About this paper
Reframe is a two-stage post-training framework that aligns visual agents’ observation states through evidence-aware reinforcement learning and observation-gated on-policy distillation, improving tool use and outperforming Mix-RL and vanilla MOPD across image and video benchmarks.
Agentic reinforcement learning (RL) and multi-teacher on-policy distillation (MOPD) offer complementary routes to post-training. For visual agents, however, tool use presents two related challenges. Models may overlook useful tool-returned observations, while poorly grounded actions can limit the evidence available for subsequent distillation. We introduce Reframe, a post-training framework that treats the observation state, rather than only the output distribution, as an object of alignment. First, Ground-Drop-GRPO (GD-GRPO) trains spatial and temporal specialists with evidence-aware rewards and stochastic removal of the original visual input, encouraging them to acquire grounded evidence…
agentic reinforcement learningmulti-teacher on-policy distillationMOPDvisual agentstool useobservation state alignmentGround-Drop-GRPOGD-GRPOevidence-aware rewardsstochastic removal of original visual input
- Upvotes
- 25
- Authors
- 4
- Published
- Nov 9, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning was first seen on Hugging Face · Daily papers on Nov 10, 2026. Since then it has appeared in 13 checks on 2 different days. Its best position was #3 of 30, reached on Nov 11, 05:28 UTC. It dropped off the list after Nov 11, 11:28 UTC.