Parallel Test-Time Scaling with Multi-Sequence Verifiers

• URL: http://arxiv.org/abs/2603.03417v1
• Date: Tue, 03 Mar 2026 18:53:56 GMT
• Title: Parallel Test-Time Scaling with Multi-Sequence Verifiers
• Abstract summary: Parallel test-time scaling is a powerful technique for improving large language model performance.<n>It is hindered by two key bottlenecks: accurately selecting the correct solution from the candidate pool, and the high inference latency from generating many full solutions.<n>We introduce the Multi-Sequence Verifier (MSV), the first verifier designed to jointly process all candidate solutions and model their interactions.
• Score: 23.363130292302483
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it is hindered by two key bottlenecks: accurately selecting the correct solution from the candidate pool, and the high inference latency from generating many full solutions. We argue that both challenges are fundamentally linked to verifier calibration. A well-calibrated verifier not only improves answer selection, but also enables early-stopping strategies to reduce latency. However, existing verifiers are limited as they score each candidate in isolation, overlooking rich contextual information across the set of candidates. To address this, we introduce the Multi-Sequence Verifier (MSV), the first verifier designed to jointly process all candidate solutions and model their interactions. MSV achieves improved calibration, which directly enhances best-of-N selection performance. We further introduce a streaming MSV variant that empowers a novel early-stopping framework. Our novel framework fully leverages parallel decoding, which contrasts with the existing multi-sequence early exit works that decode sequences one by one and thus incur significant latency. In this novel setting, MSV can achieve the same target accuracy with around half the latency that would be required with its counterpart that scores each solution in isolation.

Related papers

• $V_1$: 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)
• One-Token Verification for Reasoning Correctness Estimation [31.590898058475464]
  One-Token Verification (OTV) is a computational method that estimates reasoning correctness in a single forward pass during generation.<n>OTV consistently surpasses existing verifiers and reduces token usage by up to $90%$ through correctness-guided early termination.
  arXiv  Detail & Related papers  (2026-03-01T10:09:58Z)
• Scaling Agentic Verifier for Competitive Coding [66.11758166379092]
  Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt.<n>Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling.<n>We propose Agentic Verifier, an execution-based agent that actively reasons about program behaviors and searches for highly discriminative test inputs.
  arXiv  Detail & Related papers  (2026-02-04T06:30:40Z)
• ATTS: Asynchronous Test-Time Scaling via Conformal Prediction [112.54016379556073]
  Large language models (LLMs) benefit from test-time scaling but are often hampered by high inference latency.<n>We introduce ATTS (Asynchronous Test-Time Scaling), a statistically guaranteed adaptive scaling framework.<n>We show that ATTS delivers up to 56.7x speedup in test-time scaling and a 4.14x throughput improvement.
  arXiv  Detail & Related papers  (2025-09-18T16:55:09Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• CodeMonkeys: Scaling Test-Time Compute for Software Engineering [45.84513832258217]
  Scaling test-time compute is a promising axis for improving LLM capabilities.<n>Here, we explore this problem in the context of solving real-world GitHub issues from the SWE-bench dataset.<n>Our system, named CodeMonkeys, allows models to iteratively edit a by jointly generating and running a testing script alongside their draft edit.
  arXiv  Detail & Related papers  (2025-01-24T18:58:40Z)
• Learning Multiple Initial Solutions to Optimization Problems [52.9380464408756]
  Sequentially solving similar optimization problems under strict runtime constraints is essential for many applications.<n>We propose learning to predict emphmultiple diverse initial solutions given parameters that define the problem instance.<n>We find significant and consistent improvement with our method across all evaluation settings and demonstrate that it efficiently scales with the number of initial solutions required.
  arXiv  Detail & Related papers  (2024-11-04T15:17:19Z)
• V-STaR: Training Verifiers for Self-Taught Reasoners [71.53113558733227]
  V-STaR trains a verifier using DPO that judges correctness of model-generated solutions. Running V-STaR for multiple iterations results in progressively better reasoners and verifiers.
  arXiv  Detail & Related papers  (2024-02-09T15:02:56Z)
• Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization [64.62570402941387]
  We use a single test sample to adapt multi-modal prompts at test time by minimizing the feature distribution shift to bridge the gap in the test domain. Our method improves zero-shot top- 1 accuracy beyond existing prompt-learning techniques, with a 3.08% improvement over the baseline MaPLe.
  arXiv  Detail & Related papers  (2023-11-02T17:59:32Z)

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.