RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training
cs.AI
Submitted: 2026-08-19
Updated: 2026-08-31
Terminology
Sources
- TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL
- xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
- SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees
- WebSailor: Navigating Super-human Reasoning for Web Agent
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
- Decoupled Weight Decay Regularization
- Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
- GAIA: a benchmark for General AI Assistants
- Humanity's Last Exam
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
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