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.
arXiv:2607. 13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics.
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.
arXiv:2607. 08032v1 Announce Type: new Abstract: Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions.
arXiv:2608. 12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment state have changed.
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.
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.
arXiv:2607. 10608v1 Announce Type: new Abstract: Memory is becoming a core component of long-horizon AI agents, allowing agents to reuse past experience when operating web browsers, software tools, and other interactive environments.
The paper investigates how large language model agents can over-rely on agentic memory, a phenomenon where retrieved memories distort inference even when they are correctly stored and retrieved. It shows that memory is helpful when past experience fully transfers to the current task but becomes misleading under partial query-memory overlap, a pattern confirmed by controlled experiments. To address this, the authors propose MEMTRIM, a plug‑and‑play framework that indexes memory evidence at write time and limits its reuse at read time, thereby reducing over-reliance without retraining and preserving useful memory benefits across models and memory architectures.
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.
MemDev-Bench is a new benchmark that evaluates how memory systems influence code agents across diverse repository histories. It pairs each task with relevance‑annotated earlier tasks from the same repository, creating 4,869 historical tasks for 555 base tasks and an automated pipeline that ensures these tasks are executable and verifiable. The study finds that memory mainly improves fine‑grained localization and editing, but can also cause failures when agents reuse memory without reassessing its applicability, and that providing raw historical trajectories reduces steps more effectively than compressed memories.
arXiv:2605.12978v2 Announce Type: replace Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolid...