arXiv AI October 2, 2026 By Bangji Yang, Jiajun Fan, Hongba Ma, Xi Zhu, Weizhi Zhang, Minghao Guo, Ye Li, Hamid Palangi, Jiaxuan You

ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv AI

Aug 7

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

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.

By Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Lena Trigg, Ali Subhan, Muhammad Ali, Dean F. Hougen

llms reinforcement-learning

arXiv AI

Jul 1

Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2

arXiv:2606. 31543v1 Announce Type: new Abstract: Large language models can produce fluent, internally coherent reasoning traces for abstract reasoning tasks while still being confidently wrong - making selection among candidates, not just generation, the central challenge.

By Johan Land

llms benchmarks

arXiv AI

Sep 1

Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula

arXiv:2608.30035v1 Announce Type: new Abstract: Self-evolving reasoning frameworks train a Challenger to generate questions exposing a Solver's weaknesses, creating adaptive curricula without human d...

By Vinoth Selvendran, Zhanming Zhang

reinforcement-learning benchmarks

arXiv AI

Jun 16

Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning

arXiv:2606. 15972v1 Announce Type: cross Abstract: With large language models (LLMs) increasingly applied to mathematical reasoning, formal proof assistants such as Lean can be leveraged to verify reasoning outputs with machine-checkable rigor, enabling use cases such as answer selection in test-time scaling with K sampled candidate answers.

By Ji Feng, Zhouxing Shi

llms benchmarks

arXiv AI

Jul 14

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

arXiv:2607. 10139v1 Announce Type: cross Abstract: Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution.

By Ning Liu

llms benchmarks

Hugging Face Trending Papers

Jun 1

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths. PRM guided search avoids this by scoring candidate continuations during generation, but requires a reward model trained with step-level labels.

llms reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2

Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula

Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning