Chopthin-Consensus Power Sampling (CCPS) is a new inference-time decoding method for large language models that uses the Chopthin resampler to preserve diversity among particle trajectories. By enforcing an upper bound on weight ratios instead of equal-weight resampling, CCPS maintains a richer set of distinct reasoning paths and guarantees a lower bound on effective sample size. Coupled with a semantic-majority selection mechanism, CCPS achieves higher oracle coverage and matches or surpasses baseline accuracy on multiple reasoning benchmarks.
By Minoo Ahmadi, Seyedarmin Azizi, Erfan Baghaei Potraghloo, Mehdi Kamal, Massoud Pedram
arXiv:2609.38104v1 Announce Type: new
Abstract: Power-sharpened sampling is an inference-time alternative to reinforcement-learning (RL) post-training for enhancing reasoning in large language models...
By Panagiotis Theodoropoulos, Nan Jiang, Xintong Duan, Ali Hasan, Yuriy Nevmyvaka, Evangelos A. Theodorou, Wei Deng
arXiv:2606. 09926v1 Announce Type: cross Abstract: Sampling from the sequence-level power distribution $p^\alpha$ elicits RL-level reasoning from base language models without any parameter updates, but the standard Metropolis--Hastings (MH), a Markov Chain Monte Carlo (MCMC) sampler, is both expensive and slow-mixing.
By Hong Guo, Nianhui Guo, Christoph Meinel, Haojin Yang
arXiv:2608. 14420v1 Announce Type: new Abstract: Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at inference time.
By Haohui Yang, Jiaxing Sun, Xiujun Ma
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
arXiv:2605.30327v2 Announce Type: replace-cross
Abstract: Frontier reasoning models are produced by post-training base language models with reinforcement learning. Recent work has challenged this by...
By Felix Zhou, Anay Mehrotra, Quanquan C. Liu
arXiv:2610. 13653v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved LLM reasoning, yet growing evidence suggests it mainly performs distribution sharpening: concentrating probability mass on reasoning paths the base model already produces.
By Abiel Malkani Talwar, Christopher Nemeth, Henry Moss
arXiv:2610.08563v1 Announce Type: new
Abstract: Sequence-level power sampling has recently emerged as a training-free approach to reasoning by sampling from a sharpened output distribution of a base...
By Bingnan Xiao, Chenhao Yang, Bingcong Li, Wei Ni, Xin Wang
arXiv:2607. 09693v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become the dominant paradigm for improving the reasoning capabilities of large language models, but it requires expensive training, curated data, and reward signals.
By Zibin Meng, Peng Xie, Kani Chen
The paper investigates how reinforcement learning post‑training of large language models (LLMs) tends to sharpen existing behaviors, improving single‑shot accuracy but reducing solution coverage. It shows that pre‑trained LLMs, when paired with a lightweight inference harness, can outperform post‑trained models in coverage for agentic tasks that require multi‑turn tool use. The authors introduce the Sharpening Tax metric to quantify this trade‑off, analyze its prevalence across 14 model pairs and 42 benchmark cases, and propose a Bayesian sampler, PTGS, that mitigates the tax by adapting sampling temperature to prompt difficulty.
By Changdae Oh, Qi Zeng, Qi Qi, Andrey Zhmoginov, Deren Lei, Yun He, Hoang Phan, Hangoo Kang, Azalia Mirhoseini, Sharon Li
arXiv:2606. 13982v1 Announce Type: cross Abstract: Sampling plays an important role in long-form language-model reasoning.
By Ousmane Amadou Dia
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