The first compute-normalised comparison of five TTS families across five open-ended generation benchmarks spanning medicine, law, finance, general chat, and creative writing is conducted - grounded in a unified framework that decomposes the effectiveness of each method's token budget into exploration and exploitation.
Abstract
Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over partial sequences, or iteratively refining drafts. These techniques yield large gains on mathematics and code, but have been developed and stress-tested almost exclusively on tasks where verification is straightforward. We conduct the first compute-normalised comparison of five TTS families across five open-ended generation benchmarks spanning medicine, law, finance, general chat, and creative writing - grounded in a unified framework that decomposes the effectiveness of each method's token budget into exploration and exploitation. The answer depends on which side of that decomposition you examine. Scaling exploration works: the best candidate in the pool improves steadily with compute across all settings. What breaks is exploitation - the step that converts a rich candidate pool into a final output. With state-of-the-art generators, reward models correlate at only $\rho_v \approx 0.12$ with true quality, rendering selection near-random regardless of budget. Tree search amplifies this failure through diversity collapse. Refinement helps on one of five benchmarks; its apparent gains elsewhere are confounded. Only synthesis across candidates (Fusion) consistently improves over single-sample baselines, yet still recovers only ~40% of available quality. The candidate pool is not the bottleneck - choosing from it is.
Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it. We formalize test-time reasoning as a constrained compute allocation problem over partial trajectories. Under a fixed hardware budget, existing paradigms fail to actively allocate the compute to the most promising partial progress: traditional parallel sampling treats traces independently and induces severe memory bottlenecks, while subtractive pruning starves hardware and fails to actively and sufficiently shift the output distribution. To overcome this dichotomy, we introduce Gambit, an inference algorithm that executes \emph{thought-level beam search}. By periodically pruning unpromising trajectories and immediately branching from high-quality prefixes, Gambit dynamically concentrates compute onto the most promising reasoning traces via a light-weight scorer probing hidden states while maintaining continuous high hardware utilization. Extensive evaluations across multiple models and benchmarks demonstrate that Gambit strictly dominates existing baselines. Under identical hardware constraints, our method yields up to a +6.7\% absolute accuracy gain on HMMT-24 and +3.3\% on AIME-25 over pruning baselines, delivers $>2\times$ higher throughput on trace completion, and reduces total token consumption by up to 68.5\% relative to standard parallel sampling.
Lijie Yang, Hongyin Luo, Tri Dao et al.· 0 citations
This project explores the Countdown arithmetic reasoning task: given a set of numbers, produce an arithmetic expression that evaluates to a target value on the Qwen 2.5-0.5B base model and proposes two complementary extensions targeting these failure modes.
Test-time compute can substantially improve Large Language Model (LLM) reasoning performance, yet how and when additional compute helps remains poorly understood. We study Divergent-Convergent Reasoning (DCR), a simple two-phase primitive consisting of an exploration phase that generates multiple candidate solutions followed by a convergent reconciliation phase. We present three core results. First, we show that even a single reconciliation step can reliably amplify correct minority reports: across datasets, DCR often recovers the correct answer when correct exploration outputs are in the minority, a regime where majority voting fails. Second, we introduce recursive DCR, an autoregressive reconciliation system that iteratively analyzes disagreements and allocates additional test-time compute. Recursive DCR achieves higher accuracy than fixed-compute baselines-reaching 93.3% on AIME 2024 and 92.0% on AIME 2025-while using roughly 27% less compute on average, demonstrating that attentive resource allocation is superior to uniform scaling. Third, we analyze disagreement among exploration outputs via a simple, training-free dispersion metric. Dispersion reveals a structured relationship between disagreement and test-time gains: in regimes where DCR is effective, higher disagreement among exploration outputs is associated with larger accuracy improvements from reconciliation. Together, these results show that disagreement, often viewed as noise, can be systematically exploited to improve test-time reasoning and reveal emerging scaling laws for agentic LLM systems.
Large language models can solve substantially harder reasoning problems with more inference-time compute. The term"test-time scaling,"however, now covers diverse inference algorithms that extend deliberation along a single trajectory, sample completed candidates and aggregate them through voting or verification, or search over unfinished partial states. These algorithms differ in their statistical structure, compute accounting, and failure modes. Treating these procedures as interchangeable under a single scalar"budget,"or reporting accuracy without the inference protocol that produced it, makes results difficult to compare across studies. We develop a systematic account of test-time scaling along three axes. First, we formalize test-time scaling as budgeted inference over the implicit prefix tree of an autoregressive model and distinguish three structural regimes: single-trajectory sequential scaling, leaf-level scaling with terminal reduction, and prefix-level scaling. Second, we treat the evaluated object as the entire inference system and develop evaluation principles that separate end-to-end system performance from candidate-bank diagnostics. We introduce an evaluation profile whose coordinates and simple functionals recover or bound common repeated-sampling metrics, and prescribe protocol-matched reporting of compute and uncertainty. Third, we specify reproducibility requirements for inference protocols, distinguishing exact replay from distributional reproducibility and identifying the artifacts needed to support each. We also organize the open-weight reasoning ecosystem by model-side and interface mechanisms, apply these principles to broad-knowledge, symbolic-reasoning, and competition-mathematics benchmarks, and assemble over 2 billion full reasoning traces for release with progressively richer verifier and token-level signals.
Mohsen Hariri, Weicong Chen, Nahal Shahini et al.· 4 citations
This work proposes that AI feedback is most effective when decomposed into granular, prompt-specific checklists, and introduces DIVA: DIscriminative VAriance weighting, a dynamic aggregation scheme that prioritises checklist items based on their ability to distinguish quality across a candidate pool.
Jonathan Cook, Tim Rocktäschel, Jakob N. Foerster et al.· Annual Meeting of the Associ...· 0 citations
This work introduces Test-Time Scaling via Error Localization (TTEL), an inference-time algorithm that utilizes fixed or environment feedback to perform token-level error localization and establishes strictly dominating Pareto frontiers across sequential reasoning domains.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
