The authors developed SkillVine, a framework for refining libraries of reusable agent procedures from interaction trajectories.
Branching search improves how language agents evolve reusable skill libraries
SkillVine explores alternative library versions rather than committing every update to one linear sequence.
Chinese Tech
Kaiwei Liu · Jiqian Dong · Liran Dong · Shuai Mao · Mingming Zhao · Bufang Yang · +4 more
The Chinese University of Hong Kong · Noah’s Ark Lab, Huawei Technologies
Research Digest··2 min read
Liu et al.
Why this paper
From Noah’s Ark Lab, Huawei Technologies and The Chinese University of Hong Kong
In one line
SkillVine uses branching exploration to evolve LLM agent skill libraries, outperforming linear evolution on nine of ten benchmark-model combinations.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§