{"slug": "more-memory-worse-agents-error-reproduction-and-anti-persistence-in-llm-agents", "title": "More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents", "summary": "A study of LLM agents that store execution experience in external memory finds that retaining rules, summaries and strategies alongside observed trajectories and outcomes can degrade agent performance, a phenomenon the work terms anti-persistence. The research examines error reproduction in agents that reuse their own stored experience without updating model parameters, and asks which memory contents should be kept to guide later decisions.", "body_md": "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 s", "url": "https://wpnews.pro/news/more-memory-worse-agents-error-reproduction-and-anti-persistence-in-llm-agents", "canonical_source": "https://aiflash.com/news/136507/", "published_at": "2026-10-21 05:00:06+00:00", "updated_at": "2026-10-21 05:17:48.078321+00:00", "lang": "en", "topics": ["ai-agents", "large-language-models", "ai-research", "machine-learning", "artificial-intelligence"], "entities": [], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/more-memory-worse-agents-error-reproduction-and-anti-persistence-in-llm-agents", "markdown": "https://wpnews.pro/news/more-memory-worse-agents-error-reproduction-and-anti-persistence-in-llm-agents.md", "text": "https://wpnews.pro/news/more-memory-worse-agents-error-reproduction-and-anti-persistence-in-llm-agents.txt", "jsonld": "https://wpnews.pro/news/more-memory-worse-agents-error-reproduction-and-anti-persistence-in-llm-agents.jsonld"}}