DAIR.AI(@dair_ai):Nice paper showing a better way to evolve agent skills. And they achieve 40–70% less token cost compared to frontier evolving methods. The idea is to let agents improve their skill prompts by ranking candidates with a learned rubric instead of running a full rollout to score every revision. Rollout cost is the reason skill self-evolution usually only patches observed failures. Every candidate edit needs a real agent run to evaluate. SkillLift trains a rubric to agree with real outcomes on which of two skills is better, since ranking needs fewer oracle runs than predicting each score. An inner loop revises skills against the frozen rubric at no rollout cost. An outer loop spends a few real rollouts to re-align the rubric by rank correlation. On SkillsBench and WildClawBench (147 tasks) with three models, it beats SkillOpt and CoEvoSkills in all six combinations, even when those baselines get twice the token budget. It reaches target performance with 40 to 70% fewer tokens. Paper:

2026.09.21 20:15

Nice paper showing a better way to evolve agent skills. And they achieve 40–70% less token cost compared to frontier evolving methods. The idea is to let agents improve their skill prompts by ranking candidates with a learned rubric instead of running a full rollout to score every revision. Rollout cost is the reason skill self-evolution usually only patches observed failures. Every candidate edit needs a real agent run to evaluate. SkillLift trains a rubric to agree with real outcomes on which of two skills is better, since ranking needs fewer oracle runs than predicting each score. An inner loop revises skills against the frozen rubric at no rollout cost. An outer loop spends a few real rollouts to re-align the rubric by rank correlation. On SkillsBench and WildClawBench (147 tasks) with three models, it beats SkillOpt and CoEvoSkills in all six combinations, even when those baselines get twice the token budget. It reaches target performance with 40 to 70% fewer tokens. Paper:

显示更多