Zichen Wang

M.A. candidate in Economics · IESR, Jinan University

Advised by Shiyu Bo

I study how AI can support credible research, and how scientific knowledge is produced, shared, and recognized. My work brings together social-science measurement, the science of science, and agent systems for knowledge work.

Research interests

Research & ongoing work

01

From AI-generated variables to credible measurement

My interest in measurement grew out of using language models to turn unstructured text into research variables. This led me to a broader question: when a model produces a score or label, what evidence justifies interpreting and using it as a measure?

Assessing the Quality of Personality Measures Generated by Large Language Models

With Shuaizhang Feng , Yujie Han , and James J. Heckman

We examine AI-inferred personality from student letters using multiple human informants and later outcomes. Because self-reports are themselves imperfect, agreement with a single rater is only part of the evidence. I designed the AI scoring pipeline and contributed to validation of what the measures capture and what information they add.

Abstract

We assess the quality of personality measures generated by a large language model from student-written letters. Using data from a pen-pal program in rural China, we compare the resulting AI ratings with student, teacher, and guardian reports for the same children. The AI ratings show high internal consistency and evidence of construct validity. They are modestly related with but distinct from human reports and predict later academic performance and psychological health. Shapley-Owen decompositions show that the AI reports retain an explanatory contribution to both test scores and mental health alongside student, teacher, and guardian reports, offering a low-cost useful personality measurement source in addition to conventional subjective questionnaire reports.

Earlier, as a research assistant with Shiyu Bo , I helped construct measures of hospital purchasing from procurement text. With Zijian Wang , Jieran Wu , and Cynthia Jing Wu , I worked on text-based measures of firms’ monetary-policy attention and financial constraints.

I am interested in extending this measurement perspective to LLM-based evaluation, including judgments of agent behavior and research outputs.

02

How knowledge is produced—and how it gains recognition

I am interested in the conditions that shape scientific progress, and in the relationship between a contribution and the attention it receives. Political shocks, collaboration networks, and new technologies offer different ways to study these questions.

The Effects of China–US Tensions on Science: Evidence from the arXiv Dataset

With Shiyu Bo · Master’s thesis, work in progress

Using linked arXiv and bibliometric data, I study how geopolitical tensions affect scientific production and knowledge diffusion. Preliminary findings show citation declines without corresponding declines in publication quantity or measured text novelty, motivating a distinction between producing knowledge and its subsequent diffusion.

Looking ahead, I want to understand how AI changes research practices and scientific outcomes, and how networks shape the recognition of valuable work. These questions also depend on how we measure scientific contribution and impact.

03

Building agents for knowledge work

Alongside empirical research, I build tools and investigate agent systems for working with scientific literature. This gives me a practical setting for thinking about how knowledge is accessed, retained, and used—and how AI assistance can be evaluated.

Frowang · An agent-native platform for literature research

Independent project · Native Agent Track Champion, EvoMap Hackathon 2026

I designed and built Frowang around a reading workflow: screen papers with structured summaries, inspect the original evidence, and use an assistant for closer reading. Paper APIs, a CLI, and installable skills connect local agents to the same library for retrieval, organization, and cross-paper work.

453 registered users · approximately 100 monthly active users · October 24, 2026

EvoMap · Agent Memory & Agent Swarm

Algorithm Intern · October 2026–present

I work on agent memory systems and investigate swarms for literature discovery and synthesis. The swarm work asks how parallel retrieval and reading can reconstruct a research direction’s development when its literature exceeds one agent’s context, balancing coverage and relevance.

From Simulation to Decision Support: A Benchmark and Decision Assistant Framework for Multi-Agent Social System

Yupu Hao, Zhuoran Jin , Zichen Wang , Jiachun Li, Kejian Zhu, Lingshuai Wang, Kang Liu, and Jun Zhao

Accepted · LASS Workshop at ACM CIKM 2026 · Paper

SocialSim-Bench studies strategic interaction and simulation-based decision support. I contributed to negotiation scenarios and benchmark tasks, translating private goals and economic constraints into settings for evaluating agents’ behavior.

Abstract

Most prior LLM-based social-simulation studies ask whether agents appear realistic, socially intelligent, or behaviorally consistent. However, can LLM agents genuinely reason about evolving social dynamics and develop adaptive strategies, rather than merely role-play? Moreover, social simulations are often intended to provide guidance for real-world decision-making. We study the next step: how simulated possibilities can inform disciplined decision support. We present SocialSim-Bench, a benchmark and decision-assistant report-generation framework for multi-agent decision support, comprising two scenarios: social-media interaction and long-term negotiation. Each scenario combines contextual backgrounds, role-specific profiles, private goals, and action constraints. We evaluate agents using rule-based metrics and an LLM-as-a-judge system, while also analyzing the strategies they employ, finding that even the excellent LLMs only perform simple strategies without applying complex methods. We further investigate multiple approaches for transforming simulation results into decision-assistant reports, including direct LLM generation, harness-based generation with agents such as Codex, and our proposed recursive synthesis approach, which transforms simulation traces into decision-assistant reports by summarizing individual trajectories, aggregating recurring conditions and plausible outcomes, and synthesizing actionable recommendations. We evaluate report quality across multiple dimensions. Our results show that simulation-grounded reporting improves decision-support quality in both social-media and negotiation settings compared with no simulation.