291 citations · 595 across the 20 of their papers we have counts for
7 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…
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…
A Sober Look at Agentic Misalignment in Automated Workflows
Wenqian Ye, Bo Yuan, Zhichao Xu +4
We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solv…
Stimulating Creativity with FunLines: A Case Study of Humor Generation in Headlines
Nabil Hossain, John Krumm, Tanvir Sajed +1
Building datasets of creative text, such as humor, is quite challenging. We introduce FunLines, a competitive game where players edit news headlines to make them funny, and where t…
Inferring Fine-grained Details on User Activities and Home Location from Social Media: Detecting Drinking-While-Tweeting Patterns in Communities
Nabil Hossain, Tianran Hu, Roghayeh Feizi +3
Nearly all previous work on geo-locating latent states and activities from social media confounds general discussions about activities, self-reports of users participating in those…
A Bayesian Approach to Tackling Hard Computational Problems
Eric J. Horvitz, Yongshao Ruan, Carla P. Gomes +3
We are developing a general framework for using learned Bayesian models for decision-theoretic control of search and reasoningalgorithms. We illustrate the approach on the specific…
Towards Understanding and Harnessing the Potential of Clause Learning
P. Beame, H. Kautz, A. Sabharwal
Efficient implementations of DPLL with the addition of clause learning are the fastest complete Boolean satisfiability solvers and can handle many significant real-world problems,…