arXiv Machine Learning September 14, 2026 By Zhendong Mi, Shaoyi Huang

Sampling via Decision-Flow: Training-Free Extraction of Improved Latent Reasoning Paths in Large Language Models

Read the original on arXiv Machine Learning →

The paper introduces Decision-Flow Sampling (DF‑Sample), a training‑free, data‑free inference framework that builds a hierarchical reasoning tree, evaluates entire trajectories, and back‑propagates utilities to guide branching decisions. Unlike local step‑wise sampling, DF‑Sample explicitly assesses global paths, enabling it to recover high‑quality, low‑probability reasoning chains that standard decoding misses. On the GPQA benchmark, DF‑Sample attains 45.6% accuracy, outperforming power sampling (38.9%) and GRPO (39.9%) and consistently surpassing baselines across multiple models and benchmarks, demonstrating significant latent reasoning potential in pretrained LLMs.

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 Machine Learning.

arXiv AI

Jun 16

Latent Thought Flow: Efficient Latent Reasoning in Large Language Models

arXiv:2606. 16222v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly rely on intermediate reasoning, yet explicit Chain-of-Thought (CoT) suffers from a linguistic space bottleneck: each thought must be decoded into tokens, causing high inference overhead.

By Xiandong Zou, Jing Huang, Jianshu Li, Pan Zhou

llms fine-tuning

Hugging Face Trending Papers

Jun 22

Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently

Recent advances in large language models (LLMs) have demonstrated that reinforcement fine-tuning of pretrained base models can lead to significant gains in reasoning performance at inference time. In this work, we theoretically analyze why reinforcement fine-tuning induces better reasoning ability than purely supervised fine-tuning (SFT) methods.

llms reinforcement-learning fine-tuning

arXiv Computation and Language

22h ago

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

arXiv:2607.28077v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identica...

By Shuang Liang, Haoyang Zhou, Yifan Gong, Guowei Wang, Xiting Wang

llms reinforcement-learning benchmarks

arXiv AI

Jul 20

Understanding Reasoning from Pretraining to Post-Training

arXiv:2607. 16097v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it.

By Jingyan Shen, Ang Li, Salman Rahman, Yifan Sun, Micah Goldblum, Matus Telgarsky, Pavel Izmailov

llms reinforcement-learning fine-tuning

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

Jun 10

Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning

arXiv:2606. 10184v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) relies on the diversity of $K$ rollouts within each group; otherwise, the group-mean advantage $A^{(k)} = r^{(k)} - \mu_r$ collapses to zero.

By Wooil Jung

llms reinforcement-learning

One email a morning, machine-written

Related stories

Latent Thought Flow: Efficient Latent Reasoning in Large Language Models

Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

Understanding Reasoning from Pretraining to Post-Training

Fractured Chain-of-Thought Reasoning

Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning