Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?
- Published
- Source
- arXiv
- Paper number
- 872
- Field
- AI / General
- arXiv ID
- 2608.09629
Key points
- It is the first systematic attempt to question whether framework-defined improvement procedures, or optimization meta-policies, are still necessary.
- Using GPT-5.5, OEO beats the SKILLOPT and GEPA pipelines in 12 of 14 comparisons, with 1 tie and 1 loss.
- OEO uses only 34.3 percent of the median tokens used by SKILLOPT, which demonstrates its efficiency.
- For mid-sized models, prescribed pipelines work better, which reveals a model-capacity boundary for adaptive division of labor.
- The prescribed procedures make optimization paths more consistent, but the path differences are larger than the final action differences.
Paper links
External research summaries. These are not HDATF publications or measured product results.