Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles

תקציר מקורי באנגליתarXiv:2606.23672v3 Announce Type: replace Abstract: This paper presents our algorithmic innovations for the NVIDIA Nemotron Model Reasoning Challenge, focusing on Bit Manipulation Puzzles. In this task, the objective is to discover a hidden logical rule transforming input binary strings to outputs, then apply it to unseen inputs. Large Language Models (LLMs) notoriously struggle here; traditional methods force them to simulate complex boolean logic and arithmetic, leading to hallucinations. Furthermore, the search space of bitwise operations (combinations of shifts, rotations, and logic gates) suffers from a severe combinatorial explosion. To overcome this computational intractability, we present a novel approach that abandons arithmetic logic entirely in favor of string similarity, struct