Evidence-RL: Towards Evidence-intensive Visual Reasoning

arXiv:2608.08021 · cs.CV, cs.AI · Submitted 2026-08-08 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-08-08

Updated: 2026-09-28

Comments: 22 pages, 10 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 31× in this paper · explained in 2 episodes
• Grounding — 30× in this paper · explained in 3 episodes
• GRPO — 19× in this paper · explained in 6 episodes
• Hallucination — 14× in this paper · explained in 4 episodes
• Robustness — 10× in this paper · explained in 5 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Vision-language models — 8× in this paper · explained in 2 episodes
• Trace — 7× in this paper · explained in 2 episodes
• AUC — 6× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Multimodal Reasoning — 5× in this paper · explained in 5 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Visual Grounding — 5× in this paper · explained in 2 episodes
• Counterfactual Evidence Disentanglement — 4× in this paper
• Downstream Tasks — 4× in this paper · explained in 2 episodes
• alpha — 4× in this paper · explained in 1 episode
• Vision-Language Models (VLMs) — 3× in this paper · explained in 6 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Hyperparameters — 2× in this paper · explained in 2 episodes
• Reward Hacking — 2× in this paper · explained in 8 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination Detection — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Mutual Information — 1× in this paper · explained in 2 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
• Linking Perception, Confidence and Accuracy in MLLMs
• SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Spotlight on Token Perception for Multimodal Reinforcement Learning
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
• Treble Counterfactual VLMs: A Causal Approach to Hallucination
• PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment
• Self-Rewarding Vision-Language Model via Reasoning Decomposition
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
• Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
• Vision language models are blind: Failing to translate detailed visual features into words
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
• RegionReasoner: Region-Grounded Multi-Round Visual Reasoning
• VGR: Visual Grounded Reasoning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models