60 citations · 153 across the 23 of their papers we have counts for
11 papers · 1 filter
VETTA: Coordinating Turn- and Token-Level Credit Assignment for Multi-Turn LLM Agents
Jiaju Chen, Min Yang, Jinghua Piao +4
Multi-turn LLM agents often receive sparse task feedback across several interactions, while generating each response token by token. This creates two related credit-assignment ques…
EnterpriseBench: Benchmarking LLM Agents on Enterprise-Level Strategic Reasoning and Decision-Making
Min Yang, Yichen Pan, Jinghua Piao +3
LLM agents are increasingly expected to support enterprise workflows, where tasks often involve missing information, uncertainty, feedback, and long-term trade-offs. However, exist…
CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models
Jingquan Chen, Jie Feng, Jinghua Piao +2
Large language models (LLMs) are increasingly used for program-aided reasoning, agentic decision making, and structured task execution, but these settings often incur substantial i…
From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents
Xu Xia, Jinghua Piao, Min Yang +3
Recent work on LLM agents is shifting from external capability elicitation to capability internalization, enabling agents to retain useful skills without retrieval at inference tim…
AgentSociety 2: An Integrated Research Environment for Executable Social Science
Jinghua Piao, Jun Zhang, Haoyu Huang +16
AI scientist systems are beginning to automate parts of scientific research, but social science poses a distinct challenge: its objects of inquiry are not merely datasets or labora…
DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling
Tengyao Tu, Yulin Li, Hui-Ling Zhen +6
Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from…
SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
Min Yang, Jinghua Piao, Xu Xia +4
Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed…
Multi-LLM Systems Exhibit Robust Semantic Collapse
Weiyi Kong, Shiyang Lai, Jinghua Piao +1
Whether machines can originate novel content has been debated for nearly two centuries, from Lovelace's assertion that no engine can "originate anything" to Turing's question of wh…
AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments
Jiaju Chen, Jinghua Piao, Xia Xu +4
A long-standing challenge in economics lies not in the lack of intuition, but in the difficulty of translating intuitive insights into verifiable research. To address this challeng…
Paper2Data: Large-Scale LLM Extraction and Metadata Structuring of Global Urban Data from Scientific Literature
Runwen You, Tong Xia, Jingzhi Wang +5
Urban data support a wide range of applications across multiple disciplines. However, at the global scale, there is no unified platform for urban data discovery. As a result, resea…
PaperRepro: Automated Computational Reproducibility Assessment for Social Science Papers
Linhao Zhang, Tong Xia, Jinghua Piao +2
Computational reproducibility is essential for the credibility of scientific findings, particularly in the social sciences, where findings often inform real-world decisions. Manual…