Saved in:
Bibliographic Details
Main Authors: Yang, Songyuan, Yu, Weijiang, Ma, Jilin, Liu, Ziyu, Tang, Guijian, Yang, Wenjing, Tan, Huibin, Xiao, Nong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.04379
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908939632771072
author Yang, Songyuan
Yu, Weijiang
Ma, Jilin
Liu, Ziyu
Tang, Guijian
Yang, Wenjing
Tan, Huibin
Xiao, Nong
author_facet Yang, Songyuan
Yu, Weijiang
Ma, Jilin
Liu, Ziyu
Tang, Guijian
Yang, Wenjing
Tan, Huibin
Xiao, Nong
contents Video reasoning has advanced with large multimodal models (LMMs), yet their inference is often a single pass that returns an answer without verifying whether the reasoning is evidence-aligned. We introduce Reinforce to Learn, Elect to Reason (RLER), a dual paradigm that decouples learning to produce evidence from obtaining a reliable answer. In RLER-Training, we optimize the policy with group-relative reinforcement learning (RL) and 3 novel task-driven rewards: Frame-sensitive reward grounds reasoning on explicit key frames, Think-transparency reward shapes readable and parsable reasoning traces, and Anti-repetition reward boosts information density. These signals teach the model to emit structured, machine-checkable evidence and potentiate reasoning capabilities. In RLER-Inference, we apply a train-free orchestrator that generates a small set of diverse candidates, parses their answers and cited frames, scores them by evidence consistency, confidence, transparency, and non-redundancy, and then performs a robust evidence-weighted election. This closes the loop between producing and using evidence, improving reliability and interpretability without enlarging the model. We comprehensively evaluate RLER against various open-source and RL-based LMMs on 8 representative benchmarks. RLER achieves state of the art across all benchmarks and delivers an average improvement of 6.3\% over base models, while using on average 3.1 candidates per question, indicating a favorable balance between compute and quality. The results support a simple thesis: making evidence explicit during learning and electing by evidence during inference is a robust path to trustworthy video reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04379
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning
Yang, Songyuan
Yu, Weijiang
Ma, Jilin
Liu, Ziyu
Tang, Guijian
Yang, Wenjing
Tan, Huibin
Xiao, Nong
Computer Vision and Pattern Recognition
Video reasoning has advanced with large multimodal models (LMMs), yet their inference is often a single pass that returns an answer without verifying whether the reasoning is evidence-aligned. We introduce Reinforce to Learn, Elect to Reason (RLER), a dual paradigm that decouples learning to produce evidence from obtaining a reliable answer. In RLER-Training, we optimize the policy with group-relative reinforcement learning (RL) and 3 novel task-driven rewards: Frame-sensitive reward grounds reasoning on explicit key frames, Think-transparency reward shapes readable and parsable reasoning traces, and Anti-repetition reward boosts information density. These signals teach the model to emit structured, machine-checkable evidence and potentiate reasoning capabilities. In RLER-Inference, we apply a train-free orchestrator that generates a small set of diverse candidates, parses their answers and cited frames, scores them by evidence consistency, confidence, transparency, and non-redundancy, and then performs a robust evidence-weighted election. This closes the loop between producing and using evidence, improving reliability and interpretability without enlarging the model. We comprehensively evaluate RLER against various open-source and RL-based LMMs on 8 representative benchmarks. RLER achieves state of the art across all benchmarks and delivers an average improvement of 6.3\% over base models, while using on average 3.1 candidates per question, indicating a favorable balance between compute and quality. The results support a simple thesis: making evidence explicit during learning and electing by evidence during inference is a robust path to trustworthy video reasoning.
title Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.04379