20 results for “Problem-solving”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Lan Luo, Anqi Wang, Muzhi Zhou, Junhua Zhu +3 more
This paper presents a system called ParaTutor that supports parent-child tutoring with LLMs, preserving the distinct roles of parents and children.
Murong Yue, Desmond Alexander Mcglone, Emily Slutz, Wenhan Lyu +3 more
The paper introduces a new dataset, PeerMathDial, of peer collaborative problem-solving dialogues in middle school math classrooms.
Tingqiang Xu, Hangrui Zhou, Tianle Cai, Alex Gu +1 more
The authors introduce UOJ-Bench, a benchmark to evaluate Large Language Models' ability to identify errors in human-written code.
F. Carichon, S. Sharma, M. Girard, R. Rampa +1 more
The paper introduces IDEAFix, a systematic evaluation framework designed to analyze how structured prompting and task design influence the divergent thinking and originality of idea generation in LLMs…
The authors prove that the solution-search problem for Ice Walk puzzle is ASP-complete by reducing Hamiltonian cycles in a maximum-degree-3 spanning subgraph of a rectangular grid graph to Ice Walk so…
This paper proves that a majority of filled-in Sudoku grids require a logarithmic fraction of cells to be filled by clues, and constructs grids requiring 18 and 80 clues for 9x9 and 16x16 Sudoku, resp…
The paper introduces LLM-as-an-Investigator, an evidence-first agentic AI methodology for robust problem diagnosis.
The paper develops an explicit multi-linear polynomial form for binary polynomial optimization problems after eliminating a subset of variables, allowing for characterization of new special classes wi…
The paper shows that every problem asking if a given graph has an edge-coloring without an edge-colored clique from a fixed family is poly-time equivalent to a Constraint Satisfaction Problem, resulti…
This paper unifies the fragmented field of Tree-of-Thoughts (ToT) reasoning by mapping LLM-based search processes onto a formal taxonomy derived from classical heuristic search theory.
This paper investigates various methods for encoding factored tasks, a compact planning representation, into propositional logic for use with SAT solvers, analyzing the impact of encoding choices and…
The paper introduces BusinessCaseBench, a benchmark for measuring AI performance on analytical knowledge work using business cases and grading rubrics.
This paper proposes Workflow Cognition as a theoretical framework for explaining expertise as a dynamic cognitive phenomenon.
The paper formalizes collaborative problem solving as block optimization and proves linear convergence for teams of large language model agents.
Valdemar Švábenský, Jan Vykopal, Sukrit Leelaluk, Pavel Čeleda +2 more
This paper compares two methods for assessing student teams in tabletop exercises using data from learning platforms and evaluates their validity and reliability.
This paper proposes SHA-PF, a search hardness-aware LLM-based problem formulation framework for expensive simulation-driven design, which prioritizes rare samples with greater progress potential and r…