Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models
cs.AI
Submitted: 2026-09-03
Updated: 2026-09-03
Terminology
Sources
- Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization
- Qwen3-VL Technical Report
- SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward
- Training Multi-Image Vision Agents via End2End Reinforcement Learning
- WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent
- DeepEyesV2: Toward Agentic Multimodal Model
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- WebThinker: Empowering Large Reasoning Models with Deep Research Capability
- Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning
- Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning
- Visual Agentic Reinforcement Fine-Tuning
- Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
- ToolRL: Reward is All Tool Learning Needs
- V-Thinker: Interactive Thinking with Images
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
- R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection