PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Project page: https://research.nvidia.com/labs/lpr/pivotopd
Sources
- AgentBench: Evaluating LLMs as Agents
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
- TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
- SOD: Step-wise On-policy Distillation for Small Language Model Agents
- StepOPSD: Step-Aware Online Preference Self-Distillation for Agent Reinforcement Learning
- Qwen3 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Group-in-Group Policy Optimization for LLM Agent Training
- PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
- OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
- Privileged Information Distillation for Language Models
- Proximal Policy Optimization Algorithms
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Self-Distilled RLVR
- Self-Distilled Agentic Reinforcement Learning
- AgentOPSD: Recursive Self-Distillation for Agentic 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
- 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