The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4 games over 500 rounds, expanding accessible history degrades cooperation in 18 of 28 model--game settings, a pattern we term the memory curse. We isolate the underlying mechanism through three analyses. First, lexical analysis of 378,000 reasoning traces associates this breakdown with eroding forward-looking intent rather than rising paranoia. We validate this using targeted fine-tuning as a cognitive probe: a LoRA adapter trained exclusively on forward-looking traces mitigates the decay and transfers zero-shot to distinct games. Second, memory sanitization holds prompt length fixed while replacing visible history with synthetic cooperative records, which restores cooperation substantially, proving the trigger is memory content, not length alone. Finally, ablating explicit Chain-of-Thought reasoning often reduces the collapse, showing that deliberation paradoxically amplifies the memory curse. Together, these results recast memory as an active determinant of multi-agent behavior: longer recall can either destabilize or support cooperation depending on the reasoning patterns it elicits.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirectional causality, which underlies a phenomen…
Multi-agent Deep FBSDE Representation For Large Scale Stochastic Differential Games
In this paper we present a deep learning framework for solving large-scale multi-agent non-cooperative stochastic games using fictitious play. The Hamilton-Jacobi-Bellman (HJB) PDE associated with each agent is refor…
Autonomous RacingDecision MakingEfficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
In cooperative multi-agent reinforcement learning (MARL), agents aim to achieve a common goal, such as defeating enemies or scoring a goal. Existing MARL algorithms are effective but still require significant learning ti…
DecoderMulti-agent Reinforcement LearningQ-Learningreinforcement-learning+3Aggressive Sampling for Multi-class to Binary Reduction with Applications to Text Classification
We address the problem of multi-class classification in the case where the number of classes is very large. We propose a double sampling strategy on top of a multi-class to binary reduction strategy, which transforms the…
Binary ClassificationClassificationGeneral ClassificationMulti-class Classification+2Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations
When LLM conversations grow beyond the context window, old content must be evicted -- but how does the model recover it when needed? We propose cooperative paging: evicted segments are replaced with minimal keyword bookm…