arXiv · 2611.19244
Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns
Abstract
On-policy distillation (OPD) transfers specialized capabilities to language-model agents, but its cross-domain effects on interaction remain unclear. We investigate how OPD reshapes ReAct interaction patterns across mathematics, ALFWorld, and $τ^2$-bench, focusing on reasoning, actions, and observation acquisition. General-reasoning supervision reduces mathematical tool attempts from 70.4% to 14.4% while increasing accuracy from 16.7% to 38.0%; code-interpreter supervision improves household actions and retail queries. In contrast, ALFWorld supervision reduces $τ^2$-bench accuracy from 41.5% to 6.6%, accompanied by frequent tool calls that violate user-information dependencies. To address negative transfer using only source-domain training trajectories, we explore selective OPD guided by teacher preference changes before and after domain-specific RL. Retaining the top 95% of positions raises $τ^2$ accuracy from 11.5% to 29.9% with a source-learning trade-off.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Deyang Kong, Zhaoyi Li, Sijian Ren, Yuan Wei, Ying Wei, Defu Lian, Shikun Zhang, Wei Ye. 2026-11-14. Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns. https://searcharxiv.com/abs/2611.19244
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.