ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents

TL;DR

This paper introduces ActMem, an innovative memory framework for LLM agents that combines memory retrieval with causal reasoning, enhancing their ability to handle complex, memory-dependent tasks effectively.

Contribution

ActMem uniquely integrates causal reasoning and semantic graph structures into memory management, advancing beyond passive retrieval to active, reasoning-based memory use in LLM agents.

Findings

ActMem outperforms existing methods in complex reasoning tasks.

The ActMemEval dataset effectively evaluates reasoning capabilities.

Active causal reasoning improves memory-dependent task performance.

Abstract

Effective memory management is essential for large language model (LLM) agents handling long-term interactions. Current memory frameworks typically treat agents as passive "recorders" and retrieve information without understanding its deeper implications. They may fail in scenarios requiring conflict detection and complex decision-making. To bridge this critical gap, we propose a novel actionable memory framework called ActMem that integrates memory retrieval with active causal reasoning. ActMem transforms unstructured dialogue history into a structured causal and semantic graph. By leveraging counterfactual reasoning and commonsense completion, it enables agents to deduce implicit constraints and resolve potential conflicts between past states and current intentions. Furthermore, we introduce a comprehensive dataset ActMemEval to evaluate agent reasoning capabilities in logic-driven scenarios, moving beyond the fact-retrieval focus of existing memory benchmarks. Experiments demonstrate that ActMem significantly outperforms state-of-the-art baselines in handling complex, memory-dependent tasks, paving the way for more consistent and reliable intelligent assistants.