RewardFlow: Can Action-Level Reward Be Estimated from State-Graph Topology in Agentic RL?
cs.AI, cs.CL, cs.LG
Submitted: 2026-03-19
Updated: 2026-11-12
Code: https://github.com/tmlr-group/RewardFlow
Terminology
Sources
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
- Process Reinforcement through Implicit Rewards
- MolGAN: An implicit generative model for small molecular graphs
- TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
- Agentic Reinforced Policy Optimization
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
- Reinforcement Learning via Self-Distillation
- VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
- ToRL: Scaling Tool-Integrated RL
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
- Agentic Reinforcement Learning with Implicit Step Rewards
- Understanding R1-Zero-Like Training: A Critical Perspective
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents