works on
credit distillation 1LLM summarization 1long-horizon reinforcement learning 1policy gradient 1tool-use agents 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents

Tianyu Ding, Jianhong Xin, Juan Pablo De la Cruz Weinstein

The paper introduces Sibling-Guided Credit Distillation (SGCD), a technique that uses self‑distillation to assign finer‑grained credit to actions in long‑horizon tool‑use reinforce…