ARCHIVE · 2026-09 · 113 PAPERS · PAGE 3/3

Papers of 2026-09

Papers first published on arXiv in 2026-09, newest first. To filter by topic, discipline or organisation, use the archive search.

Agents 39Efficient training & inference 24Multimodal 24Benchmarks & data 22Reinforcement learning 18Visual generation 17Robotics & embodied AI 14Reasoning 10AI for Science 10Code & SWE 8LLMs 7Vision & 3D 7Alignment 6Safety & interpretability 4

Top organisations: Zhejiang University (5) · National University of Singapore (5) · Peking University (5) · Carnegie Mellon University (3) · Google (3)

▲33 ★141 ❝4 2026-09-21

From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health

A survey of LLMs in mental health, tracing the evolution from pattern recognisers to personalised companions.

Affiliation unverified · He Hu, Yucheng Zhou, Qianning Wang +8

LLMs AI for Science arXiv Code HF

▲30 ★224 ❝19 2026-09-21

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Jev-Mem uses a fast System 1 control plane to manage agent memory, removing costly generation from the critical path.

Affiliation unverified · Dongming Jiang, Yi Li, Bingzhe Li

Agents Efficient training & inference arXiv Code HF

▲88 ★51 ❝0 2026-09-20

Grounded Action Model: 3D Grounding as a Foundation for Robotics

Proposes Grounded Action Models, robot foundation models built on 3D grounding and promptable with language, points or boxes.

National University of Singapore · Gehao Zhang, Weikai Huang, Shailesh Shailesh +3

Robotics & embodied AI arXiv Code HF

▲50 ★45 ❝0 2026-09-20

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

Trains category-specific SWE experts and then integrates them, easing the see-saw across task categories in pooled RL.

alibaba · Jie Zhao, Ziyu Jiang, Suhang Zheng +3

Code & SWE Reinforcement learning Agents arXiv Code HF

▲240 ★227 ❝0 2026-09-19

OmniEdu: Open Foundation Models for Learning and Teaching

OmniEdu is an open family of K-12 education foundation models covering problem solving, curriculum grounding, diagnosis and tutoring.

Peking University · Hao Liang, Qihan Lin, Meiyi Qiang +5

LLMs arXiv Code HF

▲89 ❝11 2026-09-19

Transferring the Intelligence of VLMs to Robotic Control

RoboDawn exposes robot control as simple discrete commands to an agentic VLM, testing whether digital intelligence transfers to the physical world.

Affiliation unverified · Meng-Hao Guo, Zhe-Han Mo, Jia-Jun Wang +6

Robotics & embodied AI Multimodal arXiv HF

▲64 ★90 ❝0 2026-09-19

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

Spatial-Interactor trains VLM spatial reasoning on observation-action-observation interaction trajectories.

ZJU-OmniAI · Kaixiang Yao, Xu Wang, Miao Pan +10

Multimodal Reasoning arXiv Code HF

▲138 ❝2 2026-09-18

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

CodeMidas turns implemented functionality in codebases into executable coding RL environments using only source code.

Xiaomi MiMo · Bowen Ye, Lei Li, Shicheng Li +16

Code & SWE Reinforcement learning Agents arXiv HF

▲82 ★216 ❝0 2026-09-18

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Defines native audio-visual dialogue for omni models and provides synthetic data, a benchmark and training recipes.

Qwen · Haolin He, Yunfei Chu, Qi Chen +15

Multimodal Benchmarks & data arXiv Code HF

▲81 ★108 ❝1 2026-09-18

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

RecreationWorld asks computer-use agents to observe running software and re-implement it, with verifiable environments on five platforms.

Qwen · Shuai Bai, Jiayong Deng, Sicheng Fan +30

Agents Code & SWE Benchmarks & data arXiv Code HF

▲57 ★19 ❝0 2026-09-16

RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation

RayOrch is a distributed dataflow engine for foundation-model data prep that preserves lineage while batching efficiently.

Peking University · Xiaochen Ma, Zimo Meng, Junzhu Liang +13

Efficient training & inference arXiv Code HF

▲152 ★994 ❝3 2026-09-14

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

EvoOntology provides data agents with a self-evolving ontology layer served over MCP to bridge the gap to heterogeneous data.

RUC-DataLab · Meiduo Chong, Shaolei Zhang, Ju Fan +1

Agents arXiv Code HF

▲184 ★200 ❝6 2026-09-12

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Realtime-Venus is a full-duplex audio-visual interaction system that listens, watches and talks while delegating tasks asynchronously.

inclusionAI · Ant Group

Multimodal Agents arXiv Code HF