@GoogleResearch: ReasoningBank, a novel agent memory framework, enables LLM agents to continuously learn from both successful & failed e…
Summary
Google Research introduces ReasoningBank, an agent memory framework that lets LLM agents learn continuously from successes and failures, improving success rates and efficiency.
Similar Articles
ReasoningBank: an agent memory framework that lets LLM agents keep learning from wins and losses
ReasoningBank gives LLM agents a memory layer so they continuously learn from both successes and failures, driving higher task success rates and faster execution.
PolicyBank: Evolving Policy Understanding for LLM Agents
PolicyBank proposes a memory mechanism that enables LLM agents to autonomously refine their understanding of organizational policies through iterative interaction and corrective feedback, closing specification gaps that cause systematic behavioral divergence from true requirements. The work introduces a systematic testbed and demonstrates PolicyBank can close up to 82% of policy-gap alignment failures, significantly outperforming existing memory mechanisms.
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
MRAgent introduces a novel graph-based memory framework that dynamically reconstructs memory during reasoning, achieving up to 23% improvement on long-horizon benchmarks while reducing computational costs.
@rohanpaul_ai: New Illinois+ Tsinghua University and other labs study finds that LLM agents still have unreliable memory and that it c…
A study by University of Illinois and Tsinghua University finds that LLM agents' memory becomes unreliable when continuously rewritten, with performance dropping from 100% to 54% on ARC-AGI tasks. The paper proposes preserving raw episodes instead of always summarizing them.
Human-Inspired Memory Architecture for LLM Agents
Microsoft researchers propose a biologically-inspired memory architecture for LLM agents that incorporates mechanisms like sleep-phase consolidation and interference-based forgetting to manage persistent memory efficiently.