arXiv (All)
open access
Learning from All-Failed Groups via First-Visit Coverage in Long-Horizon Agentic Tasks
Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group. However, on difficult long-horizon agentic tasks, we found this comparison suffers from a sampling imbalance: repeated
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
- LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models#1011175
- Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities#1048566
- GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents#1129686
- Language-model groups overstate consensus when replaying human deliberation on a reasoning task#1034357
- Language-model groups overstate consensus when replaying human deliberation on a reasoning task#978469
Record · ID 1296462
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