arxiv
PublishedJuly 21, 2026 at 4:00 AM
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
Publisher summary· verbatim
arXiv:2607.18110v1 Announce Type: cross Abstract: Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with distinct quality profiles. We propose Experiential Learning (EL), which r
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivCapacity and Redundancy Trade-offs in Multi-Task Learning6harxivPredictive Training with Latent Imagination for Visual Quadruped Navigation6harxivWhere Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making6harxivDid We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection6hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