ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL

Xingyu Lu, Jinpeng Wang, YiFan Zhang, Shijie Ma, Xiao Hu, Tianke Zhang, Haonan fan, Kaiyu Jiang, Changyi Liu, Kaiyu Tang, Bin Wen, Fan Yang, Tingting Gao, Han Li, Chun Yuan · Feb 26, 2026 · Citations: 0

Automatic Metrics General

Open arXiv RSS feed

Abstract

We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks. Specifically, to enhance Identifiability, we provide the reward model with full reference solutions as context, enabling fine-grained process verification to filter out false positives (samples with the right answer but low-quality reasoning process). To improve Reachability, we introduce a multi-turn sampling strategy where the reward model generates mistake reports for failed attempts, guiding the policy to "recover" correct responses from previously all-negative groups. Experimental results on 11 perception and reasoning benchmarks show that ContextRL significantly improves knowledge discovery efficiency. Notably, ContextRL enables the Qwen3-VL-8B model to achieve performance comparable to the 32B model, outperforming standard RLVR baselines by a large margin while effectively mitigating reward hacking. Our in-depth analysis reveals the significant potential of contextual information for improving reward model accuracy and document the widespread occurrence of reward hacking, offering valuable insights for future RLVR research.

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: General

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.35
Flags: low_signal, possible_false_positive

Research Summary

Contribution Summary

We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks.
Specifically, to enhance Identifiability, we provide the reward model with full reference solutions as context, enabling fine-grained process verification to filter out false positives (samples with the right answer but low-quality reasonin
To improve Reachability, we introduce a multi-turn sampling strategy where the reward model generates mistake reports for failed attempts, guiding the policy to "recover" correct responses from previously all-negative groups.

Why It Matters For Eval

Experimental results on 11 perception and reasoning benchmarks show that ContextRL significantly improves knowledge discovery efficiency.