paper-with-me

Papers

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference

2026-03-09 · Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan J. Foster, Akshay Krishnamurthy arxiv

Inference-time methods that aggregate and prune multiple samples have emerged as a powerful paradigm for steering large language models, yet we lack any principled understanding of their accuracy-cost tradeoffs. In this paper, we introduce a route to rigorously study such approaches using the lens of *particle filtering* algorithms such as Sequential Monte Carlo (SMC). Given a base language model and a *process reward model* estimating expected terminal rewards, we ask: *how accurately can we sample from a target distribution given some number of process reward evaluations?* Theoretically, we identify (1) simple criteria enabling non-asymptotic guarantees for SMC; (2) algorithmic improvements to SMC; and (3) a fundamental limit faced by all particle filtering methods. Empirically, we demonstrate that our theoretical criteria effectively govern the *sampling error* of SMC, though not necessarily its final *accuracy*, suggesting that theoretical perspectives beyond sampling may be necessary.

📄 PDF Abstract BibTeX arXiv:2603.07887

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs

2026-06-30 · Zhongyang Li, Yaqian Li, Faming Fang, Rinyoichi Takezoe 외 arxiv

Multimodal large language models (MLLMs) typically employ resampling-based projectors to transform dense visual features into a compact token sequence for language modeling. Most existing resamplers adopt a single, fixed…

Multimodal Reasoning

Reasoning with Sampling: Cutting at Decision Points

2026-05-28 · Felix Zhou, Anay Mehrotra, Quanquan C. Liu arxiv

Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution,…

Reinforcement Learning

Thought Branches: Interpreting LLM Reasoning Requires Resampling

2025-10-31 · Uzay Macar, Paul C. Bogdan, Senthooran Rajamanoharan, Neel Nanda arxiv

Most work interpreting reasoning models studies only a single chain-of-thought (CoT), yet these models define distributions over many possible CoTs. We argue that studying a single sample is inadequate for understanding …

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

2025-03-27 · Wenqi Zhang, Mengna Wang, Gangao Liu, Xu Huixin 외

Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains which require continuous interaction with env…

Imitation LearningMathematical ReasoningSpatial ReasoningVisual Reasoning

Lost in Space: Probing Fine-grained Spatial Understanding in Vision and Language Resamplers

2024-04-21 · Georgios Pantazopoulos, Alessandro Suglia, Oliver Lemon, Arash Eshghi

An effective method for combining frozen large language models (LLM) and visual encoders involves a resampler module that creates a `visual prompt' which is provided to the LLM, along with the textual prompt. While this …

DiagnosticImage CaptioningQuestion AnsweringVisual Question Answering