Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning

TL;DR

RLER introduces a dual paradigm for video reasoning that explicitly incorporates evidence during learning and inference, significantly improving reliability and interpretability of large multimodal models.

Contribution

The paper proposes RLER, a novel framework that decouples evidence generation from answer inference using reinforcement learning and evidence-based election, achieving state-of-the-art results.

Findings

RLER outperforms existing models on 8 benchmarks with an average of 6.3% improvement.

The approach uses an average of 3.1 candidates per question, balancing compute and quality.

Explicit evidence modeling enhances trustworthiness and interpretability in video reasoning.

Abstract

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.