Interpretable Adaptive Sampling for LLM Test-Time Scaling

• URL: http://arxiv.org/abs/2608.03961v1
• Date: Tue, 04 Aug 2026 17:27:21 GMT
• Title: Interpretable Adaptive Sampling for LLM Test-Time Scaling
• Abstract summary: We propose a lightweight fuzzy controller that maps interpretable signals, including estimated prompt complexity and model confidence, to a per-query sampling budget.<n>The controller assigns fewer samples to easier or more confident prompts and more samples to harder or less certain prompts, making inference-time compute inspectable rather than fixed or opaque.
• Score: 8.794670104526867
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that spend the same compute on easy and difficult prompts. These fixed budgets are also difficult to inspect because they do not explain why a given prompt receives a particular number of samples. We propose adaptive} test-time scaling with a lightweight fuzzy controller that maps interpretable signals, including estimated prompt complexity and model confidence, to a per-query sampling budget. The controller assigns fewer samples to easier or more confident prompts and more samples to harder or less certain prompts, making inference-time compute inspectable rather than fixed or opaque. We evaluate under a fair-alignment protocol with matched decoding settings and controlled answer selection, and compare against best-of-$N$, compute-aware scaling, and self-certainty-based baselines on question-answering and mathematical reasoning tasks. Across models and datasets, adaptive fuzzy control improves over several standard baselines and remains close to a selector-matched full-budget control while reducing the average number of samples. These findings suggest that interpretable adaptive sampling is a practical direction for more efficient test-time reasoning in large language models.

Related papers

• REAR: Test-time Preference Realignment through Reward Decomposition [68.09214603569744]
  We introduce a novel framework that models the task as a realignment problem, since the base model often fails to align with the stated preference.<n>We derive a REAlignment Reward (REAR) that selectively rescales the proportions of these two reward terms.<n>We show that REAR can be formulated as a linear combination of token-level policy log-probabilities, making it computationally efficient and easy to integrate with various TTS algorithms.
  arXiv  Detail & Related papers  (2026-06-29T14:17:53Z)
• Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling [16.727861334696883]
  We formulate adaptive sampling as a Markov decision process (MDP)<n>We train a lightweight sampling controller with reinforcement learning (RL) to jointly balance answer correctness, latency, and cost.<n>Our method is lightweight which only relies on statistics of final answers, and can be trained and deployed on CPU.
  arXiv  Detail & Related papers  (2026-06-02T03:42:04Z)
• $V_1$: Unifying Generation and Self-Verification for Parallel Reasoners [69.66089681814013]
  $V_$ is a framework that unifies generation and verification through efficient pairwise ranking.<n>$V_$-Infer improves Pass@1 by up to $10%$ over pointwise verification.<n>$V_$-PairRL achieves $7$--$9%$ test-time scaling gains over standard RL and pointwise joint training.
  arXiv  Detail & Related papers  (2026-03-04T17:22:16Z)
• Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training [47.26632817047513]
  Reinforcement learning applied to large language models (LLMs) for reasoning tasks is often bottlenecked by unstable gradient estimates.<n>We propose Reinforce-Ada, an adaptive sampling framework for online RL post-training of LLMs.<n>Unlike conventional two-stage allocation methods, Reinforce-Ada interleaves estimation and sampling in an online successive elimination process.
  arXiv  Detail & Related papers  (2025-10-06T16:34:09Z)
• Learning to Ponder: Adaptive Reasoning in Latent Space [2.8835557003761747]
  We present FR-Ponder, a single-graph, backbone-training-free framework that allocates instance-adaptive reasoning compute via latent steering.<n>On GSM8K and MATH500, FR-Ponder improves the compute-accuracy frontier, delivering lower FLOPs with better matched accuracy and comparing favorably to early-exit baselines.
  arXiv  Detail & Related papers  (2025-09-29T03:21:42Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models? [65.18157595903124]
  This work investigates iterative approximate evaluation for arbitrary prompts.<n>It introduces Model Predictive Prompt Selection (MoPPS), a Bayesian risk-predictive framework.<n>MoPPS reliably predicts prompt difficulty and accelerates training with significantly reduced rollouts.
  arXiv  Detail & Related papers  (2025-07-07T03:20:52Z)
• Efficient MCMC Sampling with Expensive-to-Compute and Irregular Likelihoods [2.299872239734834]
  We explore several sampling algorithms that make use of subset evaluations to reduce computational overhead.<n>We introduce data-driven proxies in place of Taylor expansions and define a novel-cost aware adaptive controller.<n>We find our improved version of Importance with Nested Training Samples (HINTS), with adaptive proposals and a data-driven proxy, obtains the best sampling error in a fixed computational budget.
  arXiv  Detail & Related papers  (2025-05-15T16:06:44Z)
• Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs [60.58434523646137]
  A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency. We introduce Adaptive-Consistency, a cost-efficient, model-agnostic technique that dynamically adjusts the number of samples per question. Our experiments show that Adaptive-Consistency reduces sample budget by up to 7.9 times with an average accuracy drop of less than 0.1%.
  arXiv  Detail & Related papers  (2023-05-19T17:49:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.