works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.AI2026

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

Xiangning Lin, Shenzhe Zhu, Shu Yang +23

The paper presents AISPA, a user‑centric framework for auditing the system prompts that guide large language model behavior in commercial AI products, and reports findings from ana…

cs.LG2026

Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation

Andreas Haupt, Justin Hartenstein, Anka Reuel +2

AI benchmarks have well-documented limitations, with prior work examining contamination, saturation, and construct underspecification. Aggregation has received far less attention:…

cs.AI2026

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

Max Lamparth, Daniel Fein, Andreas Haupt +2

Single-axis mitigations of reward-model biases (e.g., reducing proxy reliance on length, sycophancy, or style) can rotate optimization pressure onto correlated proxies rather than…

cs.LG2026

General Preference Reinforcement Learning

Muhammad Umer, Muhammad Ahmed Mohsin, Ahsan Bilal +5

Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reason…

cs.GT2025

Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning

Ian Gemp, Andreas Haupt, Luke Marris +2

Behavioral diversity, expert imitation, fairness, safety goals and others give rise to preferences in sequential decision making domains that do not decompose additively across tim…