Tag
This paper investigates whether natural-language feedback leads to improvement beyond repeated attempts alone in multi-turn language agent settings. Using a controlled student-teacher protocol across multiple benchmarks, the authors find that self-generated feedback adds little, while strong external teachers yield larger gains, and that the student's ability to act on feedback is a key bottleneck.
ScholarSum is a hierarchical reflective graph-based framework for scientific abstractive summarization that emulates a student–teacher writing process. It uses a hierarchical knowledge graph to capture global structure, generates an initial draft, and iteratively refines it via evidence retrieval and teacher-like review to improve both fluency and factual faithfulness.
MIT introduces Pedagogical RL, a method that trains a teacher to produce trajectories that are learnable for a student by penalizing surprising steps, improving RL training efficiency.
Describes a training technique involving spike-aware pedagogy rewards that penalize implausible jumps, and surprisal-gated imitation where the student learns easy tokens quickly and hard ones slowly.