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

Oct 7, 2026cs.CL

The Long Road to the Same Answer: Cognitive Bias Under Escalating Reasoning Budgets in Large Language Models

Reasoning models allocate extra computation at inference time and present their answers as the product of deliberate thought. If this deliberation works the way dual-process accounts of human cognition suggest, longer thinking should weaken the classic decision biases that fast, intuitive judgment produces. Using 30 vignettes covering six biases (anchoring, framing, loss aversion, escalation of commitment, availability, confirmation) from an established benchmark, we run a dose-response study across four model families, pairing each reasoning model with a matched non-reasoning sibling and requesting thinking ceilings of 0, 1,024, 4,096, and 8,192 tokens, for 12,350 API calls. Because a requested ceiling is not the same as realized deliberation, we use the reasoning tokens each call consumed as the dose. First, reasoning models are not less biased than their siblings; the point estimate leans the other way in every family, but the item-level pooled contrast is not reliable (Delta = +0.031, t(29) = 1.45, p = .157). Second, bias magnitude does not reliably fall as realized deliberation grows: no slope is significantly negative, and where anything moves it is the signed score drifting further from the human direction. Third, anchoring is the only bias in the human direction (d = 1.89). Four of the other five lean the opposite way in all seven models; with five items per bias, that reversal is reliable for framing and directional for escalation of commitment, confirmation, and loss aversion, while availability is absent. A one-line instruction to restate the anchor before answering lowered anchoring on all five anchoring items, which no amount of additional thinking did, although the effect does not reach significance (p = .057). The results argue against treating test-time reasoning as a rationality guarantee and for auditing deployed models bias by bias.

Obada Kraishan

College of Media and Communication Texas Tech University Lubbock, TX, USA

Large Reasoning Models Language Model Bias Evaluation Inference-Time Scaling

Oct 4, 2026cs.LG

Expanding LLM Reasoning

Extra inference compute is usually spent on sampling more reasoning chains. We study where inside an existing chain an additional continuation should begin. We define expansion utility, the change in correctness from restarting a chain at a stored step, and measure it at every eligible step for nine models on six benchmarks (41 model and benchmark cells). Restart position matters: steps selected on one set of continuations beat uniform placement when scored on disjoint ones, in held-out audits on 5, 16, and 38 cells (+4.25 points [+2.51, +6.63] in a fresh five-cell audit). A fixed rule that restarts from the last eligible steps, always-last, is a strong baseline: our learned router beats uniform placement but shows no detected gain over it, and on DeepSeek-R1-Distill-Qwen-14B/MATH-500 always-last exceeds the exact self-consistency frontier at matched aggregate generated output by +0.052 [+0.008, +0.098], using 0.774x the aggregate generated output of four-sample self-consistency. Cross-fitted oracle selection still finds held-out headroom beyond declared positional classes, a target for future selectors. Finally, breaking step-label ties by earliest index flips the sign of a pointwise selector's gain over uniform placement in every seed of a five-seed diagnostic with four rollouts per step; randomized ties remove the bias.

Rian Atri, Evan Luo

Keiji AI · University of California, Berkeley

LLM Inference Efficiency Inference-Time Scaling Efficient Language Model Reasoning Inference-Time Compute Allocation LLM Reasoning

Oct 4, 2026cs.LG

When Does Longer Reasoning Help? Predicting Mathematical Reasoning Through Discovery and Execution

Test-time compute can improve mathematical reasoning, but can short-budget runs predict how mathematical reasoning scales with additional compute? We introduce a Discovery--Execution (DE) framework that predicts the aggregate held-out scaling curves through a convolution of strategy discovery and conditional execution. From independent short-budget attempts and oracle-sketch-conditioned runs, the framework estimates cumulative success along held-out reasoning trajectories under alternate compute allocations. We evaluate four models on 35 fresh Olympiad problems and non-geometry problems from IMO-ProofBench Advanced. Under the DE framework, near-saturated execution predicts geometric scaling, as observed for the GPT models. For Claude Opus 4.8, incorporating measured execution substantially improves held-out forecasts over geometric extrapolation across one- and two-arm allocations. As a secondary application, regularized DE (R-DE) decisions to continue or restart yield lower average regret than the best model-specific retrospective policy. Together, these results show that measuring conditional execution provides information about longer reasoning that short-budget success rates do not always capture.

Adib Hasan, Lay Jain, Thanic Nur Samin

Independent Researcher · IU Bloomington

Inference-Time Scaling LLM Mathematical Reasoning

Oct 1, 2026stat.ML

Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models

Inference-time scaling adapts pretrained diffusion models to new sampling tasks without additional training. Existing methods rely primarily on Monte Carlo sampling with more particles, yet are premised on the pretrained model being exact. In practice, data and training limitations make the model imperfect, and these methods inherit its error. More particles reduce Monte Carlo error but cannot remove the mismatch between the endpoint and the desired target or the error in tracking the prescribed probability path. We introduce the Energy-based Feynman-Kac Corrector (EBFKC), a framework for energy-based diffusion models that corrects these errors on the fly given a reference energy. We first derive Feynman-Kac dynamics that track a prescribed path exactly in the continuous-time population limit even when the model is imperfect, and approximate these dynamics using sequential Monte Carlo with variance-controlling guidance. To remove the endpoint mismatch, we use the pretrained energy as a surrogate along the diffusion path and progressively incorporate the discrepancy between the learned and target terminal energies. Experiments on Gaussian mixture models, particle systems, alanine dipeptide, and alanine tetrapeptide show that our method closely matches target distributions and molecular free-energy profiles under annealing and reward tilting, whereas standard inference-time scaling baselines retain substantial sampling errors.

Zuokai Wen, Louis Grenioux, Weinan E +1

School of Artificial Intelligence, Shanghai Jiao Tong University · Center for Computational Mathematics, Flatiron Institute · School of Mathematical Sciences, Peking University

Markov Chain Monte Carlo Diffusion Model Sampling Inference-Time Scaling Diffusion Models

Sep 30, 2026cs.LG

Scaling Laws for Looped Mixture of Experts

Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed parameters, while MoE sparsity expands total capacity at fixed active compute. Yet existing scaling laws model recurrence or sparsity in isolation. In this work, we introduce Loop Scaling Laws, the first scaling law to jointly model recurrence and sparsity alongside model size and data. At its core is a bounded, sparsity-conditional recurrence mapping that characterizes the effective-parameter gain from looping and how sparsity raises this gain. The laws predict the held-out loss of looped models more accurately than prior alternatives, and recover the standard dense and MoE scaling laws as special cases. Beyond prediction, the fitted laws provide a principled foundation for designing looped MoE models under compute and memory constraints. Downstream evaluations further demonstrate the complementary benefits of the two axes: sparsity delivers ~3x active-parameter efficiency, recurrence yields ~2x total-parameter efficiency on reasoning, and joint scaling further advances the performance frontier. As a practical extension, we show these gains hold at trillion-token scale: at matched training compute, a looped MoE with law-derived recurrence matches a ~2x larger non-looped MoE on the reasoning benchmarks, while enabling test-time scaling through recurrence.

Yanbei Chen, Anirudh Goyal, Raghuraman Krishnamoorthi

Meta AI

Mixture-of-Experts Language Models Language Model Scaling Laws Inference-Time Scaling Recurrent Transformers AI Scaling Laws

Sep 29, 2026cs.LG

Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling

Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context windows requires deciding how to allocate fresh contexts and what information to carry between them. We call a model's ability to make these decisions contextual reasoning. Existing approaches largely prescribe these decisions through their harness; we instead shift them to the model. We introduce 1) Hermes, a family of simple, configurable harnesses that progressively varies model control over context allocation and reuse, and 2) Hermes-Learn, a two-stage framework for learning these capabilities. We find that capable models can exploit this flexibility to scale with additional inference-time compute, while smaller open-source models initially struggle to do so. Training with Hermes-Learn closes this gap, inducing adaptive contextual reasoning strategies that vary with both the problem and the progress of reasoning. These gains generalize across benchmarks and models, extrapolate beyond the inference-time compute seen during training, and transfer to complementary test-time scaling methods beyond Hermes.

Xinyu Li, Mononito Goswami, Hao Liu +5

Carnegie Mellon University · AWS AI Labs · Washington University in St. Louis +1

LLM Inference Inference-Time Scaling Test-Time Scaling

Sep 29, 2026cs.LG

Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling

Test-time compute scaling has emerged as a cornerstone of advanced machine reasoning, yet performing iterative deliberation directly within continuous latent representation spaces reveals a catastrophic pathology: the Deliberation Drift Cliff. While unconstrained recurrent latent models achieve initial reasoning gains at short horizons (K <= 4), their reasoning collapses when extrapolated to deeper thinking steps (K >= 16), dropping by 22% to 62% across standard logical benchmarks. We resolve the trilemma among expressivity, Lyapunov stability, and computational efficiency in test-time latent reasoning through a 22-round empirical and theoretical investigation. We demonstrate that strictly conservative scalar potential gradient flows suppress long-range drift (cliff 3.40%) but bottleneck peak reasoning accuracy at 32.73%, whereas unconstrained rotational flows achieve high symbolic expressivity (82.33%) but suffer a severe 36.87% drift cliff. To resolve this geometric duality, we establish Port-Hamiltonian Latent Deliberation (PH-LD) and propose the Direct-Gradient Pure-Tensor Helmholtz-Hodge Decomposition (DG-HHD). DG-HHD parameterizes the attracting flow as a tangent projection tensor network while orthogonally decoupling non-zero circulation (Hodge machine error 1.65e-17, contraction error 5.55e-17), eliminating runtime autograd dependencies to achieve 1.84x vector field and 2.09x RK45 rollout speedups. In a 15-arm symmetrical Pareto benchmark, DG-HHD achieves 58.67% peak accuracy (+25.94% absolute gain over conservative HHD) and retains 35.27% at K=32. Transferred to small language model (SLM) multi-hop causal reasoning, DG-HHD delivers monotonic compute scaling (49.33% to 51.56%) and suppresses out-of-distribution drift (cliff -0.66%). All 30 Level 0 deterministic invariants are certified.

Zeyu Jia

School of Biomedical Engineering and Technology, Tianjin Medical University, Medical School, Tianjin University

Hodge Decomposition Inference-Time Scaling Port-Hamiltonian Systems

Sep 28, 2026cs.AI

From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining

Inference scaling has been shown to improve large language model (LLM) performance, and this principle naturally extends to autonomous LLM agents through increased search budgets, which we refer to as search scaling. Although prior work has characterized the mechanisms, scaling behavior, and performance limits of LLM inference scaling, much less is known about these questions in autonomous research. Therefore, we investigate how search scaling affects research performance and what mechanisms drive these gains using 50 quantitative factor-mining tasks grounded in financial research reports. Each task requires an agent to carry out an end-to-end research loop, from interpreting a hypothesis and implementing it in code to evaluating and iteratively refining the resulting factor. Across nine models, we examine how model capability, search depth, and search organization shape factor quality by tracing performance across varying budgets, transferring intermediate research states between models, and comparing different search strategies. We find that (1) initial performance is more strongly associated with model capability, while deeper search can narrow cross-model gaps; (2) model grafting shows that the early research state materially shapes final performance; and (3) parallel search outperforms sequential search under the same iteration budget, consistent with benefits from broader coverage of the search space. Further trajectory analysis shows that higher-performing models more effectively diagnose failures, revise search directions, and preserve the intended economic hypothesis when selecting candidates. These findings suggest that future progress in autonomous research will require stronger models together with adaptive policies for deploying test-time computation throughout the research process.

Kangcheng Deng, Hui Cai, Jiacheng Lu +6

StepFun · Shanghai Jiao Tong University · University of California, Los Angeles +1

Inference-Time Scaling Autonomous Research Agents

Sep 28, 2026cs.LG

Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation

Long-horizon agents improve solutions through sustained interaction, execution, and task feedback. Scaling studies relate performance to resources and capabilities, yet how existing capabilities shape returns to extended interaction remains less understood. To address this gap, we analyze AutoLab and EdgeBench, two long-horizon benchmarks. We find that starting performance and subsequent growth are associated with different capabilities: within a task category, similar early scores can precede different later gains. To formalize this finding, we model capability-time scaling with category-specific logistic power laws shared across models. Fitted to early trajectories, these curves extrapolate the observed models' category-average scores to later computation. However, rising average scores mask narrowing improvement opportunities: later gains concentrate among fewer improving models. High final scores and continued improvement also have distinct capability profiles. Predicted mean gains estimate each model's fraction of improving tasks; averaging these estimates forecasts the average share of improving models. These uneven returns motivate deciding whether a specific run should continue. We therefore derive a continuation policy to save time and compute with limited score loss. The policy conditions growth predictions on the run's observed progress and weighs immediate and delayed gains against computation costs. In replay with training and price calibration based on other models' histories, the policy saves roughly one-third of full-run time, with relative score losses of 2.4% on AutoLab individual runs and 3.3% on EdgeBench published mean curves. Our repository is available at https://github.com/Chihaya-Anon-chan/long-horizon-scaling.

Haoyu Zheng, Zhengyu Chen, Huaisheng Zhu +5

Meituan LongCat Team · Zhejiang University · Westlake University +2

Cost-Aware Inference Inference-Time Scaling Long-Horizon Agent Evaluation Long-Horizon LLM Agents

Sep 28, 2026cs.LG

Compute Time Scaling with Recursive Models for Combinatorial Optimization

We propose Tiny Recursive Models for Combinatorial Optimization (\ours{}), a general neural method for combinatorial optimization that scales both depth (how often we recursively invoke our network) and width (how much we sample in parallel). Both are fundamental for combinatorial optimization: hard instances demand a large amount of compute, while a small network is essential to avoid overfitting and capture the algorithmic essence of optimization. In particular, our method consists of a graph-aware tiny recursive model that iterates on a latent state with adaptive halting and needs only a lightweight problem-specific decoder. Compared with previous heatmap-based general neural solvers, it achieves a better balance between solution quality and inference speed on both the Traveling Salesman Problem~(TSP) and the Maximum Independent Set~(MIS) problem, and remains competitive with hybrid methods that combine neural components with heuristics specific to each problem. With the same backbone architecture for both tasks, \ours{} outperforms every diffusion-based solver on TSP from 500 to 10,000 cities at a lower inference cost, and on the standard Erdős--Rényi-[700-800] MIS benchmark it surpasses all neural solvers except those that only work well on MIS. We then explore self-relabeling for self-supervised training. We periodically replace the current set of training labels with the model's own better solutions, as an alternative training signal. Self-relabeling can, while forgoing supervision from near-optimal solutions, still result in on-par quality.

Zhengxi Zhang, Paul Swoboda

Traveling Salesperson Problem Inference-Time Scaling Combinatorial Optimization Neural Combinatorial Optimization

Sep 22, 2026cs.LG

Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models

Capability and efficiency are two key dimensions of reasoning in large language models (LLMs). Capability refers to the ability to solve a given problem correctly, whereas efficiency refers to the ability to do so with limited resources. When LLMs use Chain-of-Thought (CoT) reasoning to solve problems of controlled hardness, both the number of problems solved correctly and the number of tokens required to reach a correct answer depend on problem hardness and model size. However, how these factors jointly shape capability and efficiency remains poorly understood. Here, we use hierarchical Bayesian models to evaluate the capability and efficiency of LLMs from the DeepSeek-R1-Distill model family across four classes of arithmetic and algorithmic reasoning problems. At a fixed model size, the probability of correctly solving an instance decays approximately exponentially with instance size, our proxy for problem hardness. The decay scale grows sublinearly with model size, indicating that larger models are more capable, but that capability gains diminish with scale. Output length grows as a power law with instance size, which serves as a proxy for difficulty. However, the parameters of this power law do not vary systematically with model size, suggesting that larger models do not become more efficient. Together, these findings reveal potential limitations of naive scaling as a strategy for developing more capable AI systems: capability improves with diminishing returns, while efficiency shows little to no improvement.

Moritz Laber, Zohair Shafi, Germans Savcisens +6

Northeastern University, Boston, Massachusetts, USA · Complexity Science Hub Vienna, Vienna, Austria · Santa Fe Institute, Santa Fe, New Mexico, USA

LLM Inference Efficiency Language Model Scaling Laws Inference-Time Scaling Algorithmic Reasoning Large Reasoning Models

Sep 17, 2026cs.AI

The Organization of Inference: Information, Resource Constraints, and AI Production

The economic value of inference depends on how capacity and task information are distributed across stages of AI production. We study these organizational margins using controlled workflow experiments on externally verified software-engineering tasks. In two matched resource panels, direct execution records the same success rate of 59.6 percent at logical-token ceilings of 12,000 and 24,000, while success under information-constrained planning rises from 36.2 to 51.2 percent. The planning disadvantage narrows by 15.0 percentage points (95 percent task-cluster bootstrap interval: 4.2 to 25.8). A strict read-only planning campaign varies whether the planner sees the task issue. At 12,000 tokens, issue access raises success by about 16 percentage points over issue-hidden planning. Compared with direct execution, task-informed planning is about 10 points lower at 12,000 tokens; at 24,000 tokens, it shows a 29.6-point advantage. In the resource panels, direct execution uses substantially less than either ceiling, while the planning workflow's binding rate falls from 46.2 to 0.8 percent and downstream execution accounts for 89.9 percent of the increase in total use. Scale determines the capacity available to a system; workflow and information structure shape the productive value

Yukun Zhang, Kemu Xu, Yishen Chen

The Chinese University of Hong Kong Hong Kong, China · University of Edinburgh Edinburgh, United Kingdom · The Chinese University of Hong Kong, Shenzhen Shenzhen, China

LLM Planning Inference-Time Scaling Inference-Time Compute Allocation

Sep 15, 2026cs.LG

Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers

Looped Transformers offer a parameter-efficient route to test-time scaling by reusing shared layers for iterative latent reasoning. However, additional iterations can reduce support for a reference answer, leaving unclear whether an update's direction is locally unhelpful or its full displacement moves too far. We study this distinction by analysing reference utility, which measures this support, along the model's own update direction, varying the fraction of the proposed displacement supplied to the readout. This reveals finite-step failures in which a locally improving direction produces a harmful full update. A pathwise curvature decomposition characterises how initial progress is lost, while a local quadratic model predicts full-step gains and useful step scales. Bounds based on accumulated curvature variation characterise the approximation error of these predictions. Experiments across two model families reveal this separation on mathematical and commonsense tasks. A fixed quarter step produces positive gains in reference utility for 72.2--83.2% of selected failures across four settings. These findings identify a mismatch between update direction and step scale as a mechanism of lost progress, explaining how some harmful updates retain useful computation.

Zhihao Guo, Zonghan Wu, Haizhou Du +4

University of Technology Sydney, Australia · East China Normal University, China · Shanghai University of Electric Power, China +2

Inference-Time Scaling Recurrent Transformers

Sep 14, 2026cs.CL

Intelligence Under Time Constraints: Rethinking Test-Time Compute

Intelligence under time constraints requires deciding not only how much to compute, but when computation is worth starting. We study this problem in streaming interactions, where evidence arrives incrementally and may be revised. Early computation has more time to finish but rests on incomplete evidence; waiting improves information while shrinking computational slack. We call this the information-slack dilemma. We take the evidence-dependent computational job as the unit of analysis: when to start it, what supports its result, and when that result can be committed. Advance computation is valuable only insofar as its benefits survive the costs of verification, invalidation, and recovery. This applies to grounded incremental processing and reusable preparation as well as future-dependent speculation. We propose a research agenda on computation under evolving evidence, prioritizing selective recovery under controlled evidence revisions. Evaluation should separate earlier-execution effects, deployment value against a full-input alternative, and the added value of predictive policies, while accounting for shared-resource costs. The objective is not maximal advance computation, but more trustworthy, on-time responses within a declared resource envelope.

Xiaotian Zhang

Trooly.AI

Inference-Time Scaling Inference-Time Compute Allocation Online Resource Allocation

Sep 14, 2026cs.LG

Sampling via Decision-Flow: Training-Free Extraction of Improved Latent Reasoning Paths in Large Language Models

A central question in LLM reasoning is whether reinforcement learning (RL) instills genuinely new capabilities or merely reshapes how existing knowledge is expressed during inference. Building on the distribution-sharpening hypothesis, which holds that RL reallocates probability mass toward high-reward trajectories already latent in base models, we ask: can we unlock those latent paths without costly RL fine-tuning? We present Decision-Flow Sampling (DF-Sample), a training-free, data-free inference-time framework that constructs a hierarchical reasoning tree, scores terminal nodes for quality, and back-propagates utilities to inform each intermediate branching decision. Unlike conventional sampling strategies that make purely local step-wise choices, DF-Sample performs explicit global trajectory evaluation before committing to a path, recovering high-quality but low-probability reasoning chains that standard decoding overlooks. On GPQA, DF-Sample achieves 45.6% accuracy, surpassing power sampling (38.9%) and GRPO (39.9%), showing that a training-free method can outperform a trained one. Across three models and four benchmarks, DF-Sample consistently outperforms baselines, indicating substantial latent reasoning potential in pretrained base models.

Zhendong Mi, Shaoyi Huang

Stevens Institute of Technology

Inference-Time Search LLM Inference Inference-Time Scaling LLM Reasoning

Sep 1, 2026cs.LG

A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference

The ability of AI systems to improve their behavior during deployment is becoming increasingly important. As inference moves beyond the static execution of a fixed trained model, a growing body of work studies how models can refine their behavior on the fly by exploiting test-time information and additional computation. These developments have largely evolved along two directions: methods that modify the model's state using test-time signals, and methods that improve predictions through extra inference-time resources such as more sampling and tool use. However, these directions are often studied in separate communities with different terminology, making their connections harder to see. In this survey, we present feedback-driven Test-Time Intelligence (TTI) as a unified perspective for understanding such deployment-time improvement. We use this view to relate test-time adaptation, test-time learning, and test-time scaling, highlighting both their distinctions and their growing overlap in hybrid systems. This unified framework helps connect previously fragmented ideas and provides a clearer conceptual foundation for studying inference-time self-improvement. We review major methodological paradigms, representative applications, and open challenges across vision, language, multimodal learning, generative models, robotics, and healthcare. Our goal is to provide a coherent foundation and research roadmap for the study of self-improving AI systems at test time.

Shuaicheng Niu, Guohao Chen, Yaofo Chen +14

South China University of Technology · Nanyang Technological University · Tulane University +3

Test-Time Adaptation Inference-Time Scaling Test-Time Training

Sep 1, 2026cs.AI

Escaping Reasoning Basin Collapse with History-Biased Search

Inference-time search with large language models (LLMs) often concentrates on a small set of structurally or semantically similar trajectories, leaving alternative reasoning strategies underexplored---a failure mode we call \textit{reasoning basin collapse}. We introduce \textsc{BASIN}, a training-free, history-biased search method that groups reasoning states into basins and accumulates a revisit penalty on repeatedly selected basins, reallocating a fixed inference budget toward underexplored reasoning strategies. Under matched inference budgets, \textsc{BASIN} improves over Tree of Thoughts (ToT) by up to

+22

pp on Game of 24 and

+6.7

pp on MuSR. Because indiscriminate diversification can over-explore once search has found a promising basin, we further introduce \textsc{QA-BASIN}, a quality-aware variant that weakens the revisit penalty for high-quality basins and yields more robust gains. To characterize when basin-aware search helps, we introduce the \emph{redundancy gap}

Δ

, which measures the difference in search concentration between correct and incorrect predictions: standard ToT often operates near

Δ\approx 0

, whereas \textsc{BASIN} consistently shifts

Δ

positive. Together, these results identify reasoning basin collapse as a failure mode of inference-time search and show that history-dependent bias provides a simple, training-free mechanism for escaping redundant reasoning under fixed compute. Code is available at https://github.com/GitHubLuCheng/basin

Lu Cheng

Department of Computer Science University of Illinois Chicago Chicago, IL 60607

Inference-Time Search Reasoning Diversity Inference-Time Scaling

Aug 31, 2026cs.CL

When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models

As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inference-time compute to a fixed model prior. Viewed at a high level, TTS reframes inference as search over a space of partial reasoning states. While Chain-of-Thought (CoT) exposes intermediate steps, common instantiations rely on single-trajectory decoding, limiting recovery from early errors and exploration. This survey systematizes recent progress in tree-search-based reasoning, viewing inference as instance-specific optimization rather than decoding. We trace the evolution from uninformed search to Monte Carlo Tree Search (MCTS), highlighting how sampling-based control supports principled exploration-exploitation trade-offs. To unify a fragmented literature, we introduce a Unified Design Space spanning search topology, evaluation signals, and control dynamics, and advocate a standardized compute-reporting abstraction to make compute-accuracy trade-offs explicit and comparable.

Jiaqi Wei, Xiang Zhang, Yuejin Yang +10

1Zhejiang University · 2Shanghai AI Laboratory · 4Fudan University +3

Inference-Time Search Inference-Time Scaling Monte Carlo Tree Search LLM Reasoning

Aug 31, 2026cs.CL

Reactivating Test-Time Scaling for Plane Geometry Problem Solving

Plane geometry problem (PGP) solving has become a critical benchmark for multimodal reasoning because it requires accurate visual perception and precise multi-step symbolic deduction. Although test-time scaling (TTS) has demonstrated remarkable success in general mathematical reasoning, it fails to scale effectively under the symbolic-program paradigm for plane geometry. We identify two key obstacles: limited reasoning diversity induced by rigid symbolic programs and insufficient explicit visual grounding before symbolic deduction. To address these issues, we propose Multi-Trace Synthesis (MTS), which converts each symbolic program into heterogeneous reasoning traces, including executable Python scripts and CoT-augmented variants. We further propose Perception-Augmented (PA) training, which parses diagrams into structured semantic clauses before deduction, and Consensus-Guided Multi-Trace Ensemble (CG-MTE) for efficient self-adaptive inference. Experiments on three geometry benchmarks show that our method consistently improves PGP-solving across model scales and achieves strong performance against both general-purpose MLLMs and specialized geometry solvers. Under test-time scaling, CG-MTE achieves comparable accuracy to high-budget self-consistency while reducing sampling cost by up to 8x. Code and data are publicly available at https://github.com/Jason8Kang/ReTTS-PGPS.

Xiaoqiang Kang, Shengen Wu, Maizhen Ning +5

School of Advanced Technology, Xi’an Jiaotong-Liverpool University · The Hong Kong University of Science and Technology (Guangzhou) · Hithink Research +2

Spatial Reasoning Benchmarks Inference-Time Scaling Symbolic Reasoning Mathematical Reasoning

Aug 12, 2026cs.AI

Who Thinks Best Depends on How Long You Let Them: Budget-Dependent Rankings in LLM Evaluation

Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the token generation budget, i.e., the maximum tokens a model may produce, across seven levels (64--4,096), evaluating four models on three reasoning benchmarks (56,476 inferences). We report four findings: (i) 3--19% of items exhibit non-monotone behavior (accuracy decreasing with more budget), even after controlling for truncation, and this phenomenon is model-specific (cross-model overlap: 6--14%). (ii) Model rankings reverse across budgets on all benchmarks (

p {<} 0.01

, McNemar). (iii) Oracle analysis reveals model complementarity up to

+27.8

pp, most pronounced at constrained budgets. (iv) A budget-aware router captures 14.1% of the oracle gap cross-domain; budget features help within-domain (

+1.6

to

+5.7

pp) but are domain-specific and hurt transfer (

-1.2

pp). These results argue for budget-conditioned evaluation protocols.

Rodrigo Guedes de Souza, Alison R. Panisson

Federal University of Santa Catarina (UFSC) Brazil

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

Aug 4, 2026cs.RO

PACE: Adaptive Budget Allocation for Time-Efficient Embodied Planning

Reasoning-enhanced large language models have achieved remarkable improvements in planning tasks, yet their deployment in embodied systems remains impractical due to prohibitive inference delays-often exceeding minutes per planning instance. The fundamental bottleneck stems from the serial nature of existing paradigms: models must complete all reasoning before any action execution, leaving execution time windows entirely unexploited. We introduce PACE (Planning with Adaptive Cognitive Effort), a framework that enables interleaved reasoning and execution through two key innovations: an Interleaved Think-Act architecture that pipelines cognitive processing with action execution, and a Dynamic Budget Allocator that adapts reasoning token budgets to available execution time windows. On the Robotouille benchmark using Qwen3-8B-AWQ, PACE achieves a 10% success rate-representing a 67% improvement over the ReAct+Think baseline-while delivering 6.9 times acceleration in thinking time compared to unconstrained reasoning. The framework hides 66.8% of thinking time within execution windows, demonstrating that strategic cognitive effort allocation can simultaneously improve both planning quality and time efficiency. These results provide evidence that time-aware architectural innovations enable reasoning models to operate in latency-sensitive embodied domains where they were previously impractical.

Yuchen Huang, Xijiang Ying, Zhenhua Ma +14

ZTE Corporation · Shanghai, China

Large Language Model-Based Robot Planning LLM Inference Scheduling Inference-Time Scaling Agentic Reasoning Embodied Reasoning

Jul 31, 2026cs.AI

Decode-Branch Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation

As large language models serve ever more requests, cumulative inference cost is growing relative to the one-time cost of training. In typical serving, prompt prefill runs in parallel and is compute-bound, whereas autoregressive decode is sequential and memory-traffic-bound. Conventional width or depth scaling raises both costs together, since every added layer is evaluated in both phases and enlarges the weights read at each decode step. We instead ask whether additional learned computation can be allocated to continuation prediction while preserving prompt-wide primary computation and a single KV cache. We realize this with the Decode-Branch Transformer. Its primary path alone processes the prompt and writes the KV cache; the decode branch is omitted during prefill and activated only from the final prompt position onward, adding continuation computation without writing state or affecting the primary path. The paths share attention, MLP, and output matrices, using separate token embeddings with lightweight coupling. Grouped decode reuses loaded weight tiles and the primary KV cache across both paths, so the added arithmetic does not proportionally increase dominant memory traffic or decode latency. Across matched-token comparisons, Decode-Branch achieves lower validation loss across architectures and data settings. In MoE models, the primary and branch expert fan-outs become independent knobs for trading prompt cost, decode cost, and predictive quality. We study two expert-allocation regimes, holding prefill or decode computation fixed, and expose a prefill-decode-quality trade-off enabled by phase-specific expert allocation.

Liming Liu, Mingze Wang, Tuo Zhao

Georgia Institute of Technology · Peking University

Efficient Transformer Inference Inference-Time Scaling LLM Inference Acceleration

Jul 30, 2026cs.AI

Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs

Deploying autonomous computer-use agents (CUAs) locally is increasingly important for privacy, cost efficiency, and practical usability, yet improving their performance under strict hardware constraints remains challenging. While recent studies show that inference-time scaling can improve frontier computer-use agents through additional computation during execution, its effectiveness for resource-constrained local models remains poorly understood. We present a systematic empirical study of inference-time scaling in local CUAs across contextual, temporal, structural, and parallel dimensions. We evaluate Qwen3-VL-8B/30B-A3B, UI-TARS-1.5-7B, and OpenCUA-7B on the OSWorld benchmark. Our results show that additional computation often yields diminishing returns while changing failure modes. Contextual scaling provides historical grounding that improves trajectory stability and task accuracy, but its gains saturate as token cost increases and failures shift from repetitive or stalled trajectories toward premature false successes. Temporal scaling similarly reduces max-step stalls, yet does not substantially improve task success, indicating that longer horizons often extend erroneous trajectories rather than correct them. We further find that structural decomposition can introduce planning and formatting overhead in local two-stage agents, while parallel scaling partially mitigates these failures at a substantial computational cost. Overall, our findings suggest that efficient local CUAs require selective compute allocation, failure-aware control mechanisms, and agentic frameworks designed around the capabilities and limitations of local models.

