18 citations · 75 across the 40 of their papers we have counts for
41 papers
Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use
Zixiang Chen, Wenting Zhao, Zhepeng Cen +9
Multi-turn tool-use failures can hinge on a single model call, yet reward variation alone does not reveal which call would benefit from training. When rewards depend on later inter…
HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit
Zhihao Guo, Zonghan Wu, Huan Huo +6
Internal-state probes enable truthfulness prediction before a large language model generates an answer. When detectors change both the layers they read and the rules used to combin…
BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces
Liangwei Yang, Jielin Qiu, Zixiang Chen +9
Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited. Existing benchmarks for user understanding often…
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
Haolin Chen, Deon Metelski, Leon Qi +30
End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large l…
Towards Scalable Lightweight GUI Agents via Multi-role Orchestration
Ziwei Wang, Junjie Zheng, Leyang Yang +7
Autonomous Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) enable digital automation on end-user devices. While scaling both parameters an…
Whisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training
Jielin Qiu, Ming Zhu, Wenting Zhao +11
Audio-native large language models (audio-LLMs) commonly use Whisper as their audio encoder. However, Whisper was trained exclusively on speech data, producing weak representations…
Enterprise Sales Copilot: Enabling Real-Time AI Support with Automatic Information Retrieval in Live Sales Calls
Jielin Qiu, Liangwei Yang, Ming Zhu +11
During live sales calls, customers frequently ask detailed product questions that require representatives to manually search internal databases and CRM systems. This process typica…
Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial
Jielin Qiu, Zixiang Chen, Liangwei Yang +11
We present a technical tutorial for building enterprise-grade realtime voice agents from first principles. While end-to-end speech-to-speech models may ultimately provide the best…
Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models
Liangwei Yang, Shiyu Wang, Haolin Chen +12
As large language models (LLMs) transition from research prototypes to real-world systems, customization has emerged as a central bottleneck. While text prompts can already customi…
DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths
Hanqing Yang, Hyungwoo Lee, Yuhang Yao +4
The increasingly popular agentic AI paradigm promises to harness the power of multiple, general-purpose large language model (LLM) agents to collaboratively complete complex tasks.…
LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
Jielin Qiu, Zuxin Liu, Zhiwei Liu +18
As large language models (LLMs) evolve into sophisticated autonomous agents capable of complex software development tasks, evaluating their real-world capabilities becomes critical…
GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs
Liangwei Yang, Jing Ma, Jianguo Zhang +11
Graph neural networks (GNNs) on text--attributed graphs (TAGs) typically encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear nei…
Test-Time Adaptation for LLM Agents via Environment Interaction
Arthur Chen, Zuxin Liu, Jianguo Zhang +6
Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets of functions, due to a fundamental mismatch be…
xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
Cheng Qian, Zuxin Liu, Shirley Kokane +10
Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle…
ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning
Murong Yue, Zhiwei Liu, Liangwei Yang +8
Large Language Models (LLMs) equipped with external tools have demonstrated enhanced performance on complex reasoning tasks. The widespread adoption of this tool-augmented reasonin…
Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
Zhepeng Cen, Haolin Chen, Shiyu Wang +8
Large Language Models (LLMs) have achieved remarkable success through imitation learning on vast text corpora, but this paradigm creates a training-generation gap and limits robust…
UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Cheng Qian, Zuxin Liu, Akshara Prabhakar +10
Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value o…
LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering
Jielin Qiu, Zuxin Liu, Zhiwei Liu +14
The emergence of long-context language models with context windows extending to millions of tokens has created new opportunities for sophisticated code understanding and software d…
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models
Zhiwei Liu, Jielin Qiu, Shiyu Wang +9
The rapid rise of Large Language Models (LLMs)-based intelligent agents underscores the need for robust, scalable evaluation frameworks. Existing methods rely on static benchmarks…
UserBench: An Interactive Gym Environment for User-Centric Agents
Cheng Qian, Zuxin Liu, Akshara Prabhakar +9
Large Language Models (LLMs)-based agents have made impressive progress in reasoning and tool use, enabling them to solve complex tasks. However, their ability to proactively colla…
APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
Akshara Prabhakar, Zuxin Liu, Ming Zhu +12
Training effective AI agents for multi-turn interactions requires high-quality data that captures realistic human-agent dynamics, yet such data is scarce and expensive to collect m…
ActionStudio: A Lightweight Framework for Data and Training of Large Action Models
Jianguo Zhang, Thai Hoang, Ming Zhu +13
Large Action models are essential for enabling autonomous agents to perform complex tasks. However, training such models remains challenging due to the diversity of agent environme…
PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data
Juntao Tan, Liangwei Yang, Zuxin Liu +11
Personalization is critical in AI assistants, particularly in the context of private AI models that work with individual users. A key scenario in this domain involves enabling AI m…
LATTE: Learning to Think with Vision Specialists
Zixian Ma, Jianguo Zhang, Zhiwei Liu +9
While open-source vision-language models perform well on simple question-answering, they still struggle with complex questions that require both perceptual and reasoning capabiliti…