Inference-Time Scaling

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 180% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 77

Jun 26, 2026cs.LG

VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

Inference-time scaling is a promising paradigm to improve generative models, especially when outputs must satisfy structural constraints or optimize downstream rewards. We consider Masked Diffusion Model (MDM) and introduce MDM-VGB, a discrete diffusion sampler that augments unmasking generation with theoretically principled reward-guided remasking. Inspired by the recent success of the classical Jerrum-Sinclair backtracking Markov chain in reward-tilted generation, MDM-VGB extends the backtracking random walk from a fixed prefix tree to a masked-state graph, allowing tokens to be unmasked and remasked at arbitrary positions. The resulting sampler favors unmasking and remasking moves that lead to higher-value partial configurations, enabling both effective high-reward generation and efficient repair of low-reward samples. We prove that MDM-VGB is robust to process-verifier noise and achieves quadratic complexity, while popular test-time heuristics such as best-of-

N

can incur exponential complexity due to error accumulation. Our theoretical findings are corroborated by strong empirical performance, particularly on popular constraint-satisfaction and scientific benchmarks such as Sudoku and QM9.

Kijung Jeon, Thuy-Duong Vuong, Molei Tao

Georgia Tech · UCSD

Constrained Generative Modeling Masked Diffusion Models Controllable Text Generation Diffusion Sampling Inference-Time Scaling

Jun 22, 2026cs.AI

Active Inference as the Test-Time Scaling Law for Physical AI Agents

In this paper, a novel test-time scaling law for physical artificial intelligence (AI) agents is introduced. This scaling law enables physical AI agents to reason with their world models to generalize in unforeseen scenarios at test time. The derived scaling law is grounded in the first principle of active inference, which equips agents with the general objective to survive in the real world, under which their specific task objectives are subsumed. Active inference achieves this by providing the reasoning to resolve prediction errors that arise when the agent encounters unforeseen situations outside its training distribution, enabling generalization in non-stationary environments. The proposed scaling law captures this by dynamically updating the agent's policy with this reasoning at test time. This policy update is modeled as a soft Bayesian inference process in which beliefs about the policy are updated using the reasoning that reduces expected prediction errors under allowable policies as a likelihood. The resulting posterior policy admits a biological interpretation, recovering the scaling mechanism that engages the brain's basal ganglia and prefrontal cortex at test time. To solve this analytically intractable problem, a variational inference solution minimizing free energy bounds is developed. This solution extends to enable learning beyond training by reinforcing new instances, resolved at test time, in both the policy and world model. Unlike existing scaling laws constrained by model size and training data, the derived solution scales with the continuous real-world experience of a physical AI agent. Simulation results on an autonomous driving task demonstrate that the proposed solution outperforms model-free Q-learning and model-based Bayesian reinforcement learning, achieving robust generalization to unforeseen scenarios while improving inference efficiency by over 36%.

Omar Hashash, Christo Kurisummoottil Thomas, Walid Saad +3

Bradley Department of Electrical and Computer Engineering and the Institute for Advanced Computing, Virginia Tech, Alexandria, VA, USA · Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA · Khalifa University of Science and Technology, Abu Dhabi 127788, United Arab Emirates +4

Active Inference Inference-Time Scaling Robot Policy Generalization

Jun 16, 2026cs.AI

How Inference Compute Shapes Frontier LLM Evaluation

AI evaluations are shifting toward harder tasks that benefit from longer trajectories involving tool use and iterative problem solving. As a result, performance is increasingly sensitive to the amount and allocation of compute available at test time ("inference compute"). Yet many evaluations still report performance at a single restrictive budget, meaning that low scores may reflect the evaluation setup rather than the model's underlying capability. To test this, we evaluate up to 12 frontier language models on seven challenging benchmarks spanning software engineering, mathematics, medicine, and cybersecurity. We use a controlled setup combining three simple inference-scaling interventions: larger token budgets, context compaction, and repeated submission attempts, guided either by the model itself or by minimal correctness feedback. We find three main results. First, larger token budgets substantially improve performance on benchmarks across multiple domains, including cybersecurity, FrontierMath, Humanity's Last Exam, and TerminalBench. Second, fixed-budget evaluations can increasingly understate frontier capability as models advance. Newer models reach higher performance at large budgets, where they unlock harder tasks and solve them more reliably. Third, benchmarks differ in which inference-scaling methods help most: repeated submission broadly improves performance, but the value of larger token budgets, external feedback, and parallel attempts varies by benchmark. Overall, our results show that benchmark scores are protocol-dependent. We therefore argue that evaluations should report capability as a function of inference-time compute, specify protocol choices explicitly, and compare model generations over a large shared compute range at matched budgets, especially in safety- or policy-relevant settings.

Jessica McFadyen, Ole Jorgensen, Harry Coppock +2

AI Security Institute, London, UK · University of Oxford, Oxford, UK · Harvard University, Cambridge, MA, USA

LLM Evaluation Language Model Generation Evaluation LLM Inference Inference-Time Scaling

Jun 15, 2026cs.LG

Entropy-Gated Latent Recursion

Inference-time scaling has become the dominant lever for improving language-model reasoning, but existing methods derive rollout diversity from a single source: stochastic token-level sampling. We argue that this single-axis sampling space is fundamentally limiting, and identify a second, fully deterministic and complementary axis: the layer span

L

at which a frozen model's top decoder layers are recursively re-applied at high-uncertainty tokens. Different choices of

L

produce distinct rollouts that solve different subsets of problems, with no stochasticity. We instantiate this axis through Entropy-Gated Latent Recursion (EGLR), a training-free decoding procedure that re-applies the top-

L

layers for at most

K_{\max}

iterations until the next-token distribution converges. Combined with

T

temperature samples, EGLR turns a single-axis stochastic rollout pool into an

L\times T

Cartesian sampling space at almost the same per-rollout cost. We characterize this space across

8

instruction-tuned models and

6

math reasoning benchmarks, and show that the

L

-axis is genuinely complementary to temperature: on MATH-500 with Qwen2.5-3B-Instruct, the joint

L\times T

oracle reaches

91.6\%

,

+8.2

percentage points beyond the temperature-only oracle (

83.4\%

) and

+10.4

points beyond the layer-only oracle (

81.2\%

), confirming that the two axes capture genuinely complementary problems. The expanded rollout pool provides richer per-prompt candidates for any downstream procedure that consumes rollouts, including self-consistency, best-of-

N

with verifiers, and group-relative RL training (GRPO), opening a new direction for inference-time scaling that does not rely on stochastic noise.

Soham Bhattacharjee, Dushyant Singh Chauhan, Salem Lahlou +2

Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates

LLM Inference Inference-Time Scaling Efficient Language Model Reasoning LLM Reasoning Recursive Language Models

Jun 13, 2026cs.CV

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

Instruction-based image editing has made notable progress with recent advances in generative models. However, the quality of the edited result is still influenced by the randomly sampled initial noise, particularly in complex editing scenarios. An unsuitable initial noise may lead to unsatisfactory editing results. Recent inference-time scaling methods address this issue by sampling multiple initial noises and selecting better candidates. Nevertheless, most of them follow a decode-then-verify scheme which introduces an efficiency-accuracy trade-off. When decoding is performed after limited inference steps, the decoded images often remain too noisy for reliable assessment, whereas sufficiently denoised images require much higher computational cost. To address this issue, we propose VeriLatent, a plug-and-play adaptive inference-time scaling framework with early-step latent verification for image editing. Specifically, we propose a novel verifier that scores each initial noise through a latent-space editing activation map at an early stage. It identifies promising candidates by assessing whether they can induce an effective edit in the correct region. This enables efficient early pruning without decoding latents into images. Building on this, we further develop an adaptive search strategy for inference-time scaling. It allocates inference budgets according to editing difficulty, thereby reducing the number of function evaluations (NFE). Extensive experiments on multiple benchmarks and different base models demonstrate that VeriLatent consistently improves both editing performance and inference-time scaling efficiency.

Yue Yu, Yang Jiao, Jiayu Wang +2

College of Computer Science and Artificial Intelligence, Fudan University, Shanghai 200433, China · Microsoft Research Asia, Beijing 100080, China · Institute of Trustworthy Embodied AI, Fudan University, Shanghai 200433, China

Inference-Time Scaling Diffusion-Based Image Editing Diffusion Model Inference Acceleration

Jun 11, 2026cs.LG

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities -- proof generation, proof verification, and critique-conditioned proof repair -- using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

Jiacheng Chen, Xinyu Zhang, Shunkai Zhang +20

MiniMax · The Chinese University of Hong Kong · Fudan University +2

Automated Theorem Proving Inference-Time Scaling Reinforcement Learning with Verifiable Rewards LLM Mathematical Reasoning

Jun 10, 2026cs.RO

DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?

Vision-Language Models (VLMs) are increasingly deployed as high-level planners for embodied agents, with an emerging strategy of scaling test-time compute to improve capability. However, we observe that doing so increases latency, token usage, and FLOPs while yielding uneven, often diminishing gains in downstream success, limiting where embodied agents can be deployed. We argue that choosing when and where to spend test-time compute is central to bringing frontier performance to the real world. We introduce DIRECT, a routing framework that uses multimodal scene context to allocate compute per prompt, improving the success--cost Pareto frontier over fixed model selection. Across three dominant scaling axes, namely chain-of-thought depth, model size, and memory history, our experiments on VLABench and RoboMME show that test-time compute is not a uniform lever: different axes yield qualitatively distinct capability gains. We validate these insights on a physical Franka arm in a DROID setup spanning zero-shot manipulation and long-horizon chaining, where our router matches or exceeds a stronger model's success rate at up to 65% lower average latency. Ultimately, our results show that naively scaling test-time compute is wasteful, and that DIRECT can provide frontier-level embodied planning in robotic systems at a fraction of the cost. Project page can be found at jadee-dao.github.io/direct/.

Jadelynn Dao, Milan Ganai, Yasmina Abukhadra +7

Stanford University · University of Waterloo · NVIDIA

Test-Time Scaling for VLMs Inference-Time Scaling Inference-Time Compute Allocation VLMs for Robotics

Jun 9, 2026cs.CL

Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation

Large language models (LLMs) rely on tool use to act as autonomous agents, yet often fail in multi-step execution due to insufficient tool-related knowledge and ineffective knowledge activation. Therefore, we present a systematic study on how knowledge influences tool-use performance, covering the stages of knowledge acquisition, activation, and internalization. In the knowledge acquisition stage, we acquire and evaluate various forms of experiential knowledge, and our analysis shows that simple instance-level knowledge can already provide strong and reliable gains, while abstract intent-level knowledge offers limited benefits. At inference time, to activate knowledge, we find that prompting LLM to expand the depth of reasoning yields diminishing returns, whereas expanding the width of reasoning by parallel sampling with aggregation more effectively activates latent experiential knowledge. At training time, for knowledge internalization, post-training with knowledge-augmented data further improves performance, with reinforcement learning outperforming supervised fine-tuning. Based on these insights, we propose the Knowledge-Augmented Tool Execution (KATE), a knowledge-augmented tool execution framework that integrates experiential knowledge with reasoning-width-expanded inference and knowledge-aware training. Experiments on BFCL-V3 and AppWorld demonstrate consistent and substantial improvements over strong baselines across model scales. Our Code is available at https://github.com/hypasd-art/KATE.

Yupu Hao, Zhuoran Jin, Huanxuan Liao +2

1The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

Knowledge Augmentation for Language Models Inference-Time Scaling LLM Tool Use LLM Post-Training

Jun 7, 2026cs.LG

Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability

Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output selection. However, extending ITS to tasks prone to systematic failure - driven by faulty initial assumptions or unmet multidimensional constraints - typically relies on costly external solvers or brittle, model-based verifiers. Our key insight is that the intrinsic statistics of parallel sample sets, specifically length-adjusted tail entropy, provide a robust discriminative signal for solution quality without access to ground truth. Crucially, these statistics serve as a difficulty gate for adaptive compute allocation, dynamically routing problems across scaling regimes. First, Intrinsic Selection (iS) ranks candidates post-hoc, matching consensus-based algorithms across three domains and improving engineering design selection by 20% over pass@1 baselines. Second, Intrinsic Particle Filtering (iPF) generalizes this to step-level resampling, guiding generation toward high-confidence reasoning trajectories to improve pass@1 by 6.1 points on average on hard math problems. Finally, Particle Distillation (dPF) injects privileged guidance via early logit blending and KL-guided resampling, steering generation past systematic reasoning errors to satisfy expert rubrics, yielding up to 26.5% gains on complex clinical responses. Our pipeline applies seamlessly across broad-purpose, domain-specialized, and multimodal architectures, successfully extending ITS to open-ended domains without requiring trained reward models or exact ground-truth verification.

Giorgio Giannone, Mustafa Eyceoz, Shabana Baig +5

AI Innovation, Red Hat · DeCoDE Lab, MIT · Core AI, IBM

Particle Filtering Inference-Time Scaling Inference-Time Compute Allocation Inference-Time Guidance

Jun 7, 2026cs.LG

Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling

Sampling from the sequence-level power distribution

p^α

elicits RL-level reasoning from base language models without any parameter updates, but the standard Metropolis--Hastings (MH), a Markov Chain Monte Carlo (MCMC) sampler, is both expensive and slow-mixing. We trace both to a structural mismatch:

p^α

mainly departs from

p

at a sparse, spatially clustered set of high-entropy decision points, yet MH proposes resampling positions uniformly along the prefix -- wasting compute on near-degenerate conditionals while under-mixing precisely where modes diverge. We propose Entropy-Guided Power Sampling (EGPS), a training-free and verifier-free sampler that re-derives its proposal from token-level entropy already in the forward pass. EGPS skips deterministic blocks, localizes each MCMC move to a high-entropy neighborhood, and applies Multiple-Try Metropolis at decision points -- making sampling cost scale with \emph{entropy mass rather than sequence length}. On Qwen2.5-Math-7B, EGPS reaches best or tied-best accuracy on all three benchmarks (MATH500

75.8\%

, HumanEval

62.2\%

, GPQA

42.4\%

) at up to a

12.6\times

wall-clock speedup over the MH baseline.

Hong Guo, Nianhui Guo, Christoph Meinel +1

Hasso Plattner Institut · German University of Digital Science

Markov Chain Monte Carlo Inference-Time Scaling Efficient Language Model Reasoning LLM Inference Acceleration Adaptive Sampling

Jun 3, 2026cs.LG

Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers

End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for improved recognition without training a larger model. A natural approach is to reuse a shared Transformer block recurrently, but we find that naive looping does not fully exploit additional recurrent compute. We introduce LARM, a depth-conditioned looped Transformer that turns recurrent encoder depth into a controllable test-time compute axis. LARM combines sparse CTC checkpoints, supervision-clock embeddings, FiLM depth conditioning, and delayed soft-posterior feedback. These components structure the loop into recognition checkpoints separated by latent refinement phases and allow shared weights to specialize across recurrent steps. On LibriSpeech, LARM improves WER as the number of inference loops increases and achieves performance competitive with deeper unshared-parameter baselines. Our results show that test-time compute scaling can extend beyond autoregressive language-model reasoning to continuous non-autoregressive speech recognition.

Yacouba Kaloga, Shashi Kumar, Shakeel A. Sheikh +3

Idiap Research Institute, Switzerland · EPFL, Switzerland · BUT, Czech Republic

Inference-Time Scaling Test-Time Scaling Automatic Speech Recognition Recurrent Transformers

Jun 2, 2026cs.MM

Inference-Time Scaling for Joint Audio-Video Generation

Joint audio-video generation aims to synthesize realistic audio-video pairs that are both semantically aligned with text prompts and precisely synchronized. While existing joint audio-video generation models often require substantial training resources to improve fidelity, Inference-Time Scaling (ITS) has recently emerged as a promising training-free alternative in single-modality domains. However, extending ITS from a single modality to multimodal domains is non-trivial, as it requires balancing multiple heterogeneous objectives. In this paper, we present the first comprehensive study of ITS for joint audio-video generation. We first demonstrate that a multi-verifier framework is essential to address the limitations of single-objective guidance, including asymmetric performance trade-offs and verifier hacking. Through systematic analysis, we then identify an optimal multi-verifier combination that yields balanced improvements across all quality dimensions. Finally, to effectively aggregate diverse reward signals, we propose Adaptive Reward Weighting (ARW), a novel test-time optimization algorithm. ARW treats reward aggregation as an online optimization problem, utilizing learnable parameters to calibrate reward variances without requiring prior knowledge of reward distributions, thereby ensuring robust multi-objective selection. Experimental results on VGGSound and JavisBench-mini benchmarks demonstrate that our framework significantly enhances semantic alignment, perceptual quality, and audio-visual synchronization of generated outputs. Synthesized samples and code are available on the project page: https://jung-jaemin.github.io/ITS-AVGen-Proj.

Jaemin Jung, Kyeongha Rho, Inkyu Shin +1

Korea Advanced Institute of Science and Technology · Luma AI

Audio-Video Generation Inference-Time Scaling Audio-Visual Synchronization Audio-Visual Alignment Multi-Objective Optimization

Jun 2, 2026cs.AI

The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs

Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global shadow price that equilibrates marginal utility under resource scarcity. Based on this theory, we propose Constrained Latent-utility Equilibrium Allocation for Reasoning (CLEAR). It performs rational abandonment and reallocates resources from insolvent queries to solvable queries near their emergence thresholds. Extensive experiments on several reasoning tasks with different traffic streams demonstrate that CLEAR significantly improves the Pareto frontier of total token cost versus mean accuracy. In resource-scarce regimes, CLEAR achieves up to a 3x improvement in global accuracy compared to uniform allocation.

Xu Wan, Speed Zhu, Jianwei Cai +4

1Zhejiang University · 2Tecent HY Team · 3Peking University

Cost-Aware Inference Inference-Time Scaling Constrained Optimization Inference-Time Compute Allocation

Jun 2, 2026cs.CL

Predicting Inference-Time Scaling Gains from Labeled Validation-Set Output Statistics

Best-of-

N

inference scaling (drawing

N

candidate answers from a language model and returning the one a reward model ranks highest) improves accuracy by an amount that varies across models, but predicting that amount in advance currently requires running the procedure end-to-end. Prior work links cheap statistics of a model's sampled outputs and validation-set correctness (how often samples agree, how diverse they are, how confident the model is, and where correct samples appear) to model behavior, but does not isolate which of these form a stable, compact predictor of best-of-

N

gain. We fit ridge predictors on features computed from a single labeled validation-set sampling pass, use bootstrap-Lasso as a stability analysis of the candidate feature set, and give a concentration analysis with an explicit linear-approximation residual. Across three base-model families, six post-training methods, and math and reasoning task domains, the stability analysis identifies a strict three-feature core spanning prompt-level agreement spread, label-assisted first-correct-sample position, and completion-length variance; a compact ridge predictor built from this core plus an entropy add-on reaches Spearman

ρ= 0.90

with actual best-of-

N

gain under a reward-model verifier. The intended use is labeled validation-set screening of candidate configurations before paying the full reward-model scoring cost.

Luyang Zhang, Jingyan Li

Carnegie Mellon University · Johns Hopkins University

LLM Evaluation Inference-Time Scaling Best-of-N Sampling

May 30, 2026cs.LG

Score $\times$ Decoder: A Unified View of Unsupervised Inference-Time Scaling for Hallucination Mitigation

Large language models hallucinate even when the answer lies within their parameters. While inference-time scaling can surface this latent knowledge, the most effective methods require supervision: a trained verifier or reward model. We ask what can be done with only a base language model: which intrinsic signal best identifies correct outputs, and how should it be decoded? We cast this as a score~

\times

~decoder grid pairing four scores (perplexity, contrastive, power-distribution likelihood, and self-verification) with three decoding families (optimization, sampling, consensus), and evaluate every cell on MATH500 with the base and instruction-tuned Qwen3-1.7B. While self-verification, which prompts the model to judge its own answer and is sharpened by a training-free virtual-thinking prefix, works well in most settings, no score has a fixed quality: its value depends on the decoder that consumes it and on model capability. When no supervision is available, the score and the decoding family must be chosen together.

