analiza aiqbench
This research adapts the StreamLLM methodology to Answer Set Programming (ASP), leveraging Large Language Models to generate constraints that prune combinatorial search spaces. By filtering invalid candidates through syntax checks and performance validation on training instances, the approach achieves significant speedups of up to 4x–5x across standard benchmarks like Sokoban and Towers of Hanoi. The study demonstrates a practical application where AI models directly enhance logical inference efficiency in constraint solving domains.
Streamliners for Answer Set Programming
arXiv:2604.19251v2 Announce Type: replace-cross Abstract: Streamliner constraints reduce the search space of combinatorial problems by ruling out portions of the solution space. We adapt the StreamLLM approach, which uses Large Language Models (LLMs) to generate streamliners for Constraint Programming, to Answer Set Programming (ASP). Given an ASP encoding and a few small training instances, we prompt multiple LLMs to propose candidate constraints. Candidates that cause syntax errors, render satisfiable instances unsatisfiable, or degrade performance on all training instances are discarded. The surviving streamliners are evaluated together with the original encoding, and we report results for a virtual best encoding (VBE) that, for each instance, selects the fastest among the original encoding and its streamlined variants. On three ASP competition benchmarks (Partner Units Problem, Sokoban, Towers of Hanoi), the VBE achieves speedups of up to 4 to 5 times over the original encoding.
Abstract:Streamliner constraints reduce the search space of combinatorial problems by ruling out portions of the solution space. We adapt the StreamLLM approach, which uses Large Language Models (LLMs) to generate streamliners for Constraint Programming, to Answer Set Programming (ASP). Given an ASP encoding and a few small training instances, we prompt multiple LLMs to propose candidate constraints. Candidates that cause syntax errors, render satisfiable instances unsatisfiable, or degrade performance on all training instances are discarded. The surviving streamliners are evaluated together with the original encoding, and we report results for a virtual best encoding (VBE) that, for each instance, selects the fastest among the original encoding and its streamlined variants. On three ASP competition benchmarks (Partner Units Problem, Sokoban, Towers of Hanoi), the VBE achieves speedups of up to 4 to 5 times over the original encoding.
In Proceedings ICLP 2026, arXiv:2607.17707
Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI)
arXiv:2604.19251 [cs.LO]
(or arXiv:2604.19251v2 [cs.LO] for this version)
https://doi.org/10.48550/arXiv.2604.19251 Focus to learn more arXiv-issued DOI via DataCite
EPTCS 450, 2026, pp. 236-255
https://doi.org/10.4204/EPTCS.450.19 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 254 cuvinte
Subiecte conexe
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · 24 sept. 2026
Netskope (NTSK) Q2 2027 Earnings Call Transcript
fool.com · 10 sept. 2026
A Key-Position Confound in no-cot-bench (and implications for interpreting looped transformers)
LessWrong · 2 oct. 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026