Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents
arXiv:2609.36130v1 Announce Type: new Abstract: Long-running LLM agents compress past interactions into persistent memories that may be reused as premises for later tasks. This creates a distinct derivation problem: whether the memory actually follows from what the interaction history supports. Rel…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-09-30 04:00 · arXiv cs.AI
Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents