Temporal-Aware Reasoning Optimization for Video Temporal Grounding

• URL: http://arxiv.org/abs/2606.09248v1
• Date: Mon, 08 Jun 2026 09:21:01 GMT
• Title: Temporal-Aware Reasoning Optimization for Video Temporal Grounding
• Abstract summary: We propose TaRO (Temporal-Aware Reasoning Optimization), a framework that explicitly enhances the model's ability of thinking with time.<n>First, we introduce a Constructive Reasoning Exploration that leverages pre-generated dense captions to construct reasoning paths grounded in explicit visual cues and timestamps.<n>Second, to evaluate reasoning quality, we design a Temporal-Sensitivity Reward. High-quality reasoning should be anchored to specific events and timestamps.
• Score: 55.29748680163419
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-modal Large Language Models (MLLMs) have achieved remarkable progress in video temporal grounding with reinforcement learning for generating reasoning paths. However, existing models often produce superficial reasoning, which offers limited guidance for precise temporal localization. This limitation stems from (1) inefficient random exploration and (2) reward functions that focus solely on the answer correctness while ignoring reasoning quality. To address these issues, we propose TaRO (Temporal-Aware Reasoning Optimization), a framework that explicitly enhances the model's ability of thinking with time. First, we introduce a Constructive Reasoning Exploration that leverages pre-generated dense captions to construct reasoning paths grounded in explicit visual cues and timestamps, enabling efficient exploration of high-quality time-aware reasoning. Second, to evaluate reasoning quality, we design a Temporal-Sensitivity Reward. High-quality reasoning should be anchored to specific events and timestamps. If the event boundary under thinking is disrupted, such reasoning should become invalid, leading to a drop in the logit of the reasoning path. We utilize this drop as a critique of reasoning quality. Finally, TaRO follows a progressive curriculum, which starts by utilizing this reward to select better constructed reasoning paths, and evolves to a free exploration phase where the model autonomously generates effective reasoning. Experiments demonstrate that TaRO achieves state-of-the-art performance on VTG benchmarks. Code is available at https://github.com/oceanflowlab/TaRO.

Related papers

• TimeThink: Reasoning with Time for Video LLMs [28.549802513886046]
  We propose TimeThink, a reinforcement learning framework that guides temporal evidence discovery in Video-LLMs.<n>Our key idea is to treat temporal clue steps as the fundamental optimization primitive of video reasoning.<n>To enable scalable training, we construct TimeThink-RFT-20K, a dataset with automatically derived temporal evidence segments.
  arXiv  Detail & Related papers  (2026-07-06T13:50:15Z)
• Rationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Models [39.75347938309383]
  We propose the rationale-grounded in-context learning for time series reasoning, where rationales work as guiding reasoning units rather than post-hoc explanations.<n>We conduct extensive experiments to demonstrate the effectiveness and efficiency of our proposed RationaleTS on three-domain time series reasoning tasks.
  arXiv  Detail & Related papers  (2026-01-06T12:27:04Z)
• 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)
• TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding [28.79516973256083]
  Temporal Video Grounding aims to precisely localize video segments corresponding to natural language queries.<n>We propose Timestamp Anchor-constrained Reasoning for Temporal Video Grounding (TAR-TVG)<n>TAR-TVG introduces timestamp anchors within the reasoning process to enforce explicit supervision to the thought content.
  arXiv  Detail & Related papers  (2025-08-11T06:59:32Z)
• Lost at the Beginning of Reasoning [85.17612793300238]
  We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.
  arXiv  Detail & Related papers  (2025-06-27T09:53:57Z)
• 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)
• Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models [58.64449765678416]
  We introduce landscape of thoughts (LoT) to inspect the reasoning trajectories with certain reasoning methods on any multi-choice dataset.<n>LoT distinguishes between strong and weak models, correct and incorrect answers, as well as different reasoning tasks.<n>We showcase this advantage by adapting LoT to a lightweight verifier that evaluates the correctness of trajectories.
  arXiv  Detail & Related papers  (2025-03-28T06:09:51Z)
• Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency [53.8779374188643]
  We propose a principled framework with provable regret guarantees to orchestrate reasoning and acting. Specifically, we design a prompt template for reasoning that learns from the memory buffer and plans a future trajectory over a long horizon. At each step, the LLM agent takes the initial action of the planned trajectory ("act for now"), stores the collected feedback in the memory buffer, and reinvokes the reasoning routine to replan the future trajectory from the new state.
  arXiv  Detail & Related papers  (2023-09-29T16:36:39Z)

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.