9 papers
ExpEvolve: Structuring and Reusing Experience for Open-Ended Discovery
Yongqiang Chen, Chenxi Liu, Deyu Zou +4
Evolutionary coding agents such as AlphaEvolve are one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scienti…
APeB: Benchmarking Personalization Ability of Large Language Model Agents
Garry Yang, Zizhe Chen, Xinru Chen +9
LLM-powered agents struggle with personalization when users issue raw, underspecified queries. In this setting, agents must infer latent intent, extract preferences from noisy inte…
Closed-Loop Molecular Design with Calibrated Deference
Newman Cheng, Gordon Broadbent, Jason Dong +11
We present Cognitive Loop via In-Situ Optimization (CLIO), an agent that couples a continuously-updated belief-state graph with a recursive plan-then-act loop. The result is a reas…
On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
Deyu Zou, Yongqiang Chen, Fan Feng +4
Reinforcement learning (RL) has become a de facto paradigm for building LLM-based agents that act, interact, and reason over extended task horizons. However, in active reasoning wh…
Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
Deyu Zou, Yongqiang Chen, Jianxiang Wang +5
Active reasoning requires large language model (LLM) agents to interact with external sources and strategically gather information to solve problems in multiple turns. Central to t…
RoFt-Mol: Benchmarking Robust Fine-Tuning with Molecular Graph Foundation Models
Shikun Liu, Deyu Zou, Nima Shoghi +3
In the era of foundation models, fine-tuning pre-trained models for specific downstream tasks has become crucial. This drives the need for robust fine-tuning methods to address cha…
Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation
Deyu Zou, Yongqiang Chen, Mufei Li +5
Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to ground responses with structured external knowledge from up-to-date knowledge graphs (KGs)…
Pairwise Alignment Improves Graph Domain Adaptation
Shikun Liu, Deyu Zou, Han Zhao +1
Graph-based methods, pivotal for label inference over interconnected objects in many real-world applications, often encounter generalization challenges, if the graph used for model…
GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts
Deyu Zou, Shikun Liu, Siqi Miao +3
Geometric deep learning (GDL) has gained significant attention in scientific fields, for its proficiency in modeling data with intricate geometric structures. However, very few wor…