Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits
cs.AI
Submitted: 2026-10-09
Updated: 2026-10-12
Code: https://github.com/Alibaba-NLP/qqr
Terminology
Sources
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- ARE: Scaling Up Agent Environments and Evaluations
- From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Simulating Environments with Reasoning Models for Agent Training
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ZeroSearch: Incentivize the Search Capability of LLMs without Searching
- Kimi K2: Open Agentic Intelligence
- A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
- TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
- Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
- Group Sequence Policy Optimization
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