arXiv:2608. 05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity.
arXiv:2602. 03061v2 Announce Type: replace-cross Abstract: Evaluating mathematical reasoning in LLMs is constrained by limited benchmark sizes and inherent model stochasticity, yielding high-variance accuracy estimates and unstable rankings across platforms.
arXiv:2606. 30851v1 Announce Type: cross Abstract: Improving the reliability of large language models (LLMs) at inference time is a central challenge in structured reasoning tasks such as Text-to-SQL.
arXiv:2606. 06915v1 Announce Type: cross Abstract: Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.
ReSolve is a training‑free inference method that reuses candidate reasoning by selectively moderating generative outputs. It examines existing derivations when candidates disagree or lack a parseable answer, then incorporates new solutions into a bounded loop. On 130 competition‑mathematics problems, ReSolve achieves 100 and 99 correct answers with significantly fewer tokens than eight‑sample self‑consistency, while a controlled ablation shows that visible derivations improve accuracy.
arXiv:2606. 17312v1 Announce Type: new Abstract: Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to rank consistently -- a failure mode especially prevalent in multi-step deductive reasoning.
Majority Voting (MV) is a simple and widely used strategy which improves the reasoning accuracy of Large Language Models (LLMs) by allocating additional inference-time computation. Specifically, in MV...
The paper introduces a test-time aggregation framework for multi-agent reasoning with large language models. It mitigates non-semantic biases by normalizing reasoning traces and injects bias to create decision instability, which signals reliability. The method improves accuracy and token efficiency on several mathematical reasoning benchmarks without requiring validation data or prior model strength knowledge.
The paper introduces Length‑Conditioned Majority Voting (LCMV), a test‑time training method that enhances the standard Majority Voting (MV) technique for Large Language Models (LLMs). LCMV incorporates an empirical bias that longer Chain‑of‑Thoughts (CoTs) are less likely to be correct by modeling a length‑conditioned prior with a logistic function. This prior is adapted on unlabeled test data without fine‑tuning the LLM, and the resulting weighted votes consistently outperform standard MV and other length‑ or confidence‑based aggregation strategies across multiple reasoning benchmarks.
Route-Verify-Vote (RVV) is a framework that applies procedure-conditioned self-consistency to mixed-domain reasoning without updating model parameters. It selects a domain-specific reasoning procedure, verifies each option against constraints, and aggregates answer sets, allocating extra samples to questions with close vote margins. On the SCoRE 2026 benchmark, RVV achieves 74.6% exact-set accuracy, improving to 77.3% with adaptive sampling and 79.4% when combining models on selected domain routes, earning second place among participants.
arXiv:2602. 12424v2 Announce Type: replace-cross Abstract: Benchmarks establish a standardized evaluation framework to systematically assess the performance of large language models (LLMs), facilitating objective comparisons and driving advancements in the field.
arXiv:2604. 11996v2 Announce Type: replace-cross Abstract: Should we trust Large Language Models (LLMs) with high accuracy?