Yun-Chen Cheng, Che-Yu Lin, Cheng-Lin Yang

CyCraft AI Lab, Taiwan

Language Model Decoding LLM Hallucination Mitigation Inference-Time Scaling LLM Reliability

May 29, 2026cs.AI

UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling

In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing approaches tackle this trade-off along two largely independent dimensions: model routing, which switches among models of different scales to match request complexity, and test-time scaling (TTS), which adjusts inference-time compute within a fixed model for fine-grained control. However, this decoupled design introduces inherent limitations. Model routing yields coarse-grained, discrete performance changes due to the sparse set of model scales, while single-model TTS often encounters capacity ceilings and exhibits diminishing returns as compute increases. Moreover, treating the two mechanisms separately restricts adaptability in dynamic inference environments. To overcome these limitations, we introduce Unified Inference Scaling (UIS), which unifies model routing and TTS in a single optimization space. Building on this formulation, we propose UniScale, an online framework that models adaptive UIS as a contextual multi-armed bandit problem and learns inference policies via LinUCB. The framework incorporates efficiency-aware learning and cost modeling to ensure stable and scalable optimization over high-dimensional action spaces. Evaluation shows that UniScale effectively exploits the synergy in the UIS space to deliver a fine-grained and consistently better quality-cost trade-off across diverse, dynamic inference scenarios.

Kaiyu Huang, Xingyu Wang, Mingze Kong +6

School of Computer Science and Technology, Tongji University · Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen · School of Data Science, The Chinese University of Hong Kong, Shenzhen +2

Cost-Aware Inference Inference-Time Scaling LLM Routing

May 28, 2026cs.CL

Scaling Laws for Agent Harnesses via Effective Feedback Compute

Agent harnesses shape language-model performance by controlling tool use, feedback, verification, memory, and repair. Yet raw test-time expenditure, such as tokens, tool calls, wall time, or cost, cannot distinguish useful feedback from redundant or unstable interaction. We introduce \emph{Effective Feedback Compute} (EFC), a trace-level scaling coordinate for informative, valid, non-redundant, and retained feedback. We further define Estimated-EFC, NRS-EFC, harness efficiency

η

, and task-demand normalization for realistic traces and heterogeneous tasks. Across synthetic, real, held-out, and prospective evaluations, EFC-based coordinates outperform raw-compute baselines and SAS. Oracle-EFC/

D_{\mathrm{task}}

reaches

R^2=0.99

in controlled scaling, and NRS-EFC/

D_{\mathrm{task}}

reaches

R^2=0.93

on real traces where raw compute has near-zero or negative fit. Finally, \ours uses EFC as a companion control layer for existing harnesses, improving mean pass rate from

61.2\%

to

68.2\%

while reducing mean raw cost from

213.8

to

85.1

under matched settings. These results suggest that harness scaling depends on durable, task-sufficient feedback rather than raw computation alone.

Xuanliang Zhang, Dingzirui Wang, Keyan Xu +2

Harbin Institute of Technology

Inference-Time Scaling Agent Harness Optimization Tool-Using Agents LLM Agent Reliability

May 27, 2026cs.LG

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL

Linear interpolation between fine-tuned checkpoints has been shown to trace the Pareto front between competing objectives, but whether extrapolative weight averaging can extend such frontiers to new checkpoints useful at inference time, without additional RL training, remains unclear. We study this question in RL for competitive programming, where hidden unit tests under time and memory limits enforce both functional correctness and computational efficiency. Starting from a shared initialization, we train checkpoints under nested unit-test coverage: low-coverage rewards require passing smaller-input tests, while high-coverage rewards require passing progressively larger tests up to the full suite. This sweep reveals the emergence of a correctness-efficiency frontier: on hard problems, higher-coverage reward reduces optimization failures but increases correctness failures, leaving solve rate nearly unchanged. Interpolation between low- and high-coverage checkpoints recovers this frontier, while extrapolation extends it beyond the trained endpoints. Both the frontier and its extrapolative continuation appear across three inference settings, pure reasoning, tool use, and agentic coding, and across two model scales, 32B and 7B. At the problem level, moving along the frontier changes which problems are solved, making extrapolated checkpoints complementary policies in inference-time scaling. Ensembles with extrapolative weight averaging broaden coverage and improve pass@250 on LCB/hard by 3.3% over the best single checkpoint at matched sample budget. These results show that nested unit-test coverage in code RL induces a frontier that extrapolative weight averaging can navigate, extend, and exploit.

Kunhao Zheng, Pierre Chambon, Juliette Decugis +4

Meta Superintelligence Labs - FAIR · Université Paris-Dauphine PSL

Multi-Objective Reinforcement Learning RL for Code Generation Inference-Time Scaling Reinforcement Learning with Verifiable Rewards

May 24, 2026cs.AI

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling

Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories. The key challenge is to maximize accuracy while minimizing the total number of generated tokens during reasoning. Recent PRM-guided methods score intermediate prefixes to steer this search, but most are frontier-only: they keep only the current active prefixes and irreversibly prune or resample away the rest using noisy PRM scores. This can cause premature commitment, diversity collapse, and the loss of prefixes that still admit correct continuations. We introduce stochastic backtracking over a persistent pool of historical prefixes, allowing test-time compute to revisit previously generated states instead of only expanding the current frontier. To make this efficient, we propose two complementary mechanisms. Subpool Selection strengthens greedy PRM-guided search by applying Top-N selection within random subpools, giving historical prefixes a chance to bypass over-scored frontier candidates. Power Backtrack Sequential Monte Carlo extends SMC-style resampling to the persistent pool using powered PRM scores and mixture-corrected weights. Across mathematical reasoning benchmarks and model scales, our methods consistently achieve higher accuracy per token count, and the same level of accuracy using only a fraction of the token count in comparison to strong PRM-guided baselines, demonstrating that persistent-pool stochastic backtracking provides a simple and effective way to improve the accuracy-token trade-off in test-time scaling.

