activity
20242026
most citedLearning to Discover at Test Time

1 citations · 1 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CL2026

Sparse Reward Subsystem in Large Language Models

Guowei Xu, Mert Yuksekgonul, James Zou

Recent studies show that LLM hidden states encode reward-related information, such as answer correctness and model confidence. However, existing approaches typically fit black-box…

cs.LG20261 cited

Learning to Discover at Test Time

Mert Yuksekgonul, Daniel Koceja, Xinhao Li +8

How can we use AI to discover a new state of the art for a scientific problem? Prior work in test-time scaling, such as AlphaEvolve, performs search by prompting a frozen LLM. We p…

cs.AI2025

Inefficiencies of Meta Agents for Agent Design

Batu El, Mert Yuksekgonul, James Zou

Recent works began to automate the design of agentic systems using meta-agents that propose and iteratively refine new agent architectures. In this paper, we examine three key chal…

cs.AI2025

Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025

Nitya Thakkar, Mert Yuksekgonul, Jake Silberg +6

Peer review at AI conferences is stressed by rapidly rising submission volumes, leading to deteriorating review quality and increased author dissatisfaction. To address these issue…

cs.AI2025

SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

Wanjia Zhao, Mert Yuksekgonul, Shirley Wu +1

Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks. However, these systems often rely on fragile, manually designed prom…

cs.CL2024

TextGrad: Automatic "Differentiation" via Text

Mert Yuksekgonul, Federico Bianchi, Joseph Boen +4

AI is undergoing a paradigm shift, with breakthroughs achieved by systems orchestrating multiple large language models (LLMs) and other complex components. As a result, developing…