Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning
cs.AI, stat.ML
Submitted: 2026-09-24
Updated: 2026-09-24
Code: https://github.com/xcyao00/GRAFT
Terminology
Sources
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- More Bang for the Buck: Process Reward Modeling with Entropy-Driven Uncertainty
- Process Reinforcement through Implicit Rewards
- Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Soft Adaptive Policy Optimization
- ORPO: Monolithic Preference Optimization without Reference Model
- VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph
- WebSailor: Navigating Super-human Reasoning for Web Agent
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- Proximal Policy Optimization Algorithms
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
- ZeroSearch: Incentivize the Search Capability of LLMs without Searching
- Hindsight Credit Assignment for Long-Horizon LLM Agents
- Kimi K2.5: Visual Agentic Intelligence
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