Dao Tran, Duc Anh Le, Ngoc Luu +3

Qualcomm AI Research†

Inference-Time Scaling Efficient Language Model Reasoning

May 21, 2026cs.CL

RAS: Reflection-Augmented Scaling with In-Context Learning for Executable Cypher Query Generation

Inference-time scaling can reduce errors in structured query generation, but methods to allocate the compute for query code generation remains underexplored. We study Text2Cypher, where language models generate Cypher queries that execute against property graph databases. Non-executable queries constitute a distinct syntactic failure separate from semantic inaccuracy: a syntax error triggers a system-generated error message from the database. These error messages are typically discarded at inference time rather than leveraged through in-context learning (ICL). We compare two inference methods: Independent Scaling (IS), which performs memoryless resampling, and Reflection-Augmented Scaling (RAS), which conditions each new attempt on prior execution feedback via ICL. Across three Neo4j datasets and five code-specialized language models, RAS reduces the Query Execution Error Rate by 41--50% at n{=}5, outperforming IS at 32--38%. Execution errors are not merely failures to discard but actionable feedback, and structuring inference-time compute around them is a more efficient path to executability than scaling independent samples.

Minseok Jung, Abhas Ricky, Muhammad Rameez Chatni

Cloudera 6220 America Center Dr. San Jose, CA 95002

Execution-Guided Code Generation Inference-Time Scaling Text-to-Cypher In-Context Learning Text Generation

May 19, 2026cs.LG

Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement

Inference-time scaling has emerged as a major approach for improving reasoning capabilities, and has been increasingly applied to diffusion models. However, existing inference-time scaling methods for diffusion models typically rely on external verifiers or reward models to rank and select samples, limiting their scalability to settings where such evaluators are available and reliable. Moreover, while recent diffusion models perform sequential inference with region-wise, mixed-noise conditioning, inference-time scaling tailored to this setting remains relatively underexplored. We propose Iterative Partial Refinement (IPR), an inference-time scaling method for sequential diffusion that requires no external verifier. Starting from an already-generated sample, IPR re-noises a subset of regions and regenerates them conditioned on the remaining regions, enabling the model to revise earlier decisions under a richer context than was available during the initial generation. This iterative partial refinement produces more globally consistent samples without external verification. On reasoning tasks requiring global constraint satisfaction, IPR consistently improves performance: on MNIST Sudoku, the valid solution rate increases from 55.8% to 75.0%. These results show that iterative partial refinement alone can serve as an effective inference-time scaling strategy for diffusion models in sequential, mixed-noise settings. Code is available at: https://github.com/ahn-ml/IPR

Taegu Kang, Jaesik Yoon, Sungjin Ahn

KAIST · KAIST & SAP · KAIST & NYU

Inference-Time Scaling Diffusion Models

May 18, 2026stat.ML

Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures

iffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific objectives. However, most existing techniques require repeated score or gradient evaluations, introducing bias, high computational overhead, or both. We introduce \texttt{URGE}, Unbiased Resampling via Girsanov Estimation, a derivative-free inference-time scaling algorithm that performs path-wise importance reweighting via a Girsanov change of measure. Instead of computing gradient-based particle weights in previous work, \texttt{URGE} attaches a simple multiplicative weight to each simulated trajectory and periodically resamples. No score, no Hessian, and no PDE evaluation is required. We establish an equivalence between path-wise and particle-wise SMC: the Girsanov path weight admits a backward conditional expectation that recovers the previous particle-level weights, guaranteeing that both schemes produce the same unbiased terminal law. Empirically, \texttt{URGE} outperforms existing inference-time guidance baselines on synthetic tests and diffusion-model benchmarks, achieving better generation quality, while being significantly simpler to implement and fully gradient-free.

Chenyang Wang, Weizhong Wang, Yinuo Ren +2

School of Mathematical Sciences, Peking University, Beijing, China · School of Mathematical Sciences, Fudan University, Shanghai, China · Institute for Computational & Mathematical Engineering, Stanford University, Stanford, CA, United States +2

Diffusion Model Guidance Importance Sampling Inference-Time Scaling

May 17, 2026cs.LG

Drift Flow Matching

Iterative generative models such as Flow Matching and Diffusion models have demonstrated strong test-time scaling behavior, where additional inference computation can improve generation quality. In contrast, Drift Models offer efficient one-step generation, but their direct generation paradigm limits such flexibility. In this work, we propose Drift Flow Matching (DFM), a framework that connects drifting generative modeling with flow-based iterative generation. DFM preserves the efficiency of direct transport maps while enabling generation to be refined through multiple inference steps when desired. This bridges the gap between one-step Drift Models and multi-step Flow Matching methods, and provides a novel generative paradigm that can adapt sampling computation to different quality--efficiency requirements. Extensive experiments across different tasks and datasets demonstrate the effectiveness and generality of the proposed framework.

