AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

Learning Consistency in Reward Modeling for Multi-Modal Reasoning

Chen Li, Bolin Ni, Boxin Zhang, Ke Ye, Jinnian Zhang, Houwen Peng, Han Hu, Nanning Zheng

ECCV 2026 · Large language models › Reasoning and chain of thought · approach: RL with verifiable rewards for reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use soft continuous reward instead of hard rewardCRM-RL-7B · MathVistaaccuracy: 74.3% -> 75.2%Improved
use soft reward instead of hard reward (Qwen3-VL-8B)CRM-RL-8B · Avg of 4 math benchmarksAvg accuracy: 67.6% -> 68.5%Improved
replace rule-based reward with CRM rewardQwen2.5-VL-7B RL · MathVista and MathVisionaccuracy: +2.8% on MathVista, +2.0% on MathVisionImproved
replace CompassVerifier reward with CRM hard rewardQwen2.5-VL-7B RL · Avg of 4 math benchmarksAvg accuracy: 56.8% -> 57.4%Improved
add chain-of-thought to CRM (hard reward) (ablation)CRM-RL-7B · MathVistaaccuracy: 73.4% -> 74.3%Improved
add chain-of-thought to CRM (soft reward) (ablation)CRM-RL-7B · MathVistaaccuracy: 73.1% -> 75.2%Improved
add chain-of-thought to CRM (soft reward) (ablation)CRM-RL-7B · MathVisionaccuracy: 28.8% -> 30.6%Improved
add CoT to CRM soft reward judging (ablation)CRM soft reward · 50 hard casesReward accuracy: 58.0% -> 72.0%Improved
add CoT in static judging (ablation)CRM · Consistency validation setVal accuracy: 97.2% -> 98.0%Improved
add image input to the consistency reward model (ablation)CRM · Consistency validation setVal accuracy: 98.0% -> 96.7%Hurt
scale reward model from 1.5B to 7B (ablation)CRM · Win rate vs VLMEvalKit (Avg)Win rate: 64.5% -> 73.5%Improved
scale reward model from 1.5B to 7B (ablation)CRM · RL test accuracy (Avg)accuracy: 51.9% -> 52.6%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy