Puls Dane publiczne, aktualizowane automatycznie
arXiv – nowe publikacje publikacja

ModHarness-RL: Recasting Harnesses as Learnable and Evolving Programs for Agentic RL

[Sztuczna inteligencja] Autorzy: Zelin He, Siyu Zhu, Jacob Helwig i 5 więcej

Agentic reinforcement learning (RL) increasingly relies on a harness, the scaffold around the model that decides what it sees of its own interaction and what guidance it receives. Most existing approaches train under a hand-written harness that stays fixed throughout. However, an effective harness depends on the domain, the data and the model, and keeps changing as the model trains. We introduce ModHarness-RL, which recasts the harness as programs that are learned from data and evolve as the model trains with RL. ModHarness-RL records the interaction as structured State, a set of typed blocks, and two core components of the harness are programs over these blocks, a Compression program that assembles the accumulated history into the model's context and a Steering program that supplies guidance when behavior deviates. During RL training, candidate programs are proposed from recent traject…

Kategoria arxiv
cs.AI
Kategoria
Sztuczna inteligencja
Pdf
https://arxiv.org/pdf/2611.18533v1

Otwórz oryginał w źródle ↗

Więcej z tego źródła

Wszystkie