[
    {
        "id": "osp-23881",
        "type": "article-journal",
        "title": "Learning to Coach for Experiential Learning",
        "author": [
            {
                "family": "Chen",
                "given": "Guanheng"
            },
            {
                "family": "Ye",
                "given": "Tianzhu"
            },
            {
                "family": "Dong",
                "given": "Li"
            },
            {
                "family": "Wu",
                "given": "Xun"
            },
            {
                "family": "Huang",
                "given": "Shaohan"
            },
            {
                "family": "Wei",
                "given": "Furu"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/learning-to-coach-for-experiential-learning",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Language models can learn from experience, but raw solution trajectories are often too long and noisy to provide effective guidance. In this work, we propose Learning to Coach (L2C), a framework that trains a dedicated LLM-as-a-Coach to extract actionable experiential knowledge from an actor model's previous trajectory. The actor remains frozen, while the LLM-as-a-Coach is trained to maximize a reward given by the correctness of the actor's guided response. We study two such rewards: a same-instance reward, which improves subsequent responses on the original problem, and a cross-instance reward, which elicits knowledge that transfers to other instances. Across mathematical reasoning and interactive text-games, L2C consistently outperforms self-refinement and an untrained LLM-as-a-Coach. Running experiential learning for more iterations further improves accuracy and uses additional inference compute more effectively than enlarging the actor's decoding budget. The trained LLM-as-a-Coach also transfers to out-of-distribution tasks and adapts its guidance to the specific actor it coaches."
    }
]