works on
alpha discovery 1closed-loop hypothesis-to-code 1financial factor generation 1LLM-driven research 1memory systems 1quantitative trading 1

From the 1 of 6 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions

Haochen Luo, Yi Huang, Sichun Luo +5

Self-evolving frameworks usually optimize task solutions while treating the surrounding harness as fixed. We introduce Harness-Aware Self-Evolving (HASE), an agentic reinforcement-…