arXiv cs.LG
· Papers
Memory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memory
arXiv:2606.23195v2 Announce Type: replace Abstract: Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence. Recent work shows that agent memories degrade during continuous consolidation. However, existing research assumes memories are derived from unbiased experiences. In