Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
VACE: Validation-Gated Alternating Co-Evolution of Agent Models and Harnesses
Jiexing Qi, Yu He, Jun Liu +9
Language model agents can be improved by updating their model weights or refining the harness that guides task execution. These components are coupled: weight updates change how th…
cs.LG2026
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
Wen Jiang, Mingmin Chu, Yimeng Tian +6
Self-evolving agents advance toward autonomy by optimizing their harness---prompts, skills, tools, and execution logic---based on environmental feedback. This paradigm, however, is…