Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory
Read the original on arXiv AI →The paper investigates how large language model agents can over-rely on agentic memory, a phenomenon where retrieved memories distort inference even when they are correctly stored and retrieved. It shows that memory is helpful when past experience fully transfers to the current task but becomes misleading under partial query-memory overlap, a pattern confirmed by controlled experiments. To address this, the authors propose MEMTRIM, a plug‑and‑play framework that indexes memory evidence at write time and limits its reuse at read time, thereby reducing over-reliance without retraining and preserving useful memory benefits across models and memory architectures.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.