When Credit Turns Against Tools: Transition-Aware Credit Assignment in Agentic Reinforcement Learning
cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/tmlr-group/TACA
Terminology
Sources
- On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- Group-in-Group Policy Optimization for LLM Agent Training
- RewardFlow: Can Action-Level Reward Be Estimated from State-Graph Topology in Agentic RL?
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
- Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
- Measuring Mathematical Problem Solving With the MATH Dataset
- Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
- Meta-RL Induces Exploration in Language Agents
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization
- TACO: Topics in Algorithmic COde generation dataset
- ToRL: Scaling Tool-Integrated RL
- Understanding R1-Zero-Like Training: A Critical Perspective
- Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- Self-Refine: Iterative Refinement with Self-Feedback
- WebGPT: Browser-assisted question-answering with human feedback
- ToolRL: Reward is All Tool Learning Needs
- Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis