Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
cs.LG, cs.CL
Submitted: 2026-05-27
Updated: 2026-11-07
Terminology
Sources
- Execution-Grounded Credit Assignment for GRPO in Code Generation
- Learning to Configure Agentic AI Systems
- Agent-as-Tool: A Study on the Hierarchical Decision Making with Reinforcement Learning
- Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
- ToRL: Scaling Tool-Integrated RL
- Proximal Policy Optimization Algorithms
- VinePPO: Refining Credit Assignment in RL Training of LLMs
- Training Verifiers to Solve Math Word Problems
- ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
- R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
- Secrets of RLHF in Large Language Models Part I: PPO
- OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained 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