Woongkyu Lee, Jungwook Choi

Hanyang University

Computer-Use Agents Inference-Time Scaling Inference-Time Compute Allocation On-Device Inference

Jul 29, 2026cs.AI

Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs

Recent advancements in inference-time scaling have significantly unlocked the complex reasoning capabilities of Large Language Models~(LLMs). However, for agents, these approaches suffer from a critical inefficiency, operating in a stateless manner and engaging in redundant search processes. Existing memory mechanisms largely rely on the reasoning capabilities of LLMs, leading to prohibitive computational costs. In this paper, we propose a novel framework, \textit{GAMER}(Graph-based Action-centric Memory with Episodic Reasoning), that bridges the gap between inference scaling and episodic memory. Our approach models historical reasoning as a dynamic \textit{Action-Centric Graph}. By decoupling the memory mechanism from LLMs, our method can save token/money usage by providing less memory context than memory mechanism baselines. To extract knowledge from the graph effectively, we use a dual-stream Temporal Difference learning mechanism to estimate the positive(suggestion) and negative~(avoidance) value of action nodes based on past successes and failures. During the inference phase, this learned value function optimizes decision-making bi-directionally, so that positive values provide action suggestions, while negative values indicate high-risk actions. By performing efficient searches on the graph, our method significantly improves the efficiency of inference scaling. Experiments on multiple benchmarks demonstrate that \textit{GAMER} achieves superior performance by \textbf{20.81%/6.17%} for success/progress rate compared to vanilla baselines.

Xu Zheng, Chaohao Lin, Zhuomin Chen +4

Florida International University, Miami, FL, USA · Stanford University, Stanford, CA, USA · NEC Laboratories America, Princeton, NJ, USA +1

Agent Memory Inference-Time Search Inference-Time Scaling Graph-Based Agent Memory Memory-Augmented Agents

Jul 23, 2026cs.CV

Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning

Diffusion and flow-matching models dominate conditional image generation, yet inference-time scaling for these models is far less developed than for autoregressive language models. Because final quality is highly sensitive to the initial noise seed, many approaches spend extra compute on seed search or resampling under a black-box reward, but typically maintaining a constant memory footprint throughout inference. We show that relaxing this constraint enables an underexplored inference-time scaling axis: by front-loading exploration, evaluating many seeds early, and pruning aggressively, we can use a fixed compute budget more effectively. \emph{Progressive Seed Pruning} (\PSP) scores intermediate denoised estimates and progressively narrows the candidate set so that only promising trajectories are fully denoised, while keeping the total number of model evaluations fixed. Across diffusion and flow-matching backbones, \PSP \ consistently improves reward-guided selection and achieves higher GenEval scores (automated) and better human evaluation on prompt-alignment than best-of-

N

, importance-sampling, and tree-search baselines at matched compute. Project page: https://www.vision.caltech.edu/psp. Code: https://github.com/rogerioagjr/psp.

Rogerio Guimaraes, Pietro Perona

California Institute of Technology, Pasadena CA 91125, USA

Diffusion Model Sampling Diffusion Sampling Inference-Time Scaling Diffusion-Based Image Generation

Jul 22, 2026cs.LG

When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers

When does a weight-tied looped transformer -- one block applied T times -- implement an actual algorithm? We answer with four findings from controlled populations on group word problems. (1) The budget law: free training installs a linear computation frontier, a mechanism that solves v positions per loop, whose speed is priced by the training contract: v ~ n_train/T_train (exponent 0.98 +/- 0.04, R^2=0.99), exactly unity under T=n training. SGD selects a frontier matching the minimum the contract demands; granting more test-time loops than ever trained rescues late positions at fixed input length, yielding a principled halting rule T* = ceil(n / v-hat). (2) Architecture prior, not expressivity, picks the algorithm: standard-depth transformers learn parallel scans on this family; weight tying flips the selection to the serial frontier, even when positional addressing for a log-depth scan is supplied. At matched depth and parameters, untied models extrapolate worst and fail to learn A5 at all. (3) The walls are not where circuit complexity says: NC1-completeness costs nothing (A5 generalizes fully), while group order does (S5's 120x120 operator deadlocks joint learning) -- and an operator-first curriculum dissolves the wall in every seed. (4) Mechanisms are portable, not mandatable: warm-starting across budget contracts transfers the algorithm in every seed, re-pricing its speed, while imposing seriality through the input schedule fails where free training succeeds. These results are invisible to standard instruments, which provably saturate at the fixed points trained loops converge to. We introduce a head instrument, the convergence-time scaling tau(n,i), validate it causally via damage cones whose slope reproduces v, and show in-distribution head measurements predict out-of-distribution fate where tail metrics do not. Results replicate on the public easy-to-hard benchmark.

Tong Zhang, Junhao Hu, Yun Peng +1

Fudan University · Peking University

Inference-Time Scaling Length Generalization Recurrent Transformers Neural Network Training Dynamics Algorithmic Reasoning

Jul 14, 2026cs.LG

Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques

Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel generation alone does not guarantee practical speedups. Realizing this efficiency requires specialized inference mechanisms, such as diffusion-aware caching and reuse. Consequently, as inference efficiency becomes a prerequisite for practical deployment, recent research has actively explored acceleration techniques across algorithms, architectures, and systems. However, rigorous comparisons remain difficult, as end-to-end latency stems from intricate trade-offs between algorithmic, architectural, and system-level factors that are often conflated in existing benchmarks. In this survey, we introduce a unified latency decomposition framework for dLLMs to disentangle these factors and analyze their impact on inference speed in real deployments. Guided by this framework, we categorize acceleration techniques along three axes covering algorithmic innovations, architectural and system optimizations, and inference-time scaling. Finally, we provide guidelines for reproducible benchmarking and highlight open challenges for realizing the full potential of parallel generation.

