More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents
LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decisions. A central design question is whether to retain only observed trajectories and outcomes or also the rules, summaries, and skills inferred from them. Retaining these abstractions allows agents to reuse strategies without repeatedly deriving them from raw trajectories. However, errors in stored abstractions can propagate to subsequent decisions through retrieval and reuse. They can also shape execution trajectories, which then become the basis for new abstractions that reproduce the original errors. We term this feed...
| Authors | Ruhan Wang, Kishan Panaganti, Dongruo Zhou |
|---|---|
| Primary category | cs.AI |
| Published | 19 October 2026 |
| Last updated at source | 19 October 2026 |
Recent changes
- 21 Oct 2026 Description: LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decisions. A central design question is whether to retain only observed t → LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decisions. A central design question is whether to retain only observed t
- 21 Oct 2026 Topics added cs.AI, cs.CL removed hf-daily-papers, llm agents, external memory, error reproduction, abstraction, anti-persistence, memory design, self-improvement
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 21 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.