arXiv (All)
open access
Bellman-Consistent Trajectory RL for LLM Arithmetic Reasoning
To address sparse terminal rewards in LLM arithmetic reasoning, we propose a Bellman-consistent trajectory RL method. Our framework introduces Trajectory Bellman Residual Minimization (TBRM) to transform sparse rewards into dense token-level signals. We integrate a Reinforce Leave-One-Out (RLOO) gro
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Learning Chance-Constrained MDPs with Bellman Distributional Certificates#1105415
- Adaptive Information Control for Search-Augmented LLM Reasoning#1199742
- Balancing Risk and Reward : A General Architecture for Safe Exploration in Robotic Learning#1066030
- Improving Math Reasoning through Value-guided Informative Search#1156015
- LLM Value Functions for Credit Assignment in Agentic RL#1327090
Record · ID 1356396
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive