Agents
Nice paper showing a better way to evolve agent skills. And they achieve 40–70% less token cost compared to frontier evolving methods. The i…
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
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: https://academy.dair.ai/papers/skilllift-learning-dense-rubrics-from-sparse-oracles-for-efficient-skill-evoluti-2609.15396
Related
- New paper from Microsoft on Self-Evolving Agent Skills
- Nice paper with great insights on improving self-evolving agents. Self-evolving agents fail in three specific ways: 1. Terminal-only feedbac…
- cool new paper on self-improving agents
- Great paper on self-improving agents. Why? We need to think more deeply about AI agent system design. The protocol specifies a framework for…
Source: DAIR.AI (X) | 2026-09-21