CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding

• URL: http://arxiv.org/abs/2607.24582v1
• Date: Mon, 27 Jul 2026 15:49:42 GMT
• Title: CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
• Abstract summary: CADER (Confidence-Aware Dynamic Evidence Reasoning) is a training-free framework for adaptive and reliable long-video reasoning.<n>We show that CADER improves long-video reasoning while bypassing Stage2 for high-confidence samples.
• Score: 17.497595783869745
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-video understanding increasingly relies on large vision-language models and tool-augmented reasoning, but most systems apply the same inference procedure to every example regardless of difficulty. This uniform strategy invokes unnecessary tool-assisted processing for easy questions and provides limited control when difficult questions require fine-grained temporal evidence. We propose CADER (Confidence-Aware Dynamic Evidence Reasoning), a training-free framework for adaptive and reliable long-video reasoning. CADER first performs global reasoning over uniformly sampled frames and estimates answer confidence with a logit-margin signal, allowing high-confidence examples to exit early. For uncertain examples, CADER activates a second-stage tool-augmented loop that combines temporal cropping, lightweight semantic verification, and Relevance-Guided Resampling to progressively localize question-relevant evidence. This design treats tool use as a sample-level decision: a single global pass handles easy cases, while additional reasoning is reserved for examples where uncertainty suggests that more evidence is needed. Experiments on multiple VideoQA benchmarks show that CADER improves long-video reasoning while bypassing Stage~2 for high-confidence samples. Moreover, when applied to a backbone trained only with tool-free chain-of-thought supervision, CADER achieves competitive performance against specialized tool-augmented frameworks, suggesting a practical inference-time route for adaptive long-video reasoning.

Related papers

• 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)
• Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding [37.607009528052565]
  This work proposes Reflect-R1, the first Evidence-Driven self-correction framework for long video understanding.<n>The framework constructs a three-stage pipeline consisting of intuition, verification, and arbitration.<n>Our method significantly improves the genuine rectification rate and enables authentic self-correction strictly grounded in objective evidence.
  arXiv  Detail & Related papers  (2026-06-26T10:15:36Z)
• CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs [50.189987475377656]
  We propose CARE, a competence-aware reward shaping framework for adaptive reasoning length optimization in multimodal reasoning.<n> CARE maintains a smoothed competence estimate via an exponential moving average of pass rates, and uses it to route training into progressive stages.<n>Experiments on multiple video reasoning and general video understanding benchmarks demonstrate that CARE consistently improves reasoning accuracy, stabilizes reinforcement learning, and significantly enhances token efficiency.
  arXiv  Detail & Related papers  (2026-06-18T08:28:26Z)
• Efficient Test-Time Scaling via Temporal Reasoning Aggregation [5.87118425760756]
  We propose TRACE, a training-free framework for efficient test-time scaling.<n>TRACE determines when to terminate reasoning based on temporal aggregation of multi-step evidence.<n>We show that TRACE reduces reasoning token usage by 25-30% on average while maintaining accuracy within 1-2% of full-length reasoning.
  arXiv  Detail & Related papers  (2026-04-19T07:39:40Z)
• Clue Matters: Leveraging Latent Visual Clues to Empower Video Reasoning [14.945921705882725]
  This work bridges the perception-to-generation gap in MLLM video understanding, providing an interpretable, faithful reasoning paradigm for VideoQA applications.<n>Inspired by hierarchical human visual cognition, we propose ClueNet, a clue-aware video reasoning framework with a two-stage supervised fine-tuning paradigm.
  arXiv  Detail & Related papers  (2026-03-16T09:15:12Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• 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)
• Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute [60.151643048803145]
  We propose Fractional Reasoning, a framework that enables continuous control over reasoning intensity at inference time.<n>Our method operates by extracting the latent steering vector associated with deeper reasoning and reapplying it with a tunable scaling factor.<n> Experiments on GSM8K, MATH500, and GPQA demonstrate that Fractional Reasoning consistently improves performance across diverse reasoning tasks and models.
  arXiv  Detail & Related papers  (2025-06-18T21:15:59Z)
• VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning [12.293826084601115]
  Video anomaly understanding is essential for smart cities, security surveillance, and disaster alert systems.<n>Despite advances in anomaly detection, existing methods often lack interpretability and struggle to capture the causal and contextual aspects of abnormal events.<n>We introduce VAU-R1, a data-efficient framework built upon Multimodal Large Language Models (MLLMs), which enhances anomaly reasoning through Reinforcement Fine-Tuning (RFT)
  arXiv  Detail & Related papers  (2025-05-29T14:48:10Z)
• STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training [87.58996020705258]
  Video Large Language Models (Video-LLMs) have recently shown strong derivation in basic video understanding tasks.<n>Video-LLMs struggle with compositional reasoning that requires multi-step explicit-temporal inference across object relations, interactions and events.<n>We propose STEP, a novel graph-guided self-training method that enables VideoLLMs to generate reasoning-rich finetuning data from any raw videos to improve itself.
  arXiv  Detail & Related papers  (2024-11-29T11:54:55Z)

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.