LabEvolver: 訓練不要の経験進化による安全で接地されたウェットラボエージェント
LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents
実行経験からエピソード記憶を獲得し、安全検証を伴う適応的知覚・計画を行う訓練不要のフレームワークを提案。pH調整タスクで時間と安全介入を大幅削減し、ALFWorldでも成功率を向上させた。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Jingya Wang, Yuyang Gao, Liuzhenghao Lv, Yonghong Tian, Yuyang Liu
分類: cs.RO, cs.AI
原文アブストラクト
We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience. LabEvolver couples a state-grounded inner trial loop for adaptive perception, online planning, and safety validation with an outer evolution loop that distills completed trajectories into reusable skill, strategy, and safety experience. On robotic solution-preparation tasks, LabEvolver demonstrates real-world feasibility, reducing pH-regulation completion time and safety-gate intercepts by 48.2% and 60.0%, respectively. On ALFWorld, it further improves cumulative success rate within 20 steps from 76.2% with ReAct to 91.4% over 500 continual tasks, showing generality beyond wet-lab settings. These results support learn-by-doing experience evolution as a feasible path toward closed-loop automated scientific discovery. The project page is available at https://andygao6186.github.io/LabEvolver/.
