARC, an active and reflectiondriven framework that formulates context management as the online maintenance of a dynamically revisable internal reasoning state during execution. ARC operationalizes this view through incremental context construction together with selectively triggered reflection, allowing agents to reorganize their working context when misalignment or degradation is detected. Experiments on five challenging longhorizon information-seeking benchmarks show that ARC consistently outperforms raw history accumulation and passive summarization baselines, achieving up to an 11% absolute improvement on BrowseComp-ZH with Qwen2.5-32B-Instruct. 1 rather than revised in light of downstream reasoning outcomes. More fundamentally, the challenge of long-horizon information seeking lies not only in deciding what to retain, but also in ensuring that the maintained context can evolve as the agent's understanding changes.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Reflexion: language agents with verbal reinforcement learning cites Self-Refine: Iterative Refinement with Self-Feedback
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing cites Self-Refine: Iterative Refinement with Self-Feedback
Builds on14
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
- A-Mem: Agentic Memory for LLM AgentsWujiang Xu, Zujie Liang, Kai Mei, Hang Gao et al.NeurIPS 2025 · 1,138 citations
- GAIA: a benchmark for General AI AssistantsGrégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun et al.ICLR 2024 · 716 citations
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive CritiquingZhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen et al.ICLR 2024 · 699 citations
Related papers
- ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn DialogueJiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi et al.ACL Findings 2026
- U-Fold: Dynamic Intent-Aware Context Folding for User-Centric AgentsJin Su, Runnan Fang, Yeqiu Li, Xiaobin Wang et al.ACL Findings 2026
- Sculptor: Empowering LLMs with Cognitive Agency via Active Context ManagementMo Li, L.H. Xu, Qitai Tan, Long Ma et al.ICLR 2026 · 20 citations
- PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM AgentsLei Wei, Xiao Peng, TT, Guannan Zhang et al.ACL 2026
- Agentic Conversational Search with Contextualized Reasoning via Reinforcement LearningFengran Mo, Yifan Gao, Sha Li, Hansi Zeng et al.ACL Findings 2026
