Learning to Coach for Experiential Learning

arXiv:2609.15851 · cs.CL · Submitted 2026-09-14 · Read on arXiv

cs.CL

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 21 pages, 16 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Actor — 141× in this paper · explained in 3 episodes
• Accuracy — 57× in this paper · explained in 1 episode
• GRPO — 9× in this paper · explained in 6 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Test-time Scaling — 5× in this paper · explained in 2 episodes
• Thinking mode — 3× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Meta-learning — 2× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• TextArena
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
• Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison
• No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning
• LLM Critics Help Catch LLM Bugs
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Cognitive Architectures for Language Agents
• Agent Workflow Memory
• Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and Planning
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• TextGrad: Automatic "Differentiation" via Text
• LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
• Qwen3 Technical Report
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
• Agent Learning via Early Experience
• Instruction-Following Evaluation for Large Language Models
• Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering