From the 1 of 9 linked papers with an AI index.
9 papers
MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning
Ayoung Lee, Ryan Kwon, Yunxiang Zhang +3
The paper introduces a multilingual, culture-aware benchmark (MCLASH) and a two-step, theory‑grounded prompting method (MET) with a self‑distillation variant (MET‑D) to improve mor…
LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
Kaijian Zou, Aaron Xiong, Yunxiang Zhang +6
Competitive programming problems are increasingly used to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification. Yet, cu…
AdaMEM: Test-Time Adaptive Memory for Language Agents
Yunxiang Zhang, Yiheng Li, Ali Payani +1
A central challenge for language agents is utilizing past experience to adapt to dynamic test-time conditions. While recent work demonstrates the promise of agentic memory mechanis…
Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
Yunxiang Zhang, Muhammad Khalifa, Lechen Zhang +5
Large reasoning models exhibit long chain-of-thought reasoning with complex strategies such as backtracking and self-verification. Yet, these capabilities typically require resourc…
Learning to Ideate for Machine Learning Engineering Agents
Yunxiang Zhang, Kang Zhou, Zhichao Xu +5
Existing machine learning engineering (MLE) agents struggle to iteratively optimize their implemented algorithms for effectiveness. To address this, we introduce MLE-Ideator, a dua…
Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim +6
Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories inclu…