arXiv Machine Learning

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

arXiv:2608. 09819v1 Announce Type: new Abstract: Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment.

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

arXiv AI

Sep 15

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

ZGCM-1 is a 7B dense foundation model trained from scratch with extreme data, system, and algorithmic efficiency. It uses a core premise that compact models can overcome capacity limits by combining deliberate internal thinking with active external tool use, supported by a 256K context and an end‑to‑end high‑efficiency training recipe that includes interleaved gated sliding‑window and full attention, a stable FP8 Muon optimizer, progressive curriculum scaling, and reformulation of interaction traces into Markov Decision Processes. The model is competitive with much larger frontier models on challenging mathematical reasoning and agentic search tasks, offers a ~4.2× efficiency improvement in pre‑training time‑to‑loss, and its weights, checkpoints, training code, data recipes, and logs are fully open‑source to support community research.

By Jiyan He, Guang Liang, Hao Liu, Haoxiang Guan, Jinbo Sun, Junyi Guo, Wenjun Feng, Yantai Xie, Yifei Shen, Bin Shao, Chuyang Wei, Kai Chen, Kexin Zhou, Minghang Zhu, Shuxin Zheng, Tie-Yan Liu, Taine Zhao, Wenhui Zhu, Xueyin Xu, Xiaoqing Zhang, Yatao Li, Yuxuan Ren

agents reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jul 23

Fara-1.5: Scalable Learning Environments for Computer Use Agents

arXiv:2606. 20785v2 Announce Type: replace Abstract: Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies.

By Ahmed Awadallah, Sahil Gupta, Yash Lara, Yadong Lu, Hussein Mozannar, Akshay Nambi, Zach Nussbaum, Yash Pandya, Aravind Rajeswaran, Corby Rosset, Alexey Taymanov, Luiz do Valle, Vibhav Vineet, Spencer Whitehead, Andrew Zhao

llms agents fine-tuning benchmarks data-engineering

arXiv AI

Jul 28

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

arXiv:2607. 23124v1 Announce Type: new Abstract: Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings.

By Hao Jiang, Gangtao Xin, Yingdi Huang, Guojie Zhu, Jiangshan Zhang, Xinyuan Lin, Yunkun Xu, Chengyu Shen, Wenlong Fei, Jiawei Li, Yujie Fu, Sichen Kang, Tingyu Xie, Yedi Hu, Jingren Zhang, Hongcheng Gao, Jianshu Zeng, Chong Chen, Chang Guo, Chao Feng, Feng Wang, Fulin Lin, Jinchao Ma, Lang Mei, Li Huang, Liyan Liu, Qing He, Shuting Tao, Siyu Mo, Xiangnan Chen, Xiaohan Yu, Xiaoyang Li, Yanheng Hou, Yanyu Wu, Zhihan Yang, Wentao Zhang, Yang Gao, Zhao Cao

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 7

OpenTinker: Separating Concerns in Agentic Reinforcement Learning

arXiv:2601. 07376v2 Announce Type: replace Abstract: We introduce \textsc{OpenTinker}, an open infrastructure for training large language model (LLM) agents with many LoRA-backed policies over shared execution resources.

By Siqi Zhu, Jiaxuan You

llms agents reinforcement-learning fine-tuning

arXiv AI

Jul 24

OpenForgeRL: Train Harness-native Agents in Any Environment

arXiv:2607. 21557v1 Announce Type: new Abstract: Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems.

By Xiao Yu, Baolin Peng, Ruize Xu, Hao Zou, Qianhui Wu, Hao Cheng, Wenlin Yao, Nikhil Singh, Zhou Yu, Jianfeng Gao

llms agents reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Aug 20

Flama: a Python framework for development and deployment of production-ready APIs, machine learning, and LLM services

Flama is an open‑source Python framework that unifies the development and deployment of production‑ready web APIs, machine‑learning services, and large‑language‑model (LLM) applications. Built on ASGI, it offers an async‑first, type‑driven programming model with seven subsystems—including dependency injection, a pluggable schema layer, automatic CRUD generation, a portable binary model format, a multi‑backend LLM server, a Rust‑accelerated core, and a Model Context Protocol module. The framework also provides built‑in JWT authentication, pagination, background tasks, WebSocket and streaming support, OpenAPI generation, and a CLI for running, packaging, and inspecting models.

By Jos\'e A. Perdiguero L\'opez, Miguel A. Dur\'an-Olivencia

llms agents

arXiv Machine Learning

Aug 27

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

JIT‑Agent is a model that automatically generates task‑adaptive agent harnesses for any off‑the‑shelf LLM, replacing manual, task‑specific harness design. It learns to compose, repair, and evolve harnesses using a fixed four‑module protocol, and its use boosts performance on benchmarks such as DeepSearchQA and OdysseyBench, outperforming several mature agent runtimes. The approach demonstrates that harness intelligence can be trained, transferred, and compounded independently of model scaling.

By Guibin Zhang, Leo Lu, Fangzhou Xie, Kang Zhu, Junhao Wang, Zhifei Xie, Zhaochen Yu, Zihang Liu, Zhongxiang Sun, Qiankun Li, Yue Liao, Heng Chang, Xiaobin Hu, Qibing Ren, Wangchunshu Zhou, Shuicheng Yan

llms agents

arXiv AI

Jun 9

From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spatial NPUs

arXiv:2606. 07586v1 Announce Type: cross Abstract: Spatial neural processing units (NPUs) provide an energy-efficient platform for edge LLM inference, but efficiently deploying an LLM end-to-end on such hardware remains labor-intensive.

By Jiajie Li, Erwei Wang, Zhiru Zhang, Samuel Bayliss

llms agents

arXiv AI

Jul 28

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model

arXiv:2607. 22083v2 Announce Type: replace Abstract: We present Nanbeige4.

By Nanbeige Lab, :, Chen Yang, Chengrui Huang, Fufeng Lan, Hanhui Chen, Hao Zhou, Huatong Song, Jiaqi Cao, Jiaying Zhu, Jinlin Niu, Kai Wang, Lisheng Huang, Qiliang Liang, Ran Le, Ruixiang Feng, Shuang Sun, Tao Gu, Tao Zhang, Tianyu Luo, Yang Song, Yun Xing, Yuntao Wen, Ziyao Xu, Zongchao Chen, Zongqiang Li

llms rag agents reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Sep 10

ACE: Adapter Consolidation across Experts for Parameter-Efficient Fine-Tuning of MoE LLMs

arXiv:2609.06072v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) of mixture-of-experts (MoE) models commonly attaches a separate low-rank adapter to each expert. This expert-w...

By Ahin Lee, Sehyun Yun, Joonha Park, Taesik Gong

llms fine-tuning

arXiv AI

Jul 29

A Control System, a Dataset, and a Recipe for Making Frozen LLM Agents Learn a Domain

arXiv:2607. 25415v1 Announce Type: new Abstract: Production LLM agents are increasingly assembled from a frozen model wrapped in a harness: a prompt template, a tool set, a memory/retrieval layer, a planning strategy, and a verification policy.

By Debjyoti Paul

llms agents reinforcement-learning benchmarks

Related stories