{"slug": "keeper-learning-control-sufficient-textual-memory-for-long-horizon-llm-agents", "title": "KEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM Agents", "summary": "A new arXiv paper (2610.41482v1) introduces KEEPER, a comparative analysis of four auxiliary objectives for recursive textual memory in long-horizon LLM agents, evaluated along information-content and update-sensitivity axes within a shared recursive interface. The authors report that reward-related prediction achieved the highest task performance both before and after offline reinforcement learning, outperforming joint supervision, and define \"self-consistency bias\" as the persistence of incorrect claims already present in incoming memory. A claim-level analysis of one baseline trajectory documented error persistence despite corrective observations, leading the authors to argue that error persistence and valid-information retention should be evaluated alongside task outcomes.", "body_md": "arXiv:2610.41482v1 Announce Type: new \nAbstract: Recursive textual memory can carry earlier errors into later updates, yet task performance alone does not establish memory reliability. We define self-consistency bias as the persistence of incorrect claims already present in the incoming memory. We present KEEPER, a comparative analysis of four auxiliary objectives along information-content and update-sensitivity axes within a shared recursive interface, examining how supervision targets relate to agent performance. Among evaluated conditions, reward-related prediction achieve the highest task performance before and after offline reinforcement learning, outperforming joint supervision. A claim-level analysis of one baseline trajectory documents error persistence despite corrective observations. Together, these analyses motivate evaluating error persistence and valid-information retention alongside task outcomes.", "url": "https://wpnews.pro/news/keeper-learning-control-sufficient-textual-memory-for-long-horizon-llm-agents", "canonical_source": "https://www.machinebrief.com/news/keeper-learning-control-sufficient-textual-memory-for-long-h-jxju", "published_at": "2026-11-02 05:00:00+00:00", "updated_at": "2026-11-02 05:22:58.783462+00:00", "lang": "en", "topics": ["ai-agents", "large-language-models", "ai-research", "artificial-intelligence"], "entities": ["KEEPER", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/keeper-learning-control-sufficient-textual-memory-for-long-horizon-llm-agents", "markdown": "https://wpnews.pro/news/keeper-learning-control-sufficient-textual-memory-for-long-horizon-llm-agents.md", "text": "https://wpnews.pro/news/keeper-learning-control-sufficient-textual-memory-for-long-horizon-llm-agents.txt", "jsonld": "https://wpnews.pro/news/keeper-learning-control-sufficient-textual-memory-for-long-horizon-llm-agents.jsonld"}}