arXiv Machine Learning August 12, 2026 By Yuhang Yao, Zeyu Wang, Wanyi Chen, Tongyun Yang, Yuhang Han, Jie Xiao, Chengke Bao, Tianyi Zhao, Lynn Ai, Eric Yang, Tianyu Shi

MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale

Read the original on arXiv Machine Learning →

arXiv:2608. 10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 22

One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context

arXiv:2607. 18293v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) teaches large language models new skills through a teacher that shares the student's backbone and supervises its own rollouts.

By Yingzi Ma, Zichen Zhu, Ming Jiang, Chaowei Xiao

llms agents fine-tuning efficiency benchmarks

arXiv AI

Jun 2

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

arXiv:2606. 01311v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks.

By Zhuoyun Yu, Xin Xie, Wuguannan Yao, Chenxi Wang, Lei Liang, Xiang Qi, Shumin Deng

llms agents

arXiv AI

Jul 7

MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution

arXiv:2607. 05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability.

By Zefeng Wang, Minxi Yan, Jinhe Bi, Sikuan Yan, Volker Tresp, Yunpu Ma

llms agents benchmarks

arXiv AI

Jul 7

TREK: Distill to Explore, Reinforce to Refine

arXiv:2607. 05339v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution modes lie outside the student's on-policy support.

By Yuanda Xu, Zhengze Zhou, Kayhan Behdin, Jelena Markovic-Voronov, Hejian Sang, Xiaomin Li, Wenhui Zhu, Xinchen Du, Aida Rahmattalabi, Ran He, Sen Na, Zhipeng Wang, Alborz Geramifard

agents efficiency

arXiv AI

Jun 2

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

arXiv:2606. 01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) and open-ended planning/reasoning steps (long, complex, high perplexity).

By Prateek Kumar Sikdar

llms agents fine-tuning

arXiv Machine Learning

Jul 13

Mach-Mind-4-Flash Technical Report

arXiv:2607. 09375v1 Announce Type: new Abstract: We present Mach-Mind-4-Flash, a 35B-parameter Mixture-of-Experts (MoE) agentic model with 3B activated parameters.

By Foundation Model Team

agents reinforcement-learning efficiency

Related stories

One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution

TREK: Distill to Explore, Reinforce to Refine

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

Mach-Mind-4-Flash Technical Report