Daehoon Gwak, Minhyung Lee, Junwoo Park +1

KAIST AI · Yonsei University

Masked Diffusion Models Inference-Time Scaling Diffusion Language Model Inference Diffusion Language Model Decoding Diffusion Model Caching

Jul 5, 2026cs.CV

Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models

Inference-time scaling for text-to-image generation has progressed from simple Best-of-

N

(BoN) sampling to guided search methods that verify and steer candidate trajectories at intermediate denoising steps. These approaches focus on when and how often to verify during denoising but largely treat the cost of generation itself as fixed. Moreover, the standard practice of comparing methods by number of function evaluations (NFEs) counts only denoising forward passes and ignores verifier overhead, which can distort efficiency rankings. We show that under wall-clock evaluation, simple BoN already matches or outperforms several guided search techniques, suggesting that compute is better spent on broader exploration than on repeated intermediate verification. This motivates Flash-BoN, which generates a large pool of inexpensive draft candidates by combining three complementary acceleration knobs: timestep truncation, layer skipping, and activation proxies into a single configuration optimized once per model. An efficient multi-stage verification procedure then identifies the most promising draft, which is refined at full quality. Across three benchmarks and three model scales, Flash-BoN consistently outperforms all baselines under fixed wall-clock budgets, with gains that grow at larger model scales (+8% AUC). We further show that our strategy combines well and improves existing orthogonal techniques such as reflection-based prompt optimization (+16% AUC). The gains correlate with increased candidate diversity, which also enables draft-guided selection to accelerate RL post-training convergence.

Ruchit Rawal, Reza Shirkavand, Sayak Paul +5

University of Maryland, College Park, MD, USA · Hugging Face, USA

Inference-Time Scaling Best-of-N Sampling Diffusion Model Inference Acceleration T2I Diffusion Models

Jul 1, 2026cs.LG

QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling

Scaling inference compute, by generating many parallel attempts per problem, is a costly but reliable lever for improving language model capabilities. By default these attempts are generated independently, wasting inference compute on redundant solutions. This waste seems unavoidable. After all, independence is what makes parallel sampling trivial to scale. However, this tradeoff is not fundamental: there is a rich design space of samplers that generate correlated but exact samples entirely in parallel. We explore this design space as an avenue for improving sample efficiency in scaling inference compute and reinforcement learning (RL). Concretely, we introduce QuasiMoTTo, which uses correlated samples as a drop-in replacement for i.i.d. samples. To generate these samples, QuasiMoTTo uses a reparameterization of autoregressive sampling as inverse-CDF sampling and draws the underlying uniforms with quasi-Monte Carlo (QMC); because QMC spreads the uniforms out more evenly than i.i.d., the resulting samples cover the output space with far less redundancy. Even though the batch is correlated, each sample is marginally distributed according to the language model, so we can use the batch for policy-gradient training. Our empirical analysis focuses on understanding how efficiently QuasiMoTTo can turn compute into performance. To evaluate correlated samplers, whose dependence breaks standard pass@k estimators, we first develop an unbiased bootstrap estimator. Across four reasoning benchmarks, QuasiMoTTo matches i.i.d. pass@k accuracy with 25-47% fewer samples. Strikingly, QuasiMoTTo often saturates an upper bound on pass@k that holds for any marginal-preserving sampler. We also apply QuasiMoTTo to policy-gradient RL (GRPO) where it matches i.i.d. performance with 50% fewer training steps. These gains come from higher coverage, which yields a stronger learning signal per batch.

Michael Y. Li, Anthony Zhan, Kanishk Gandhi +2

Stanford University

Inference-Time Scaling Sample-Efficient RL

Jul 1, 2026cs.CL

Message Passing Enables Efficient Reasoning

While inference-time scaling has improved the reasoning abilities of large language models (LLMs), the need to generate long chains-of-thought (CoTs) is a computational bottleneck. Thus, in contrast to sequential scaling methods like CoT, recent parallel scaling techniques instead use fork and join (FJ) primitives to divide work across multiple LLM threads. However, in the fork-join paradigm, threads are typically transient and do not communicate pointwise with one another which limits scalability. To tackle this, we introduce Message Passing Language Models (MPLMs), a framework for LLM reasoning in which threads communicate directly via lightweight send and receive primitives. MPLMs enable efficient scaling through two key mechanisms: (1) reduced communication costs, achieved by avoiding redundant context sharing, and (2) preemption, which allows threads to terminate early based on partial information from their peers. We demonstrate the promise of MPLMs on 3 classes of tasks. First, on Sudoku puzzles, we show that MPLMs require an asymptotically smaller context than both serial CoT and parallel FJ. We then fine-tune a single model to solve 25 x 25 puzzles that remain challenging for standard CoT and FJ approaches, as well as frontier reasoning models without tools. Second, on 3-SAT puzzles, the capability of preemption allows termination of unpromising branches, which results in improved efficiency. Finally, we show that appropriately prompted large pre-trained models follow the MPLM protocol, achieving competitive results on long-context question answering relative to popular fork-join approaches.

Xuecheng Liu, Daman Arora, Gokul Swamy +1

Carnegie Mellon University

Inference-Time Scaling Efficient Language Model Reasoning LLM Inference Acceleration Language Modeling Large Reasoning Models