← Back to all news
arXiv Machine Learning By Shangyang Wu, Shuai Zhao, Ziyue Zhu, Jinyang Wu, Anh Tuan Luu, Haoran Luo

SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents

Read the original on arXiv Machine Learning →

SCAD (Structured Credit Assignment and Distillation) is a new method for training long‑horizon agents that separates planning from bounded subtask execution, distills execution locally, and refines planning credit using cross‑rollout subtask prefix trees. It gives planning full terminal credit while providing execution with positive terminal credit and teacher guidance. On all tested benchmarks, SCAD improves macro‑average accuracy by 4.48 percentage points on text tasks and 4.19 points on multimodal tasks compared to the strongest baseline.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 9

PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment

arXiv:2606. 09348v1 Announce Type: new Abstract: Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide limited guidance on which intermediate reasoning steps or tool interactions contribute to the outcome.

By Yang Tian, Rui Wang, Xumeng Wen, Junjie Li, Shizhao Sun, Lei Song, Jiang Bian, Bo Zhao
agentsreinforcement-learningefficiency
More like this →
arXiv AI
Sep 3

APEx: Distillation of Agent Procedural Experience for Adaptive Deep Research Question Answering

APEx is a hierarchical framework that organizes a deep research agent’s interaction history into instance-level trajectory memories and category-level procedural skills. It couples these through an Executor, Distiller, and Planner, trained with a three-stage alternating GRPO paradigm to enable reward-guided skill distillation. At test time, distilled skills act as procedural priors for online Planner adaptation via skill-guided reinforcement learning, achieving state‑of‑the‑art results on seven benchmarks, outperforming GPT‑5.4 by 14.7 points and the best memory‑augmented baseline by 3.0 points.

By Jie Ding, Rui Sun, Xinyuan Zhang, Zeyu Zhang, Xin Liu
llmsagentsnlpreinforcement-learningefficiencybenchmarkssafety
More like this →
arXiv AI
Jun 10

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

arXiv:2606. 10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks.

By Juncheng Diao, Zhicong Lu, Peiguang Li, Yongwei Zhou, Changyuan Tian, Qingbin Li, Rongxiang Weng, Jingang Wang, Xunliang Cai
llmsagentsnlpreinforcement-learningbenchmarks
More like this →