# Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

arXiv: https://arxiv.org/abs/2607.08716 · HTML: https://mlsanity.com/paper/2607.08716/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [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)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025)
- [Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2510.12635/) (2025)
- [How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models](https://mlsanity.com/paper/2510.02453/) (2025)

## Built on by (most cited first, 11 of 11)

- [CORAL: An LLM-Native Harness for Production Recommender Systems](https://mlsanity.com/paper/2609.02730/) (2026)
- [Sigma-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2607.27958/) (2026)
- [Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures](https://mlsanity.com/paper/2609.13463/) (2026)
- [Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression](https://mlsanity.com/paper/2609.27332/) (2026)
- [Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents](https://mlsanity.com/paper/2609.27334/) (2026)
- [Dude, Where's My State? Execution Information Requirements for Stateful Agents](https://mlsanity.com/paper/2609.32687/) (2026)
- [Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses](https://mlsanity.com/paper/2609.34649/) (2026)
- [When Should Agents Check External State? Budgeting Observations for Stored Intentions](https://mlsanity.com/paper/2609.37125/) (2026)
- [ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning](https://mlsanity.com/paper/2610.00592/) (2026)
- [RunningTab: Direct Workspace Interaction with Environment-Side Tabs](https://mlsanity.com/paper/2610.10444/) (2026)
- [Recurrent Harness for Agentic Continual Learning](https://mlsanity.com/paper/2610.12668/) (2026)

## Abstract (arXiv)

In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention mechanism rather than passive retrieval. A separate memory agent runs alongside an unmodified action agent, updating a structured memory bank from the recent trajectory and deciding whether to inject a memory-grounded reminder or remain silent. The module is plug-and-play with frontier action agents and existing agent harnesses. Across Terminal-Bench 2.0 and τ2-Bench, it improves pass@1 for both weaker and stronger action agents, with gains of +8.3 pp on Terminal-Bench and +6.8 pp on τ2-Bench. Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retrieval. As an early step toward open-weight memory policies, we train Qwen3.5-27B on SETA using SFT and GRPO, improving validation reward and achieving partial transfer to Terminal-Bench.