# ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents

arXiv: https://arxiv.org/abs/2601.12030 · HTML: https://mlsanity.com/paper/2601.12030/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization](https://mlsanity.com/paper/2509.13313/) (2025)
- [Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory](https://mlsanity.com/paper/2511.20857/) (2025)
- [xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations](https://mlsanity.com/paper/2506.13651/) (2025)
- [AgentFold: Long-Horizon Web Agents with Proactive Context Management](https://mlsanity.com/paper/2510.24699/) (2025)
- [MemEvolve: Meta-Evolution of Agent Memory Systems](https://mlsanity.com/paper/2512.18746/) (2025)
- [Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering](https://mlsanity.com/paper/1905.05733/) (2019)
- [Length-Induced Embedding Collapse in PLM-based Models](https://mlsanity.com/paper/2410.24200/) (2024)

## Built on by (most cited first, 7 of 7)

- [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026)
- [LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents](https://mlsanity.com/paper/2605.05191/) (2026)
- [MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.02113/) (2026)
- [ACE: Pluggable Adaptive Context Elasticizer across Agents](https://mlsanity.com/paper/2606.31564/) (2026)
- [Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation](https://mlsanity.com/paper/2604.11628/) (2026)
- [ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces](https://mlsanity.com/paper/2609.33326/) (2026)
- [Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses](https://mlsanity.com/paper/2609.34649/) (2026)

## Abstract (arXiv)

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, which is the first framework to systematically formulate context management as an active, reflection-driven process that treats context as a dynamic internal reasoning state during execution. ARC operationalizes this view through reflection-driven monitoring and revision, allowing agents to actively reorganize their working context when misalignment or degradation is detected. Experiments on challenging long-horizon information-seeking benchmarks show that ARC consistently outperforms passive context compression methods, achieving up to an 11% absolute improvement in accuracy on BrowseComp-ZH with Qwen2.5-32B-Instruct.