Find, Fix, Reason: Context Repair for Video Reasoning

• URL: http://arxiv.org/abs/2604.16243v1
• Date: Fri, 17 Apr 2026 17:04:19 GMT
• Title: Find, Fix, Reason: Context Repair for Video Reasoning
• Abstract summary: Reinforcement learning has advanced video reasoning in large multi-modal models.<n>We introduce an observation-level intervention: a frozen, tool-integrated teacher identifies the missingtemporal dependency and provides a minimal evidence patch.<n>We propose a Robust Improvement Reward (RIR) that aligns optimization with two goals: outcome validity through correct answers and dependency alignment rationales.
• Score: 45.021693494492666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and demands careful regularization. Dynamic context methods zoom into focused evidence but often require curated pretraining and two-stage tuning, and their context remains bounded by a small model's capability. In contrast, larger models excel at instruction following and multi-modal understanding, can supply richer context to smaller models, and rapidly zoom in on target regions via simple tools. Building on this capability, we introduce an observation-level intervention: a frozen, tool-integrated teacher identifies the missing spatiotemporal dependency and provides a minimal evidence patch (e.g., timestamps, regions etc.) from the original video while the question remains unchanged. The student answers again with the added context, and training updates with a chosen-rollout scheme integrated into Group Relative Policy Optimization (GRPO). We further propose a Robust Improvement Reward (RIR) that aligns optimization with two goals: outcome validity through correct answers and dependency alignment through rationales that reflect the cited evidence. Advantages are group-normalized across the batch, preserving on-policy exploration while directing it along causally meaningful directions with minimal changes to the training stack. Experiments on various related benchmarks show consistent accuracy gains and strong generalization. Web page and source code will be available at https://github.com/JethroJames/FFR.git.

Related papers

• Rank-Then-Act: Reward-Free Control from Frame-Order Progress [5.357451930622806]
  Rank-Then-Act (RTA) is a framework for learning control policies from expert video demonstrations without environment rewards.<n>We train a Vision-Language Model (VLM) offline as a progress-based ordinal scorer.<n>We compute the Spearman rank correlation between predicted progress rankings and true temporal indices, yielding a bounded, scale-invariant learning signal.
  arXiv  Detail & Related papers  (2026-07-02T08:50:32Z)
• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training [50.86545293331458]
  Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from.<n>We present a simple yet effective batch-adaptive objective that replaces fixed clipping with the normalized effective sample size of the policy ratios.
  arXiv  Detail & Related papers  (2026-05-12T16:44:47Z)
• STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering [28.670443420523796]
  STRIVE is a structured reinforcement learning framework for question answering.<n>It enriches reward signals and promotes more stable and informative policy updates.<n>It prioritizes frames most relevant to the input question while preserving temporal coverage.
  arXiv  Detail & Related papers  (2026-04-02T09:35:27Z)
• HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations [25.503211313768062]
  We propose a bilevel meta-learning method that performs augmentation directly in feature space to improve spurious correlation handling in the classifier head.<n>By operating at the backbone output rather than in pixel space, the method is highly efficient and stable, requiring only a few minutes of training on a single GPU.
  arXiv  Detail & Related papers  (2026-03-31T06:32:56Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach [53.727460222955266]
  Temporal Sentence Grounding in Videos (TSGV) aims to ground a natural language sentence in an untrimmed video. Recent studies have found that current benchmark datasets may have obvious moment annotation biases. We introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets.
  arXiv  Detail & Related papers  (2022-03-10T08:58:18Z)

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.