27 citations · 64 across the 23 of their papers we have counts for
8 papers · 1 filter
Heterogeneous Agentic Coevolution
Wenqian Ye, Ziwei Guan, Zi Yang +14
Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-specific applications rely on spe…
Capturing In-Context Learning Dynamics with Task Operators
Guangzhi Xiong, Zhenghao He, Bohan Liu +3
In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the full set of…
LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery
Bo Yuan, Wenqian Ye, Zelin Zhao +4
Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from…
Rethinking Reasoning Paths as Phase-Structured Trajectories
Zhenghao He, Guangzhi Xiong, Sanchit Sinha +3
Large language models often improve problem-solving performance by generating multi-step reasoning paths, yet how to analyze the hidden states along these paths remains unclear. Ex…
From World Models to World Action Models: Rethinking Next-State Prediction
Tingyu Yuan, Ziming Ji, Biaoliang Guan +9
Predicting the next state is a core paradigm of World Models for modeling physical dynamics, emphasizing prediction fidelity. As World Models evolve into World-Action Models (WAMs)…
ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving
Wenqian Ye, Ziwei Guan, Eric Xie +6
Automated theorem proving offers a natural foundation for recursive self-improvement in scientific discovery. However, existing neural provers do not fully preserve this recursive…
ALPS: Measuring Valid Creativity in Large Language Models with Mathematical Construction
Eric Xie, Wenqian Ye, Aidong Zhang
Large language models produce outputs presented as discoveries - new proofs, conjectures, or molecules. Whether such an output that appears creative is truly original and effective…
Towards Robustness against Typographic Attack with Training-free Concept Localization
Bohan Liu, Wenqian Ye, Guangzhi Xiong +3
Models trained via Contrastive Language-Image Pretraining (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Models (LVLMs). Despite their wides…