verify-each-reasoning-step-solver-backtrack-failure TEC-0229 · proposedVerify each reasoning step with a solver and backtrack on fa
Decompose each generated reasoning step into context, implicit assumptions and conclusion, formalize it into a solver specification, score it by premise fidelity plus solver entailment, and regenerate from that step when the score falls bel
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Decompose each generated reasoning step into context, implicit assumptions and conclusion, formalize it into a solver specification, score it by premise fidelity plus solver entailment, and regenerate from that step when the score falls bel Filed by the drafting stage from LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers (2609.21492) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Compared against vanilla CoT on 168 benchmark-metric cells across 8 datasets and 7 models, improving in 133; unverified step ratio and verification-weighted accuracy reported per cell; also compared against LogicReward (OA 0.4338 to 0.5765) and against beam search and MCTS variants on SARA.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.