arXiv AI August 26, 2026 By Sophia Xiao Pu, Yumo Xu, Sailik Sengupta, Millennium Bismay, Ruixue Lian, James Gung, Yi-an Lai, Arshit Gupta

Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning

Read the original on arXiv AI →

Selective Regenerative Decoding (SRD) is a new inference-time decoding method that improves large language model reasoning by allowing segment-level intervention on candidate trajectories. Instead of discarding or keeping entire trajectories, SRD selectively refines only the degraded suffix while preserving useful prefixes, leading to higher expected trajectory quality and better sample efficiency. Experiments on MATH500, GPQA Diamond, HotpotQA, and AlpacaEval show that SRD matches Best-of-N accuracy with fewer generated tokens and outperforms speculative rejection in low‑compute settings.

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.

arXiv AI

Jun 16

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling

arXiv:2605. 02427v3 Announce Type: replace Abstract: A recurring pattern in "reasoning without training" is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the bottleneck is locating these modes efficiently at inference time.

By Tu Nguyen, Matthieu Zimmer, Rasul Tutunov, Xiaotong Ji, Haitham Bou Ammar

llms safety

arXiv AI

Jun 15

Fractured Chain-of-Thought Reasoning

arXiv:2505. 12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining.

By Baohao Liao, Hanze Dong, Yuhui Xu, Doyen Sahoo, Christof Monz, Junnan Li, Caiming Xiong

llms benchmarks

arXiv AI

Aug 11

Thought-Level Beam Search for Reasoning

arXiv:2608. 08020v1 Announce Type: new Abstract: Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it.

By Lijie Yang, Hongyin Luo, Tri Dao, Ravi Netravali

efficiency benchmarks

arXiv Machine Learning

Jul 24

Test-Time Scaling via Error Localization

arXiv:2607. 21453v1 Announce Type: new Abstract: Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks.

By Rajiv Shailesh Chitale, Rahul Madhavan, Taneesh Gupta, Deepanway Ghosal, Aravindan Raghuveer

llms benchmarks

arXiv Computation and Language

Oct 15

REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning

arXiv:2610.19561v1 Announce Type: new Abstract: An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to...

By Yi Ding, Mengyu Wang, Min Zhou, Menglin Yang

benchmarks

arXiv Machine Learning

Aug 6

SpecRoll: Fast-Slow Verifier-Feedback Adaptation for Speculative Reinforcement Learning Rollouts

arXiv:2608. 04962v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but autoregressive rollout generation remains a major efficiency bottleneck.

By Nhat Minh Pham, Duy Tung Doan, Thi Duyen Ngo, Vinh Van Nguyen, Khac-Hoai Nam Bui

llms reinforcement-learning

One email a morning, machine-written

Related stories

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling

Fractured Chain-of-Thought Reasoning

Thought-Level Beam Search for Reasoning

Test-Time Scaling via Error Localization

REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning

SpecRoll: Fast-Slow Verifier-Feedback Adaptation for Speculative Reinforcement Learning Rollouts