The paper introduces Activation Replay, a training‑free method that improves reasoning in post‑trained large multimodal models (LMMs) by replaying low‑entropy activations from the base model’s input context. It shows that Reinforcement Learning with Verifiable Rewards (RLVR) shifts low‑entropy activations and that modulating these activations enhances reasoning across tasks such as mathematics, visual agents, and video reasoning. Experiments demonstrate that Activation Replay outperforms alternatives like high‑entropy replay or direct cross‑model intervention, boosting Pass@K and broadening RLVR’s reasoning coverage.
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:2510. 17045v2 Announce Type: replace-cross Abstract: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in substantial computational overhead during both training and inference.
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.
arXiv:2512. 10414v2 Announce Type: replace Abstract: Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs).
arXiv:2510. 21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models.
The paper introduces PIVOT, a dual-level learning framework designed to improve visually-grounded multimodal reasoning in large vision-language models. PIVOT employs a self‑calibrated experience replay mechanism to selectively reuse valuable visual reasoning trajectories, and a vision‑guided advantage allocation scheme that assigns extra rewards to tokens with strong visual support. Experiments on multiple benchmarks show that PIVOT enhances the multimodal reasoning performance of these models.
arXiv:2606. 03937v1 Announce Type: new Abstract: While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether this mechanism still holds in visual reasoning.
arXiv:2607. 10966v1 Announce Type: new Abstract: We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning.
Co‑RL is a multi‑agent reinforcement learning framework that trains several decoupled models without shared parameters, using rewards generated by their peers. By increasing cohort diversity—through heterogeneous model families, varying sizes, and rephrased training samples—Co‑RL reduces self‑reinforcing feedback loops, preserves behavioral diversity, and prevents training collapse. Across both text‑only and multimodal benchmarks, Co‑RL outperforms base models and prior label‑free methods, achieving gains of 3.0‑8.6% on seven text benchmarks and 2.3‑7.2% on four multimodal benchmarks, while matching or surpassing supervised approaches without any ground‑truth labels.
The paper introduces DyCPO, a co‑evolutionary framework that jointly optimizes token selection and adaptive counterfactual intervention for video reasoning. It builds a multi‑role dependence metric to balance visual exploration with answer‑relevance mining, suppressing filler tokens and spurious visual noise. By deriving counterfactual signals from the model’s own successful and failed rollouts, DyCPO enables self‑diagnostic analysis and co‑evolution of the optimization objective with the policy, leading to consistent performance gains on complex video reasoning benchmarks.
The paper introduces OWLET, an on-policy weighted learning method for post-training Video Large Language Models. OWLET leverages a richer teacher view that combines global temporal context with question-conditioned local windows to provide visual evidence, and it employs evidence-aware credit redistribution and spatiotemporal state alignment to better utilize this evidence during reinforcement learning. The approach aims to improve video reasoning by aligning token-level supervision with spatiotemporal representations.
arXiv:2608. 08326v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective approach for improving multimodal reasoning.