arXiv (All)
open access
RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents
Group Relative Policy Optimization (GRPO) avoids a separate critic by estimating advantages from rollout groups. For multi-turn agents, however, trajectory-level supervision provides coarse, noisy credit: terminal rewards do not locate errors and can penalize useful actions alongside mistakes. Group
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
- Selective Successor Eligibility Traces for RLVR#1343575
- Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models#405700
- Right Answer, Wrong Tokens: Tail-Aware Credit Calibration for RLVR#1356112
- World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models#1186637
- Playing social deduction games with reinforcement fine-tuned large language models#1199535
Record · ID 1216724
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