Tool Verification for Test-Time Reinforcement Learning
cs.AI, cs.CL
Submitted: 2026-03-02
Updated: 2026-08-26
Comments: 12 pages, 11 figures; Code: https://github.com/mayhugotong/T3RL
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Test-Time Training on Nearest Neighbors for Large Language Models
- Measuring Mathematical Problem Solving With the MATH Dataset
- Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
- T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
- The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
- The pitfalls of next-token prediction
- Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning
- Training Verifiers to Solve Math Word Problems
- Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
- The Llama 3 Herd of Models
- Learning to (Learn at Test Time): RNNs with Expressive Hidden States
- Qwen3 Technical Report
- Solving math word problems with process- and outcome-based feedback
- Trust but Verify! A Survey on Verification Design for Test-time Scaling
- Self-Consistency Preference Optimization
- Reinforcement Learning for Reasoning in Large Language Models with One Training Example
- Learning to Discover at Test Time
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
- Agents' Last Exam
- 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