The paper introduces PACE, a method that enhances multimodal reinforcement learning with verifiable rewards (RLVR) by using pairwise token contrast and adaptive trajectory confidence. Pairwise token contrast evaluates each token under four teacher views—combining correct/incorrect hints with image presence or absence—to isolate image-dependent support, while adaptive trajectory confidence normalizes teacher predictions to guide credit redistribution. Experiments demonstrate that PACE outperforms existing approaches on multiple multimodal reasoning benchmarks, achieving top accuracy across three backbones and the Qwen3‑VL‑8B‑Instruct model.
arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...
arXiv:2601.08010v4 Announce Type: replace Abstract: Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoni...
arXiv:2609.39120v1 Announce Type: new Abstract: On-policy distillation (OPD) improves reasoning by providing token-level supervision from a teacher on a student's own trajectories. Existing methods p...
arXiv:2606. 05718v1 Announce Type: cross Abstract: On-policy distillation (OPD) improves reasoning by training a student on trajectories sampled from its own policy under supervision from a teacher.
arXiv:2610.14939v1 Announce Type: new Abstract: GRPO-style reinforcement learning has advanced vision-language reasoning, but its sequence-level rewards provide limited credit assignment for individu...
arXiv:2610.16735v1 Announce Type: cross Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal di...
arXiv:2606. 07000v1 Announce Type: new Abstract: Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models (LVLMs).
The paper introduces EASE, a method that enhances multimodal reinforcement learning with verifiable rewards (RLVR) by adding visual‑evidence process supervision. EASE transforms annotated evidence regions into smoothed visual‑token targets and uses them to guide attention during RL training, but only on high‑reward trajectories. Experiments on Qwen2.5‑VL‑7B, Qwen3‑VL‑4B, and Qwen3‑VL‑8B show that EASE improves average scores over DAPO by 2.5 to 3.1 points across perception, hallucination, visual math, and multimodal reasoning benchmarks, and diagnostics confirm better alignment of visual attention with annotated evidence.
The paper introduces ViMoD, a lightweight framework that dynamically manages visual memory for multimodal large language models. ViMoD uses Deformable Aggregation of Region-wise Tokens (DART) to create content‑adaptive coarse representations linked to recoverable fine tokens, and Temporal Routing for Adaptive Contextual Evidence (TRACE) to anticipate and adjust evidence needs during reasoning. On the Qwen3‑VL‑4B model, ViMoD achieves superior performance across eight reasoning benchmarks with only a 20% visual token budget and minimal additional parameters.
arXiv:2609.36838v1 Announce Type: cross Abstract: Visual agents solve problems by interleaving reasoning with image operations, and on-policy distillation (OPD) provides guidance from a strong teache...
arXiv:2512. 03438v3 Announce Type: replace Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers.
OPD‑Aha is a privileged on‑policy distillation method that improves multimodal reasoning by reconstructing the distillation target from the teacher’s isolated visual preference instead of relying on fragile teacher‑student discrepancies. It suppresses continuations that contradict the image, encouraging students to interrupt flawed reasoning with reflection tokens such as "wait" and "actually." This approach leads to consistent improvements across fine‑grained perception and complex multimodal reasoning benchmarks.