arXiv:2606. 14470v1 Announce Type: new Abstract: Large language model (LLM) reasoning is ephemeral: chains of thought vanish with the context window, pruned search branches leave no record, and memory buffers cannot be diffed, merged, or audited.
By Pavan C Shekar, Abhishek H S, Aswanth Krishnan
arXiv:2609.23570v1 Announce Type: cross
Abstract: Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks. Yet existing evaluatio...
By Liyang Fan, Yingcheng Shi, Yongbin Li, Chenghao Sun, Xin Chen, Xander Xu, Hu Wei, Shiwen Ni, Min Yang, Jieping Ye
arXiv:2606. 09900v1 Announce Type: cross Abstract: Long-term memory is the missing layer for LLM agents: across sessions they forget, and the common workaround -- replaying the whole history into the prompt -- is expensive, slow, and, as distractors accumulate, less accurate.
By Liuyin Wang
arXiv:2606. 11976v1 Announce Type: cross Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue.
By Akeela Darryl Fattha, Kia Ying Chua, Lingxiao Jiang, Laura Wynter
Agora is a system that uses Git as a shared memory for autonomous research agents, recording each claim as an immutable commit in an append‑only directed acyclic graph. In a 12‑day run, 13 language‑model workers independently explored a weight‑transfer problem, producing 1,703 contributions that improved a 119.6M‑parameter model’s performance from 3.39 to 1.899 bits per byte. The system’s design includes a diversity‑aware selection rule and an index that tracks the frontier, neglected branches, and verification status of each claim.
By Yifan Zhang, Yunheng Zou, Shaokun Zhang, Jian Hu, Hao Zhang, Binfeng Xu, Jan Kautz, Yi Dong
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