From the 1 of 13 linked papers with an AI index.
8 papers · 1 filter
Neurosymbolic Discovery of Algebraic Graph Constructions
David Seka, Stefan Szeider
There are several methods for searching for graphs with prescribed properties, such as SAT solvers and specialized generators. These methods return the result as raw data: an adjac…
LeanCSP: A Framework for Certifying Constraint Reformulation and Solving in Lean
Pablo Manrique, Stefan Szeider
The paper presents LeanCSP, a framework built in the Lean theorem prover that can formally verify constraint reformulations and certify solver results for constraint problems, prov…
Algorithm Selection with Zero Domain Knowledge via Text Embeddings
Stefan Szeider
We propose a feature-free approach to algorithm selection: instead of hand-crafted instance features, we use pretrained text embeddings. Our method, ZeroFolio, proceeds in three st…
Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design
Hai Xia, Carla P. Gomes, Bart Selman +1
We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with symbolic computation tools, and…
CP-Agent: Agentic Constraint Programming
Stefan Szeider
The translation of natural language to formal constraint models requires expertise in the problem domain and modeling frameworks. To explore the effectiveness of agentic workflows,…
What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns
Stefan Szeider
We introduce an architecture for studying the behavior of large language model (LLM) agents in the absence of externally imposed tasks. Our continuous reason and act framework, usi…