Video-FLAIR: Not Whether to Reason, But How

• URL: http://arxiv.org/abs/2608.26495v2
• Date: Fri, 28 Aug 2026 20:24:12 GMT
• Title: Video-FLAIR: Not Whether to Reason, But How
• Abstract summary: Video-FLAIR learns to select the appropriate reasoning mode for each query using reinforcement learning.<n>Video-FLAIR improves accuracy over the Qwen2.5-VL base model by +5.4 on MathVista, +4.8 on Video-Holmes, and +4.8 on Video-MMMU.
• Score: 3.4997248570131343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal queries can require different types of reasoning. Some can be answered via perceptual reasoning, extracting information directly from the visual signal, while others require compositional reasoning that combines observations or deliberative reasoning that evaluates competing hypotheses. However, many existing methods apply a uniform reasoning strategy across queries, leading to unnecessary computation on simple tasks and insufficient reasoning on complex ones. We introduce Video-FLAIR, a training framework that learns to select the appropriate reasoning mode for each query using reinforcement learning. During training, the model generates responses under all three modes for the same prompt, enabling direct comparison. A composite reward compares these responses to favor the most effective one based on correctness, grounding, and cost, while discouraging unsupported or misaligned deliberation. This yields a supervision signal for learning adaptive reasoning without per-query annotations. Video-FLAIR improves accuracy over the Qwen2.5-VL base model by +5.4 on MathVista, +4.8 on Video-Holmes, and +4.8 on Video-MMMU, while reducing average token usage to 95 compared to 417 for always-thinking baselines.

Related papers

• AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning [35.47019695877336]
  Chain-of-thought (CoT) reasoning can improve performance on difficult video questions but often wastes decoding tokens on simple ones.<n>We propose AdaThinkV, an adaptive framework for video reasoning that learns whether to reason explicitly without offline difficulty labels.<n>AdaThinkV achieves a mean accuracy of 40.79 with an average of 257.20 output tokens, outperforming the strongest evaluated adaptive baseline by 2.98 points.
  arXiv  Detail & Related papers  (2026-08-03T09:42:42Z)
• Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning [72.45536737928015]
  We propose Switch-Reasoner, a framework that learns to adaptively select reasoning modes for MLLMs.<n>It treats thinking as a virtual tool invocation and allows the model to either answer directly or invoke explicit reasoning before answering.<n>Experiments on 11 multimodal tasks show that Switch-Reasoner reduces unnecessary reasoning while maintaining strong performance.
  arXiv  Detail & Related papers  (2026-07-09T15:04:05Z)
• VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice [88.93674345138054]
  Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks.<n>We propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy.
  arXiv  Detail & Related papers  (2026-01-08T18:00:59Z)
• Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models [56.851611990473174]
  Reasoning over dynamic visual content remains a central challenge for large language models.<n>We propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency.<n>The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T18:59:58Z)
• Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models [33.398631680508814]
  We propose Answer-Consistent Reinforcement Learning that modifies the GRPO algorithm with an auxiliary consistency check.<n>We design a consistency-verification reward that grants a high reward only if both the original and the post-shuffle answers agree and are correct.<n>We evaluate ACRE on challenging Video Reasoning benchmarks and multimodal math reasoning benchmarks, achieving an average 2.2% and 1.5% improvement.
  arXiv  Detail & Related papers  (2025-10-11T08:32:52Z)
• MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos [22.10711693948861]
  We propose MMR-V: A Benchmark for Multimodal Deep Reasoning in Videos.<n>The benchmark is characterized by the following features.<n>Experiments reveal that current models still struggle with multi-modal reasoning.
  arXiv  Detail & Related papers  (2025-06-04T16:33:41Z)
• The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models [54.88805865447848]
  We show that instruct models achieve higher efficiency overall, and problem difficulty affects efficiency.<n>We propose COTHINK, a simple two-stage pipeline: an instruct model drafts a brief outline, and a thinking model expands it.<n>On GSM8K, MATH500, and AIME24, COTHINK cuts token usage by 21.1% while keeping accuracy on four thinking models, and remains competitive with strong efficiency baselines.
  arXiv  Detail & Related papers  (2025-05-28T06:24:45Z)
• Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models [67.87579664988199]
  TON is a two-stage training strategy for vision-language models (VLMs)<n>It introduces a think-or-not format that serves as a cold start for selective reasoning.<n>TON can reduce the completion length by up to 90% compared to vanilla GRPO.
  arXiv  Detail & Related papers  (2025-05-22T16:13:29Z)
• Thinkless: LLM Learns When to Think [57.857534644932194]
  Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference.<n>We propose Thinkless, a learnable framework that empowers an LLM to adaptively select between short-form and long-form reasoning.<n>On several benchmarks such as Minerva Algebra, MATH-500, and GSM8K, Thinkless is able to reduce the usage of long-chain thinking by 50% - 90%.
  arXiv  Detail & Related papers  (2025-05-19T17:24:16Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)

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.