19 papers
SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes
Kuan Li, Shuo Zhang, Huacan Wang +12
Smart homes are evolving toward complex state-dependent living environments, requiring Large Language Models (LLMs) to reason over user intent, preferences, and multi-device intera…
HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation
Yi Gu, Huacan Wang, Shuo Zhang +10
Large language model agents are moving beyond text-only interaction toward physical-world control, with smart homes as a representative domain. Real domestic interaction requires u…
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…
SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
Ningyan Zhu, Huacan Wang, Jie Zhou +8
The rise of OpenClaw in early 2026 marks the moment when millions of users began deploying personal AI agents into their daily lives, delegating tasks ranging from travel planning…
Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure
Huacan Wang, Jie Zhou, Ningyan Zhu +8
AI coding agents have become central to developer workflows, yet every existing solution locks its reasoning capabilities within a specific delivery form, such as a CLI, IDE plugin…
EpochX: Building the Infrastructure for an Emergent Agent Civilization
Huacan Wang, Chaofa Yuan, Xialie Zhuang +15
General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to organize production and coordination. We believe AI agents are approa…
Story2Proposal: A Scaffold for Structured Scientific Paper Writing
Zhuoyang Qian, Wei Shi, Xu Lin +19
Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing la…
Chain of Mindset: Reasoning with Adaptive Cognitive Modes
Tianyi Jiang, Arctanx An, Hengyi Feng +12
Human problem-solving is never the repetition of a single mindset, by which we mean a distinct mode of cognitive processing. When tackling a specific task, we do not rely on a sing…
Controlled Self-Evolution for Algorithmic Code Optimization
Tu Hu, Ronghao Chen, Shuo Zhang +9
Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discove…
Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
Zhenxiong Yu, Zhi Yang, Zhiheng Jin +19
As large language models (LLMs) evolve into autonomous agents, their real-world applicability has expanded significantly, accompanied by new security challenges. Most existing agen…
EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines
Shuo Zhang, Chaofa Yuan, Ryan Guo +11
While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work…
QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining
Jun Han, Shuo Zhang, Wei Li +14
Financial markets are noisy and non-stationary, making alpha mining highly sensitive to backtest noise and regime shifts. While recent agentic frameworks improve automation, they o…
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
Qihao Wang, Ziming Cheng, Shuo Zhang +12
While autonomous software engineering (SWE) agents are reshaping programming paradigms, they currently suffer from a "closed-world" limitation: they attempt to fix bugs from scratc…
FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments
Zhi Yang, Runguo Li, Qiqi Qiang +15
Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to…
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
Chengwen Liu, Xiaomin Yu, Zhuoyue Chang +15
In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore ne…
KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions
Tingyu Wu, Zhisheng Chen, Ziyan Weng +8
Existing long-horizon memory benchmarks mostly use multi-turn dialogues or synthetic user histories, which makes retrieval performance an imperfect proxy for person understanding.…
REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model
Bo Li, Guanzhi Deng, Ronghao Chen +5
Understanding how Large Language Models (LLMs) perform complex reasoning and their failure mechanisms is a challenge in interpretability research. To provide a measurable geometric…
GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
Ziyi Ni, Huacan Wang, Shuo Zhang +15
Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evalua…
RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
Huacan Wang, Ziyi Ni, Shuo Zhang +11
The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks t…