The reviewed record of science sign in
Pith

arxiv: 2502.01618 · v5 · pith:Z6ELNVS6 · submitted 2025-02-03 · cs.LG · cs.AI

Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:Z6ELNVS6record.jsonopen to challenge →

classification cs.LG cs.AI
keywords scalinginference-timeinferencemethodsapproachllmsmodelsonly
0
0 comments X
read the original abstract

Large language models (LLMs) have achieved significant performance gains via scaling up model sizes and/or data. However, recent evidence suggests diminishing returns from such approaches, motivating scaling the computation spent at inference time. Existing inference-time scaling methods, usually with reward models, cast the task as a search problem, which tends to be vulnerable to reward hacking as a consequence of approximation errors in reward models. In this paper, we instead cast inference-time scaling as a probabilistic inference task and leverage sampling-based techniques to explore the typical set of the state distribution of a state-space model with an approximate likelihood, rather than optimize for its mode directly. We propose a novel inference-time scaling approach by adapting particle-based Monte Carlo methods to this task. Our empirical evaluation demonstrates that our methods have a 4-16x better scaling rate over our deterministic search counterparts on various challenging mathematical reasoning tasks. Using our approach, we show that Qwen2.5-Math-1.5B-Instruct can surpass GPT-4o accuracy in only 4 rollouts, while Qwen2.5-Math-7B-Instruct scales to o1 level accuracy in only 32 rollouts. Our work not only presents an effective method to inference-time scaling, but also connects the rich literature in probabilistic inference with inference-time scaling of LLMs to develop more robust algorithms in future work. Code, videos, and further information available at https://probabilistic-inference-scaling.github.io.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Power of Test-Time Training for Approximate Sampling

    cs.DS 2026-06 unverdicted novelty 7.0

    Establishes a quadratic lower bound on query complexity for sampling from large classes of distributions given approximate density oracles, answers an open question on optimality of random walks, and shows circumventi...

  2. ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

    cs.AI 2025-10 unverdicted novelty 7.0

    ToolPRM provides fine-grained intra-call process supervision via a new dataset and reward model, outperforming outcome and coarse-grained alternatives on function-calling benchmarks.

  3. Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement

    cs.LG 2025-07 conditional novelty 7.0

    PG-DLM applies particle Gibbs sampling over full trajectories in diffusion language models to enable iterative refinement, yielding higher accuracy on reward-guided generation with theoretical convergence guarantees.

  4. TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation

    cs.LG 2025-11 unverdicted novelty 6.0

    TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and S...

  5. TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning

    cs.LG 2025-05 unverdicted novelty 5.0

    TokUR estimates token-level uncertainty via low-rank weight perturbations in LLMs, aggregates signals to correlate with correctness, and uses them to improve reasoning performance on math tasks.