8 papers
Agent-Facing Information Design in LLM Tool Registries
Haochuan Kevin Wang
LLM tool registries function as unregulated advertising platforms: providers write free-text descriptions that agents use for selection, yet no measurement infrastructure -- no vie…
Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers
Haochuan Kevin Wang, Zechen Zhang
Multi-agent LLM systems are entering production -- processing documents, managing workflows, acting on behalf of users -- yet their resilience to prompt injection is still evaluate…
Diffusion-MPC in Discrete Domains: Feasibility Constraints, Horizon Effects, and Critic Alignment: Case study with Tetris
Haochuan Kevin Wang
We study diffusion-based model predictive control (Diffusion-MPC) in discrete combinatorial domains using Tetris as a case study. Our planner samples candidate placement sequences…
Forecasting Liquidity Withdraw with Machine Learning Models
Haochuan, Wang
Liquidity withdrawal is a critical indicator of market fragility. In this project, I test a framework for forecasting liquidity withdrawal at the individual-stock level, ranging fr…
Heterogeneous Trader Responses to Macroeconomic Surprises: Simulating Order Flow Dynamics
Haochuan Wang
Understanding how market participants react to shocks like scheduled macroeconomic news is crucial for both traders and policymakers. We develop a calibrated data generation proces…
A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios
Xiachong Feng, Longxu Dou, Ella Li +5
Game-theoretic scenarios have become pivotal in evaluating the social intelligence of Large Language Model (LLM)-based social agents. While numerous studies have explored these age…