Tag
EnvLunch 提出一种无标注的热身训练阶段，通过从可执行环境中采样并执行动作轨迹，让智能体根据最终观测恢复等价轨迹，从而在无需人工标注的情况下提升下游智能体强化学习性能，显著减少所需标注数据量。
This paper shows that language agents fail to reliably connect past actions with their outcomes when using interaction history, and proposes a simple outcome-labeling annotation plus a learned calibrator that selectively records experience, improving task success and reducing action repetition.
The paper introduces Trace, a credit-guided framework that compiles noisy interaction histories into executable walkthroughs to enhance long-horizon AI agent performance, showing significant improvements in experiments.
This article discusses the importance of trajectory learning in AI agent self-evolution and introduces the Apodex 1.1 system and open-source tool FrontierAgent for executing and evaluating long-duration research tasks.