Research archive
Publications.
Selected work spanning agent systems, large language models, multimodal intelligence, search, and recommender systems.
17 selected papers
01
χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
Agents
NeurIPS E&D2026
↗02BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces
Agents
NeurIPS E&D2026
↗03Test-Time Adaptation for LLM Agents via Environment Interaction
Agents
ICLR2026
↗04WebScale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
Agents
ICLR2026
↗05UserBench: An Interactive Gym Environment for User-Centric Agents
Agents
EMNLP2026
↗06UserRL: A Gym-Based Testbed for User-Centric Reinforcement Learning
Agents
EMNLP2026
↗07MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models
Agents
arXiv2025
↗08LATTE: Learning to Think with Vision Specialists
Multimodal
EMNLP2025
↗09PRACT: Optimizing Principled Reasoning and Acting of LLM Agent
Agents
CoNLL2024
↗10xLAM: A Family of Large Action Models to Empower AI Agent Systems
Agents
arXiv2024
↗11AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System
Agents
arXiv2024
↗12BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
Agents
ICLR LLMAgent2024
↗13Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
Agents
ICLR2024
↗14DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
Language
arXiv2023
↗15Contrastive Self-supervised Sequential Recommendation with Robust Augmentation
Recommendation
Sequential recommendation2021
↗16Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer
Recommendation
CIKM2021
↗17Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer
Recommendation
SIGIR2021
↗Looking for the complete citation record?
View Google Scholar ↗