The paper investigates how large language model (LLM) agents can improve performance by storing and reusing experience in external memory. It identifies a problem called error reproduction, where mistakes in stored abstractions propagate through cycles of abstraction, execution, and re-abstraction, leading to persistent errors. To mitigate this, the authors propose Anti-Persistence, a memory design that retains raw trajectories and outcomes but reconstructs task-specific guidance on demand, discarding it after use. Experiments across multiple benchmarks show that Anti-Persistence yields higher held‑out success rates and lower LLM‑call costs compared to other memory designs, supporting the idea of separating experience accumulation from abstraction persistence.
By Ruhan Wang, Kishan Panaganti, Dongruo Zhou
arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.
By Alex Kwon
The paper introduces REM (Reusable Experience Memory), a framework that manages the lifecycle of experience for large language model agents performing long-horizon coding tasks. REM consolidates completed trajectories into compact, phase-structured documents, injects them at task start, and evicts them after a single exposure, making the memory system responsive to the agent’s needs. Experiments on repository-level bug fixing show REM outperforms state‑of‑the‑art memory systems in retrieval accuracy and task resolution while reducing cost.
By Xinyi Lisa Chen, Pedro Herrero-Vidal, Xiaohan Chen, Xiaojing Yu, Cris Liu, Bingqing Song, Bin Xu, Suleiman A. Khan, You-Lin Chen
arXiv:2608. 06811v1 Announce Type: cross Abstract: Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation, and verification.
By Jiahao Zhang, Yifan Zhang, Yu Huang
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
By Shweta Mishra, Shashank Mishra
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
By Chao Yao, Yangbo Wei, Zhen Huang, Junhong Qian, Chenle Chen, Shaoqiang Lu, Chen Wu, Lei He