11 papers
HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration
Yanchen Deng, Jianguo Huang, Yao Long Teng +6
Orchestrating multiple agents on a complex task requires reconciling local subtask execution with global task planning. Dynamic dispatch approaches provide execution flexibility bu…
Prism-1: Position- and Rival-Independent Scoring for System One Models
Yao Long Teng, Jianguo Huang, Yanchen Deng +2
Given a state and a set of options, such as intents, tools or interface elements, System One decision models return a distribution over the options in one forward pass, without gen…
Consider, Then Choose: Order-Invariant Decisions in System One Models
Jianguo Huang, Yao Long Teng, Yanchen Deng +1
System One models answer typed questions in a single forward pass and promise the same answer for the same input. For choice questions, this promise fails: the answer depends on th…
Hesitation-Aware On-Policy Distillation for Diffusion Language Models
Jianguo Huang, Lipeng Wan, Yanchen Deng +1
Diffusion large language models (dLLMs) generate text by iterative unmasking. At each denoising step, a dLLM proposes a token at every masked position, but the decoder commits only…
Discovering physical mechanisms from experiment-simulation mismatches
Yue Li, Penghui Yang, Yushan Xiao +7
Scientific discovery often begins where observation and prediction disagree. As computation and machine learning survey chemical space, experiment-simulation mismatches are exposed…
HyPAC: Cost-Efficient LLMs-Human Hybrid Annotation with PAC Error Guarantees
Hao Zeng, Huipeng Huang, Xinhao Qu +3
Data annotation often involves multiple sources with different cost-quality trade-offs, such as fast large language models (LLMs), slow reasoning models, and human experts. In this…
Conditional Performance Guarantee for Large Reasoning Models
Jianguo Huang, Hao Zeng, Bingyi Jing +2
Large reasoning models have shown strong performance through extended chain-of-thought reasoning, yet their computational cost remains significant. Probably approximately correct (…
Anytime Safe PAC Efficient Reasoning
Chengyao Yu, Hao Zeng, Youxin Zhu +3
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks but suffer from high computational costs and latency. While selective thinking strategies im…
MATAI: A Generalist Machine Learning Framework for Property Prediction and Inverse Design of Advanced Alloys
Yanchen Deng, Chendong Zhao, Yixuan Li +10
The discovery of advanced metallic alloys is hindered by vast composition spaces, competing property objectives, and real-world constraints on manufacturability. Here we introduce…
On the Provable Performance Guarantee of Efficient Reasoning Models
Hao Zeng, Jianguo Huang, Bingyi Jing +2
Large reasoning models (LRMs) have achieved remarkable progress in complex problem-solving tasks. Despite this success, LRMs typically suffer from high computational costs during d…
Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs
Zhiyi Lyu, Jianguo Huang, Yanchen Deng +2
Large Language Models (LLMs) with inference-time scaling techniques show promise for code generation, yet face notable efficiency and scalability challenges. Construction-based tre…