ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair
cs.AI, cs.CL, cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- DeepSeek-V3 Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models
- RewardBench: Evaluating Reward Models for Language Modeling
- ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
- Structured Feedback Improves Repair in an LLM Agent Loop
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration
- ProcessBench: Identifying Process Errors in Mathematical Reasoning
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