arXiv (All)
open access
HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL
Rubric-based reinforcement learning (RL) trains policies for open-ended generation with natural-language criteria as rewards, but these rewards can become ineffective as training progresses. We identify two failure modes. Under non-discriminative rewards, scores collapse to uniformly low or high val
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
- CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents#1117955
- Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework#216847
- HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning#1083243
- Efficient Bayes-Adaptive Reinforcement Learning with Temporal Logic Specifications#1050940
- Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction#1354565
Record · ID 1401594
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