HINT-SD introduces a targeted self‑distillation framework for long‑horizon language‑model agents that uses full‑trajectory hindsight to identify failure‑relevant actions and applies feedback‑conditioned distillation only to those action spans. This selective approach reduces the need for per‑turn feedback, improving training efficiency and effectiveness. Experiments on BFCL v3 and AppWorld demonstrate that HINT‑SD outperforms dense per‑turn feedback baselines by up to 13.60 percentage points on average while cutting training time per step by 2.26×.
By Woongyeong Yeo, Yumin Choi, Taekyung Ki, Sung Ju Hwang
arXiv:2609.39306v1 Announce Type: cross
Abstract: Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI). Yet our...
By Shengjie Jin, Hengbo Xu, Zelong Sun, YuJie Guo, Zhiwu Lu
arXiv:2606. 15912v1 Announce Type: cross Abstract: Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice.
By Gengsheng Li, Mao Zheng, Mingyang Song, Ruiqi Liu, Tianyu Yang, Jie Sun, Qiyong Zhong, Haiyun Guo, Junfeng Fang, Dan Zhang, Jinqiao Wang
ComputerSD is an online self‑distillation method for computer‑use agents that leverages real‑time feedback from executed GUI transitions. It uses a fine‑tuned GUI analyzer to generate guidance and a step‑level value score after each action, combining token‑level OPSD with trajectory‑level GRPO in an asynchronous training framework. On the OSWorld‑Verified benchmark, ComputerSD improves performance over outcome‑only GRPO by 1.9 and 4.1 percentage points on Qwen3‑VL‑8B‑Thinking and EvoCUA‑8B backbones, and shows strong generalizability in out‑of‑distribution tests.
By Yong Du, Tongbo Chen, Zhengxi Lu, Yizhou Liu, Bofan Chen, Tao Jiang, Wenhao Xu, Yongliang Shen
Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI). Yet our experiments with existing methods reveal a collaps...
AHEAD is a step‑aware framework that augments reinforcement learning for multi‑turn LLM agents by matching different supervision sources to different step types. The teacher receives environment feedback on all steps and LLM‑generated corrective hints only on error steps, providing finer‑grained guidance than uniform trajectory‑level rewards. Across ALFWorld, WebShop, and Search‑based QA, AHEAD improves task success by 13.3 points on ALFWorld and 11.0 on WebShop at 7B, reaches target success rates faster, and solves tasks within tighter interaction budgets compared to outcome‑only RL and prior self‑distillation baselines.
By Xiaolong Jin, Dingmin Wang, Vijay Lingam, Varun Kumar
arXiv:2601. 19897v2 Announce Type: replace Abstract: Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models.
By Idan Shenfeld, Mehul Damani, Jonas H\"ubotter, Pulkit Agrawal
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no sup...
arXiv:2608. 05219v1 Announce Type: new Abstract: Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response at every turn with access to training-only references, such as successful trajectories.
By Junzhuo Liu, Weiwei Li, Jun Ling, Peng Wang
arXiv:2608. 16333v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories.
By Changhui Sun, Lanbo Liu, Hang Lei, Tong Ling, Jiahang Xie, Zhiyong Zheng, Yujia Wang, Hao Liu, Feng Xiao, Lu Liu, Yanlong Du, Zifeng Cheng, Ziwei Jiang, Qing Gu
The paper introduces TISD, a trajectory-intervention self-distillation method that forces a teacher-selected branch action and then lets the student generate the suffix, distilling the full trajectory under a privileged-context-conditioned teacher. This approach addresses a data-collection bottleneck in on‑policy self‑distillation by exposing successor contexts that the student would otherwise miss. Experiments on coding and science domains show modest but consistent improvements in average performance metrics compared to baseline methods.
By Taeckyung Lee, Rinat Amankos, Jeonghye Kim, Hyungjun Yoon, Woogyeol Jin, Sung-Ju Lee
arXiv:2609. 40285v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories.
By Yinghui He, Yapei Chang, Khushi Bhardwaj, Daniele Molinari, Tugrul Konuk, Jan Kautz, Ali Hatamizadeh