The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents

Key points

• The problem is to reconcile the classical game-theoretic prediction that longer memory promotes cooperation with behavioral psychology findings that excessive human memory can undermine cooperation.
• There has been no systematic large-scale study of how changes in interaction-history length affect cooperation in LLM multi-agent social dilemmas.
• Prior LLM agent studies often used short interaction horizons, which may have missed the long-term effects of accumulated history on cooperative intent.
• We performed extensive experiments over 500 rounds in four repeated social dilemma games with seven LLMs, systematically varying the accessible memory length from 0 to 80 rounds.
• We analyzed more than 378,000 chain-of-thought reasoning traces with lexical analysis to quantify strategic intent, from future-oriented thinking to paranoia.
• We performed targeted fine-tuning, memory purification, and asymmetric-memory experiments to causally identify the mechanism and develop mitigation strategies.

Paper links

External research summaries. These are not HDATF publications or measured product results.