Chenrui Ma, Xi Xiao, Lin Zhao +3

University of California, Irvine · University of Virginia · University of Alabama at Birmingham +1

Flow Matching Inference-Time Scaling One-Step Generative Modeling Flow-Based Generative Modeling Drifting Models

May 16, 2026cs.CL

Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models

Large Reasoning Models (LRMs) generate chain-of-thought traces whose length tracks human reaction times across cognitive tasks, but recent debate questions whether this alignment reflects genuine computational structure or surface verbosity. We test whether the alignment varies with inference-time reasoning effort. Across GPT-OSS-20B and GPT-OSS-120B, three effort levels, and six reasoning tasks, within-task and cross-task alignment remain invariant: Bayes Factors lean toward the null, and mean alignment is numerically near-identical across conditions. A manipulation check reveals that the effort parameter sets an upper budget on generation rather than driving real-time allocation, suggesting that the allocation policy is crystallized at training time. Arithmetic complexity contrasts further show that token allocation tracks fine-grained, format-dependent human difficulty patterns, with model scale improving the match. Cognitive cost alignment between LRMs and humans appears to be a training-time achievement, robust to inference-time perturbations, supporting a compiled rather than online account of LRM problem-solving.

Yueqing Hu, Tianhong Wang

Institute of Neuroscience, Chinese Academy of Sciences, Shanghai, China · School of Philosophy, Anhui University, Hefei, China

Computational Cognitive Modeling Inference-Time Scaling Inference-Time Language Model Alignment Large Reasoning Models

May 14, 2026cs.AI

Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling

Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling faces challenges in trade-off between sampling budget and reasoning quality. Current strategies remain inefficient as they typically treat sampling width and depth as orthogonal objectives, where width consensus methods risk reinforcing hallucinations, while depth pruning mechanisms prematurely truncate complex yet valid reasoning chains. Therefore, we propose Dual-Dimensional Consistency (DDC), a unified framework that bridges path quality with adaptive termination. By coupling Confidence-Weighted Bayesian protocol with a Trend-Aware Stratified Pruning, our method ensures that computational resources are concentrated on high quality reasoning paths, filtering hallucinations while accelerating consensus. Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.

Rongman Xu, Yifei Li, Tianzhe Zhao +3

Xi’an Jiaotong University

Inference-Time Scaling LLM Inference Acceleration

May 13, 2026cs.AI

Inference-Time Amplification of Weak Reasoning Models

How much of the capability of a reasoning model exposed by repeated sampling can an imperfect selector recover? We study this problem as {\em inference-time amplification}, separating {\em coverage}---whether a useful candidate is generated---from {\em identifiability}---whether it can be recognized among the alternatives. We show that better coverage alone does not guarantee better selection, while even imperfect local selection signals can be amplified through repetition. We also characterize proposal-side blind spots that additional sampling cannot overcome. On SWE-bench Verified, a single GPT-5.4 nano trajectory solves 67.0% of tasks, while eight proposals contain a correct patch on 79.0%; critic--comparator selection reaches 76.4%, recovering 78.3% of the oracle-exposed gain. The same pattern appears across proposer families and in mathematical reasoning, competitive programming, and formal proof. On MATH L4--5 and GSM-Plus, our selector recovers 85% and 77% of the oracle gap and substantially outperforms majority vote. Holding proposal coverage fixed, providing the selector with additional repository information also improves recovery. Conversely, when the available selection signal is weak, redundant, or misaligned, amplification can diminish or fail. These results identify selection quality as the key factor governing how much capability exposed by repeated sampling can actually be recovered.

Varun Sunkaraneni, Pierfrancesco Beneventano, Riccardo Neumarker +2

MIT

Inference-Time Scaling LLM Reasoning

May 13, 2026cs.LG

TabPFN-3: Technical Report

Tabular data underpins most high-value prediction problems in science and industry, and TabPFN has driven the foundation model revolution for this modality. Designed with feedback from our users, TabPFN-3 builds on this foundation to scale state-of-the-art performance to datasets with 1M training rows and substantially reduce training and inference time. Pretrained exclusively on synthetic data from our prior, TabPFN-3 dramatically pushes the frontier of tabular prediction and brings substantial gains on time series, relational, and tabular-text data. On the standard tabular benchmark TabArena, a forward pass of TabPFN-3 outperforms all other models, including tuned and ensembled baselines, by a significant margin, and pareto-dominates the speed/performance frontier. On more diverse datasets, TabPFN-3 ranks first on datasets with many classes, and beats 8-hour-tuned gradient-boosted-tree baselines on datasets up to 1M training rows and 200 features. TabPFN-3 introduces test-time compute scaling to tabular foundation models. Our API offering TabPFN-3-Plus (Thinking) exploits this to beat all non-TabPFN models by over 200 Elo on TabArena, rising to 420 Elo on the largest data subset, and outperforms AutoGluon 1.5 extreme while being 10x faster, without using LLMs, real data, internet search or any other model besides TabPFN. TabPFN-3 extends the capabilities of our models, enabling SOTA prediction on relational data (new SOTA foundation model on RelBenchV1) and tabular-text data (SOTA on TabSTAR via TabPFN-3-Plus); and improves existing integrations: a specialized checkpoint, TabPFN-TS-3, ranks 2nd on the time-series benchmark fev-bench, and SHAP-value computation is up to 120x faster. TabPFN-3 achieves this performance while being up to 20x faster than TabPFN-2.5. In addition, a reduced KV cache and row-chunking scale to 1M rows on one H100 with fast inference speed.

