SIPO: Selective-Inference Policy Optimization for Tree-Structured Agentic RL
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/Zenghuang-Fu/SIPO
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
- Agentic Entropy-Balanced Policy Optimization
- Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember
- Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
- TreeRL: LLM Reinforcement Learning with On-Policy Tree Search
- Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Process Reward Informed Tree Rollout for Effective Multi-Turn RL
- CoEvoKG: Co-Evolving Knowledge Graphs with Self-Evolving Search Agents
- TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization
- Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Hindsight Credit Assignment for Long-Horizon LLM Agents
- BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents
- Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
- APPO: Agentic Procedural Policy Optimization
- Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
- Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching
- TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
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