Trendoday

Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning

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. M

  • Upvotes25
–Rank now
#3Peak rank
2Days on list
330Score · 7d
Nov 10, 2026First seen
Rank · 7 days

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.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 11:2817:2823:2805:2811:28 Nov 10, 11:28 UTC · #11Nov 10, 13:28 UTC · #8Nov 10, 15:28 UTC · #8Nov 10, 17:28 UTC · #7Nov 10, 19:28 UTC · #6Nov 10, 21:28 UTC · #6Nov 10, 23:28 UTC · #6Nov 11, 01:28 UTC · #6Nov 11, 03:28 UTC · #6Nov 11, 05:28 UTC · #3Nov 11, 07:28 UTC · #3Nov 11, 09:28 UTC · #3Nov 11, 11:28 UTC · #3

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hugging Face.

0132538 11:2817:2823:2805:2811:28 Nov 10, 11:28 UTC · 25Nov 10, 13:28 UTC · 33Nov 10, 15:28 UTC · 35Nov 10, 17:28 UTC · 36Nov 10, 19:28 UTC · 37Nov 10, 21:28 UTC · 37Nov 10, 23:28 UTC · 37Nov 11, 01:28 UTC · 37Nov 11, 03:28 UTC · 38Nov 11, 05:28 UTC · 38Nov 11, 07:28 UTC · 38Nov 11, 09:28 UTC · 38Nov 11, 11:28 UTC · 38

Questions

Is Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 11, 11:28 UTC, after 2 days of trending.

What is the highest rank Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning reached?

#3 on Hugging Face · Daily papers, on Nov 11, 05:28 UTC. Trendoday checks this list every 120 minutes.

How long has Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning been trending?

It was first seen on Nov 10, 2026 and has been on the list on 2 days (13 checks) since.