Google · Google Research
ReasoningBank: Enabling agents to learn from experience
Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.
★ Tier-1 Source
Jun Yan and Chen-Yu Lee, Research Scientists, Google Cloud.
Key facts
- This research was conducted by Siru Ouyang, Jun Yan, the reporter-Hung Hsu, Yanfei Chen, Ke Jiang, Zifeng Wang, Rujun Han, Long T
- Jun Yan and Chen-Yu Lee, Research Scientists, Google Cloud
- To bridge this gap, in their ICLR paper, " ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory ", they introduce a novel agent memory framework ( github ) that distills useful insights
- Using the ReAct prompting strategy as the foundation for all agents, they compared ReasoningBank against three memory configurations: a memory-free baseline (Vanilla ReAct), Synapse (Trajectory Memory)
Summary
ReasoningBank is a novel agent memory framework that uses successful and failed experiences to distill generalizable reasoning strategies, enabling an agent to continuously learn from experience after deployment. Agents are becoming increasingly crucial in tackling complex real-world tasks, ranging from general web navigation to assisting with extensive software engineering codebases. Agents approaching each new task without a memory mechanism will repeatedly make the same strategic errors and discard valuable insights. To bridge this gap, in their ICLR paper, " ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory ", they introduce a novel agent memory framework ( github ) that distills useful insights from both successful and failed experiences for test-time self-evolution.