Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Field
Mathematical and algorithmic reasoning (theorem proving, math benchmarks, algorithmic generalisation, neural solvers)
This field studies machine reasoning where correctness is checkable: formal theorem proving in proof assistants (Lean, Isabelle, Coq), mathematical problem solving by language models, learning to execute algorithms and synthesise programs with out-of-distribution generalisation, and neural solvers for combinatorial problems such as routing and satisfiability. Evaluation is by verified success under a stated compute or sample budget (proofs accepted by the kernel, exact-match answers, optimality gap to a classical solver), with close attention to benchmark contamination and to size or distribution shift between training and test.