Harness Annealing: Learning to Act with Less External Control
Language agents rely on external harnesses to track state, organize workflows, and verify answers. Beyond providing tools and information, these harnesses supply control decisions about what to investigate, whether to revise, and when to stop. Training on successful harness-supported trajectories can improve task perfo...
Yingxuan Yang, Hua-Can Chai, Ying Wen
· 0 citations