Selective Memory Retention for Long-Horizon LLM Agents
On the map: LLM agents and tool use → Agent memory systems
Abstract (arXiv)
When does retention matter for memory-augmented LLM agents? We study this with TraceRetain, a lightweight framework for bounded external memory in frozen LLM agents that scores entries by interpretable features (success, age, access frequency, redundancy, specificity, similarity, downstream utility) and evicts the lowest-scoring ones at capacity. On clean ALFWorld with gpt-5-mini, external memory robustly improves over no memory across two seeds, but differences among bounded retention policies fall within Wilson 95% CIs: clean ALFWorld at T=100 to T=200 does not naturally exhibit the memory pollution retention is designed to address. Under a controlled noisy-write stress (75% synthetic distractors), unbounded memory and FIFO-K50 degrade on Precision@5 (20.2% to 12.4% and 15.8% to 3.8%) while TraceRetain-CEM is essentially unchanged (16.9% to 16.6%) and preserves 97/100 task success. The mechanism: unbounded memory has the highest mean similarity (0.87) but lowest precision, indicating failed distractors close to the query in embedding space. Held-out in-distribution evaluation shows memory-augmented policies solving 47 to 49 of 50 tasks vs. 39/50 for no memory. Bounded retention buys memory and step efficiency on saturated clean benchmarks at no task-success cost, and only differentiates from cache heuristics when streams contain noise.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 16 of its 19 references that are in the map. First posted on arXiv 28 Jun 2026.
Builds on
16 of 19 references.
References · 16
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
- 2017Gradient Episodic Memory for Continual Learningcited by 1,871
- 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
- 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
- 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
- 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
- 2018Experience Replay for Continual Learningcited by 1,074
4 more
- 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
- 2021Carbon Emissions and Large Neural Network Trainingcited by 561
- 2023Cognitive Architectures for Language Agentscited by 422
- 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
- 2026Human-Inspired Memory Architecture for LLM Agents
- 2026Rosetta Memory: Adaptive Memory for Cross-LLM Agents
- 2026What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
- 2026CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents
- 2025Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
- 2026Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory
- 2026FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory