DART‑SD introduces a diamond‑topology aware framework for training large language models to perform multi‑turn tool‑calling. It models the execution process as an Interaction‑State Transition Graph, identifies critical topological breakpoints, and retrieves recovery references to guide localized self‑distillation. Experiments show that this approach outperforms traditional full‑trajectory baselines on complex multi‑turn tool‑calling benchmarks.
arXiv:2606. 24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason.
By Tianyuan Shi, Canbin Huang, Bei Li, Xin Chen, Xiaojun Quan, Jingang Wang, Qifan Wang
arXiv:2512. 07287v3 Announce Type: replace-cross Abstract: As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts.
By Sijia Li, Yuchen Huang, Zifan Liu, Zijian Li, Jingjing fu, Lei Song, Jiang Bian, Jun Zhang, Rui Wang
The paper introduces PACEvolve, a framework that improves self‑evolving agents powered by Large Language Models by addressing their tendency to become trapped in local contexts and repeat flawed hypotheses. It does so through three techniques: Hierarchical Context Management to prune memory, Momentum‑Based Backtracking to escape local minima, and a self‑adaptive Collaborative Evolution policy to balance refinement and knowledge transfer. These methods enable the agents to maintain a global view of search momentum and achieve state‑of‑the‑art results on complex evolutionary benchmarks.
By Minghao Yan, Bo Peng, Benjamin Coleman, Ziqi Chen, Zhouhang Xie, Shuo Chen, Zhankui He, Noveen Sachdeva, Isabella Ye, Weili Wang, Chi Wang, Ed H. Chi, Fernando Pereira, Wang-Cheng Kang, Derek Zhiyuan Cheng, Beidou Wang
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
Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often separate inference-time orchestration from parameter-level learning, leaving tool selection weakly structured and preference updates vulnerable to train--deployment prompt mismatch.
arXiv:2606. 18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution.
By Zhilin Huang, Hang Gao, Ziqiang Dong, Yuan Chen, Yifeng Luo, Chujun Qin, Jingyi Wang, Yang Yang, Guanjun Jiang
Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns.
arXiv:2608. 11967v1 Announce Type: cross Abstract: Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory.
By Zhixin Zhang, Xinke Jiang, Zhibang Yang, Weixuan Xu, Guohong Qiu, Xu Chu, Junfeng Zhao, Yasha Wang
arXiv:2606. 18890v1 Announce Type: new Abstract: Improving GUI agents typically relies on behavior cloning on expert trajectories.
By Zhimin Fan, Hongwei Yu, Yeqing Shen, Haolong Yan, Guozhen Peng, Tianhao Peng, Yudong Zhang, Xiaowen Zhang, Kaijun Tan, Zheng Ge, Xiangyu Zhang, Daxin Jiang
The paper introduces Procedural Graphs, a framework that structures procedural knowledge for large language model agents as (procedure, relation, procedure) triplets, analogous to knowledge graphs for factual data. At each decision point, a guidance model uses the local subgraph to bias the agent’s next action, while an LLM refiner self‑evolves the graph by comparing failed and successful trajectories, editing its topology to improve performance. Experiments across various datasets, tasks, and LLMs show that Procedural Graphs consistently outperform memory‑based baselines, and the self‑evolution mechanism further enhances results without manual engineering.
By Yuxing Lu, Yicheng Chen, Shanchan Wu, Sercan \"{O}. Ar{\i}k
The paper introduces Reverse‑Turn Policy Optimization (RTPO), a method that restructures multi‑turn agentic reinforcement learning rollouts into sparse reverse trees and updates policies in temporal reverse order. This approach addresses three key instability sources—context mismatch, weak turn‑level credit assignment, and asynchronous policy drift—by aligning each decision with its downstream continuation. Theoretical analysis shows RTPO eliminates context mismatch and drift, reduces credit bias, and converges to recursive optimality, while experiments demonstrate performance gains of 21.50% over trajectory‑level and 10.76% over turn‑level baselines on multi‑turn agentic RL benchmarks.
By Yugu Li, Jimmy Cao, Jianglin Qiao, Siyi Hu