Tag
This paper investigates how to encode factored planning tasks (FTS) into SAT, proposing multiple encoding strategies and analyzing the impact of task transformations on SAT-based planning performance. It aims to extend SAT solving to more compact planning representations beyond heuristic search.
This paper benchmarks seven LLM feedback agents in propositional logic tutoring, finding they perform well on optimal steps but systematically fail to correctly diagnose valid suboptimal and incorrect solutions, highlighting limitations for adaptive tutoring.
Recreation of the first published version (1956, IPL-I) of the Logic Theorist theorem prover, a seminal AI program by Newell, Shaw, and Simon, with runnable Python code and documentation.