Video Reasoning without Training

• URL: http://arxiv.org/abs/2510.17045v1
• Date: Sun, 19 Oct 2025 23:17:13 GMT
• Title: Video Reasoning without Training
• Abstract summary: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought.<n>We show that using entropy of the model's output as a signal, we discover that the high-quality models go through a series of micro-explorations and micro-exploitations.<n>We then use these novel, theoretically-grounded insights to tune the model's behavior directly at inference.
• Score: 38.74334895026965
• License: http://creativecommons.org/licenses/by/4.0/
• 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. Moreover, the mechanisms that control the thinking process in these reasoning models are very limited. In this paper, using entropy of the model's output as a signal, we discover that the high-quality models go through a series of micro-explorations and micro-exploitations which keep the reasoning process grounded (i.e., avoid excessive randomness while the model is exploring or thinking through an answer). We further observe that once this "thinking" process is over, more accurate models demonstrate a better convergence by reducing the entropy significantly via a final exploitation phase (i.e., a more certain convergence towards a solution trajectory). We then use these novel, theoretically-grounded insights to tune the model's behavior directly at inference, without using any RL or supervised fine-tuning. Specifically, during inference, our proposed approach called V-Reason (Video-Reason) adapts the value cache of the LMM via a few optimization steps on a small, trainable controller using an entropy-based objective, i.e., no supervision from any dataset or RL is necessary. This tuning improves the model's micro-exploration and exploitation behavior during inference. Our experiments show that our proposed method achieves significant improvements over the base instruction-tuned models across several video reasoning datasets, narrowing the gap with RL-trained models to within 0.6% average accuracy without any training, while offering massive efficiency benefits: output tokens are reduced by 58.6% compared to the RL model.

Related papers

• Scalable Offline Model-Based RL with Action Chunks [60.80151356018376]
  We study whether model-based reinforcement learning can provide a scalable recipe for tackling complex, long-horizon tasks in offline RL.<n>We call this recipe textbfModel-Based RL with Action Chunks (MAC).<n>We show that MAC achieves the best performance among offline model-based RL algorithms, especially on challenging long-horizon tasks.
  arXiv  Detail & Related papers  (2025-12-08T23:26:29Z)
• Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models [57.49136894315871]
  New paradigm of test-time scaling has yielded remarkable breakthroughs in reasoning models and generative vision models.<n>We propose one solution to the problem of integrating test-time scaling knowledge into a model during post-training.<n>We replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise.
  arXiv  Detail & Related papers  (2025-08-13T17:33:37Z)
• RAST: Reasoning Activation in LLMs via Small-model Transfer [33.32587030836428]
  Reinforcement learning (RL) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs)<n>Applying RL at scale remains intimidatingly resource-intensive, requiring multiple model copies and extensive GPU workloads.<n>We propose RAST, a simple yet effective method that transfers reasoning behaviors by injecting RL-induced probability adjustments from a small RL-trained model into larger models.
  arXiv  Detail & Related papers  (2025-05-30T17:57:08Z)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models.<n>We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• Score as Action: Fine-Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning [15.789898162610529]
  Reinforcement learning from human feedback (RLHF) has become a crucial step in building reliable generative AI models.<n>This study is to develop a disciplined approach to fine-tune diffusion models using continuous-time RL.
  arXiv  Detail & Related papers  (2025-02-03T20:50:05Z)
• Predictable MDP Abstraction for Unsupervised Model-Based RL [93.91375268580806]
  We propose predictable MDP abstraction (PMA) Instead of training a predictive model on the original MDP, we train a model on a transformed MDP with a learned action space. We theoretically analyze PMA and empirically demonstrate that PMA leads to significant improvements over prior unsupervised model-based RL approaches.
  arXiv  Detail & Related papers  (2023-02-08T07:37:51Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• ReLACE: Reinforcement Learning Agent for Counterfactual Explanations of Arbitrary Predictive Models [6.939617874336667]
  We introduce a model-agnostic algorithm to generate optimal counterfactual explanations. Our method is easily applied to any black-box model, as this resembles the environment that the DRL agent interacts with. In addition, we develop an algorithm to extract explainable decision rules from the DRL agent's policy, so as to make the process of generating CFs itself transparent.
  arXiv  Detail & Related papers  (2021-10-22T17:08:49Z)
• Revisiting Design Choices in Model-Based Offline Reinforcement Learning [39.01805509055988]
  Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies. This paper compares and designs novel protocols to investigate their interaction with other hyper parameters, such as the number of models, or imaginary rollout horizon.
  arXiv  Detail & Related papers  (2021-10-08T13:51:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.