Yue Huang黄跃/hwɑːŋ jwɛ/

NARRA-Gym for Evaluating Interactive Narrative Agents

Yue Huang, Yuchen Ma, Jiayi Ye, et al. — Executable environment that grows an emotional seed into a full interactive story episode and scores nine frontier agents on it.

SkillGen: Verified Inference-Time Agent Skill Synthesis

Yuchen Ma*, Yue Huang*, Han Bao, et al. — Synthesizes one auditable skill from an agent's successful and failed trajectories, then verifies it as an intervention by counting the repairs and regressions it causes.

ProbeLLM: Automating Principled Diagnosis of LLM Failures

Yue Huang*, Zhengzhe Jiang*, Yuchen Ma*, et al. — Hierarchical MCTS framework that surfaces structured, recurring failure modes of LLMs.

TrustGen: Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

Yue Huang, Chujie Gao, Siyuan Wu, et al. — Featured by Hoover Institution Technology Policy Accelerator and Notre Dame–IBM Technology Ethics Lab.

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

Yue Huang, Hang Hua, Yujun Zhou, et al. — Toolkit and model for trustworthy agentic systems.

SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization

Yue Huang, Xiangqi Wang, Xiangliang Zhang — Oral. Alignment that puts safety before helpfulness via self-priority optimization.

Synthetic Interaction Data for Scalable Personalization in Large Language Models

Yuchen Ma, Yue Huang, Wenjie Wang, et al. — PersonaGym synthetic interaction data and PPOpt for scalable personalization.

DataGen: Unified Synthetic Dataset Generation via Large Language Models

Yue Huang*, Siyuan Wu*, Chujie Gao, et al. — A unified framework for diverse, accurate, and controllable synthetic dataset generation.

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking

Xiangqi Wang*, Yue Huang*, Yanbo Wang, et al. — Spotlight. Adaptive reasoning that adjusts thinking style to the task.

TrustLLM: Trustworthiness in Large Language Models

Yue Huang, Lichao Sun, Haoran Wang, et al. — Featured by U.S. DHS, NIST, FLI AI Safety Index, and the Springer textbook Introduction to Foundation Models.

ChemOrch: Empowering LLMs with Chemical Intelligence via Groundbreaking Synthetic Instructions

Yue Huang*, Zhengzhe Jiang*, Xiaonan Luo, et al. — Highlighted by NSF Center for Computer-Assisted Synthesis (C-CAS).

HonestLLM: Toward an Honest and Helpful Large Language Model

Chujie Gao*, Siyuan Wu*, Yue Huang*, et al. — Training LLMs toward honesty and helpfulness.

MetaTool Benchmark: Deciding Whether to Use Tools and Which to Use

Yue Huang, Jiawen Shi, Yuan Li, et al.