ConMem: Counterfactual Multi-Scenario Probing for Resolving LLM Memory Misalignment

arXiv:2610.33432v1 Announce Type: new Abstract: Long-term memory is critical for autonomous Large Language Model (LLM) agents executing multi-session, long-horizon tasks. However, existing memories often inappropriately store, retain, or retrieve over-generalized, misattributed, or privacy-sensitive

arXiv cs.AIDienstag 05:00 · 27.10.1 Min. Lesezeit