The authors replaced free-form skill instructions with graph-structured natural-language artifacts.
Graph-structured skills improve LLM agents through evolutionary optimization
Across five agent benchmarks, evolving workflow graphs outperformed iterative optimization of unstructured natural-language instructions.
Top University
Rui Sun · Zhi Zheng · Zhenkun Wang · Zhichao Lu
City University of Hong Kong · National University of Singapore · Southern University of Science and Technology
Research Digest··2 min read
Thread:Skill Selection for Agents
The authors represent agent skills as directed graphs whose nodes specify execution steps and whose edges define context-dependent transitions.
Why this paper
From City University of Hong Kong and 2 others · Released code · Part of Skill Selection for Agents, now 14 papers
In one line
Graph-structured skills improve LLM agent performance more than unstructured skill optimization.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·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.
§