Axioms and representation
We study which assumptions allow preferences to admit a utility representation, and which additional conditions a characterization requires.
Expected uncertain utility →Research profile
Shuo Li Liu
Research programme coordinator · AgentNorm
Shuo Li Liu coordinates the research programme within AgentNorm, where he works on mathematical decision theory and its applications. He is a PhD student in Economics at Princeton University. His papers use axioms, representation theorems, proofs, and counterexamples to study decision making under uncertainty, judgment aggregation, and the evaluation of agentic risk.
AgentNorm is the public research identity of NORMATIVE AI INSTITUTE INC., a British Columbia corporation (company no. 1449218). This page describes Shuo’s role within this independent research initiative; his university affiliation is PhD student in Economics at Princeton University.
The selected work includes a corrected representation theorem in Econometrica, sufficient conditions for convexity in Economic Theory Bulletin, and counterexamples concerning regret and dominance. It also includes four peer-reviewed ICML 2026 workshop posters and a letter in Science.
Research programme
At AgentNorm, Shuo coordinates a small independent research programme. The work includes theoretical papers on utility representations, convexity under ambiguity, and regret, alongside research software and studies of collective judgment and evidence for AI systems.
At AgentNorm, Shuo coordinates open research and works with student collaborators. The initiative shares mathematical arguments, evidence, and research resources so that others can examine and build on them.
We start with explicit definitions and assumptions, prove what follows, and then give counterexamples that push a claim to its limits. In the applied work, we make a clear distinction between mathematically guaranteed results and computational evidence.
Convexity, ambiguity, and regret
We study the structure of preferences under uncertainty, and provide sufficient conditions and counterexamples for the analysis of diversification, transitivity, and regret.
Convexity under ambiguity →Decision theory for agentic risk
We apply decision theory and mathematical analysis to questions about dominance, judgment aggregation, verification, and the limits of deployment claims.
Savage Without Monotonicity →Corrigibility, risk measurement, and assurance
We study how corrigibility, oversight, and measurement can support cautious assessment of risks in agentic systems, distinguishing formal guarantees from empirical evidence.
Behavior-only deployment certification →Academic service and conference roles
Program Committee Member
AAAI-27 Special Track on AI Alignment
2026–2027
Serving on the program committee for the AI Alignment special track of the 41st AAAI Conference on Artificial Intelligence.
Official track information →Program Chair
Cellular agriculture conference
Program Chair role for a cellular agriculture conference; the event name and year are not specified in the available record.
Selected papers
Mathematical papers lead this selection, followed by applications to decision theory for agentic risk, corrigibility, and AI risk measurement. Each entry identifies its publication type and links to a source.
- 2024
A Comment on: “Expected Uncertain Utility”
Econometrica 92(1):247–256
Journal article
Constructs a counterexample to an expected uncertain utility characterization and proves a corrected representation theorem. The revised axioms establish the required structure of ideal events and state-independent interval utility.
- 2025
Convexity under ambiguity
Economic Theory Bulletin 13(2):353–373
Journal article
Establishes sufficient conditions for convex preferences in portfolio choice under ambiguity. The result combines aversion to mean-preserving spreads with uncertainty aversion, providing a foundation for diversification without assuming concave utility.
- 2024
Counterexamples to “Transitive Regret”
arXiv:2407.00055
Preprint
Constructs counterexamples to a claimed implication from transitivity and continuity to indifference between identically distributed prospects. The analysis examines the assumptions underlying regret-based preference representations.
- 2026
Savage Without Monotonicity
Philosophy Meets Machine Learning (PhilML), ICML 2026
Peer-reviewed workshop poster
Develops a conditional counterexample in which a finitely additive expected-utility representation assigns equal value to an act and its statewise improvement. It identifies additional additivity, dominance, or domain assumptions that prevent this conflict.
- 2026
Model Collapse Despite Ground-Truth Verification
Hypothesis Testing, ICML 2026
Peer-reviewed workshop poster
Separates exact verification of generated artifacts from coverage of the target task population, showing how missing task types limit risk identification and developing an audit bound for target-risk claims.
- 2026
Behavior-Only Deployment Certification Requires Bridge Assumptions
Failure Modes in Agentic AI (FAGEN), ICML 2026
Peer-reviewed workshop poster
Shows why behavioral evaluation alone cannot certify deployment safety without assumptions connecting evaluation and deployment histories, and quantifies the sample cost of detecting rarely reached failures.
- 2026
Bayesian Truth Serum for LLMs?
Statistical Frameworks for Uncertainty in Agentic Systems (AgenticUQ), ICML 2026
Peer-reviewed workshop poster
Tests Bayesian Truth Serum aggregation for language-model panels, finding lower accuracy than majority voting but improved calibration on the evaluated review and benchmark tasks.
- 2019
Assessing cell-based animal proteins
Science 363(6429):826
Letter
Mentorship and collaboration
Shuo collaborates with student researchers on language-model evaluation and model collapse. The work connects theoretical questions with computational experiments and reproducible research artifacts, while giving students opportunities to take part in open research.
Xuanyi Wang
Research collaborator
Collaborates with Shuo Li Liu on CAST Decision Theory, supported by a $20,000 Corrigibility Research Fund grant.
Hruday Sivakumar
Student researcher
Research collaboration on Bayesian Truth Serum and the evaluation of language-model panels.
Vivan Shankar
Research mentee
Research assistance on model collapse, verification, and the evaluation of learning systems.
Research resources
- Bayesian Truth-Serum Debate Aggregator
Research code for evaluating Bayesian Truth Serum aggregation in language-model panels.
- Constitutional AI as Judgment Aggregation
Repository accompanying work on judgment aggregation and constitutional AI.
- Public Knowledge Labor after Generative AI
Research on how generative AI changes participation in public technical knowledge.
- Public knowledge replication materials
Data and replication infrastructure for the public-knowledge research project.
Academic background
- Princeton UniversityPhD student in Economics.
- Harvard UniversityMaster’s degree in Finance, Extension Studies · 2017–2019.
- McGill UniversityBachelor’s degree in Biochemistry and Mathematics · 2012–2016.
Contact
For research collaboration, student mentorship, or AgentNorm’s public-interest research programme:
admin@agentnorm.tech
Public scholarly profiles: OpenReview · Google Scholar · GitHub