6 papers
Safe Harness Self-Evolution: A Theoretical Analysis of Feasibility and Limits
Qianshu Cai, Yonggang Zhang, Jun Nie +6
Harness self-evolution is the process by which an agent modifies its prompts, tools, code, or orchestration in response to task feedback while keeping the underlying language model…
Execution-grounded evaluation reveals hidden failures in language-model calculations for environmental science
Maohao Ran, Chendong Ma, Yanting Zhang +4
Large language models are increasingly used for quantitative work in the environmental sciences, yet existing evaluations score only final answers, leaving calculation process unob…
A Control Theory of Predictability in Latent World Models
Hanzhe You, Yonggang Zhang, Maohao Ran +6
Latent world models are trained to predict future states in a learned representation and are then deployed inside a planner that selects actions by simulating them forward. Current…
Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection
Cooper Lin, Yanting Zhang, Maohao Ran +7
E-commerce platforms and payment solution providers face increasingly sophisticated fraud schemes, ranging from identity theft and account takeovers to complex money laundering ope…
Crisis-Bench: Benchmarking Strategic Ambiguity and Reputation Management in Large Language Models
Cooper Lin, Maohao Ran, Yanting Zhang +6
Standard safety alignment optimizes Large Language Models (LLMs) for universal helpfulness and honesty, effectively instilling a rigid "Boy Scout" morality. While robust for genera…
CaveAgent: Transforming LLMs into Stateful Runtime Operators
Maohao Ran, Zhenglin Wan, Cooper Lin +21
LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks…