6 papers
Discovering Expert-Level Nash Equilibrium Algorithms with Large Language Models
Hanyu Li, Dongchen Li, Xiaotie Deng
Designing polynomial-time algorithms for approximate Nash equilibria (ANE) with provable worst-case guarantees is a fundamental open problem in algorithmic game theory. While large…
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
Hanyu Li, Yichi Zhang, Speed Zhu +3
Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on end-to-end tasks such as issue…
An Information-Theoretic Criterion for Efficient Data Synthesis
Hanyu Li, Zhengqi Sun, Xiaotie Deng
Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: s…
Will AI Trade? A Computational Inversion of the No-Trade Theorem
Hanyu Li, Xiaotie Deng
Classic no-trade theorems attribute trade to heterogeneous beliefs. We re-examine this conclusion for AI agents, asking if trade can arise from computational limitations, under com…
How Large Language Models Need Symbolism
Xiaotie Deng, Hanyu Li
We argue that AI's future requires more than scaling. To unlock genuine discovery, large language models need a compass: human-crafted symbols to guide their powerful but blind int…
IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis
Hanyu Li, Haoyu Liu, Tingyu Zhu +4
Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper i…