Léo Grinsztajn, Klemens Flöge, Oscar Key +38

Tabular Foundation Models Efficient Neural Network Inference Inference-Time Scaling Tabular ICL Tabular Prediction

May 10, 2026cs.RO

Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning

Despite rapid progress in Vision-Language-Action (VLA) models for robotic control, instruction drift remains a persistent failure mode in long-horizon tasks. This paper reconceptualizes this phenomenon, positing that instruction drift is fundamentally a systematic sampling error: local greedy sampling is prone to collapsing into "Negative Pivotal Windows"--irreversible local optima with high local probability that sever global success pathways. To address this, we propose Context-Aware Power Sampling (CAPS), a training-free inference-time computation framework. CAPS leverages power distributions to sharpen global trajectory probabilities, enabling lookahead search over the model's conditional generative trajectory distribution. Furthermore, we introduce a metacognitive control mechanism based on Signal-to-Noise Ratio (SNR). This mechanism triggers adaptive MCMC search solely when drift risk is detected, enabling a dynamic transition from "intuitive fast thinking" to "rational slow search." Experiments on RoboTwin, Simpler-WindowX, and Libero-long benchmarks show that CAPS achieves substantial improvements over strong baselines, including OpenVLA and TACO, without parameter updates. These results support the effectiveness of adaptive inference-time computation for improving long-horizon robustness in embodied control.

Kewei Chen, Yayu Long, Mingsheng Shang

Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences · Chongqing School, University of Chinese Academy of Sciences

Robotic Control Inference-Time Scaling Robot Task Planning VLMs for Robotics

May 9, 2026cs.LG

Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching

SKETCHVERIFY is a within-tier cost-performance policy, not a universal accuracy improvement. The operational question: a practitioner stuck with a small, cheap code model (here, Gemini 3.1 Flash Lite) for latency, deployment, or budget reasons -- how should they spend a small amount of extra test-time compute? SKETCHVERIFY factorizes the search space: the LLM enumerates K distinct algorithmic strategies, writes a program sketch for each (a partial program with ?? holes), and fills each sketch M times, producing K x M structurally diverse candidates that are verified by execution and selected by fingerprint clustering. Each extra sketch is guaranteed to explore a different algorithm; each extra flat sample likely duplicates an existing one. Our central evidence is a cost-quality Pareto plot on HumanEval+ across three Gemini tiers (Lite, Flash, Pro), and a reanalysis of the 19 problems where Lite greedy fails. Two findings: (1) Within-tier, sketching dominates flat sampling at matched candidate count. On the hard subset, Lite Sketch K=2, M=5 recovers 11/19 (58%) vs. flat N=10 at 5/19 (26%, +32pp); Lite Sketch K=10, M=10 recovers 15/19 (79%) vs. flat N=100 at 10/19 (53%, +26pp). Flat cannot close the gap even at ~3x the budget: flat N=50 still loses to Sketch K=2, M=5 by +11pp. (2) Cross-tier, sketching does not replace upgrading. Pro greedy (89%) dominates Lite Sketch K=10, M=10 (79%) on both pass@1 and dollar cost. Practitioner rule: if a stronger tier is available, use greedy on it; otherwise sketching is the cost-effective way to spend extra compute. We characterize the K-vs-M trade-off via a Flash Lite scaling sweep, report HumanEval+ saturation on Flash and Pro, and show the method composes cleanly with execution-based selection from the concurrent Semantic Voting line of work.

Shan Jiang, Zijian Yi, Chenguang Zhu

The University of Texas at Austin

LLM Inference Efficiency Test-Time Optimization Code Generation Inference-Time Scaling

May 8, 2026cs.AI

VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection

A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most common answer is selected. More recently, it has been shown that weighted majority voting (e.g. Confidence-Informed Self Consistency (CISC)), which assigns a confidence value to each candidate answer and chooses the answer with the largest accumulated score, tends to be more accurate on a wide range of popular benchmarks. In practice, weighted majority voting necessitates calling a critic LLM on each candidate's reasoning trace to produce the answer's confidence score. This secondary series of LLM calls greatly increases the overhead and cost of weighted majority voting, despite its potential performance benefits. To reduce this expense, we propose VecCISC, a lightweight, adaptive framework that uses a measure of semantic similarity to filter reasoning traces that are semantically equivalent to others, degenerate, or hallucinated, thus decreasing the number of candidate answers that must be evaluated by the critic. To ensure adequate experimental thoroughness, we evaluate VecCISC on five challenging, widely-adopted datasets spanning the domains of mathematics, chemistry, biology, commonsense reasoning, and the humanities. Our results demonstrate that VecCISC reduces the total token usage by 47%, while maintaining or exceeding the accuracy of CISC.

James Petullo, Sonny George, Dylan Cashman +1

Computer Science Department, Brandeis University

LLM Inference Efficiency Inference-Time Scaling LLM Reasoning Reasoning Trace Analysis Majority Voting