Test-Time Scaling

Follow this topic Ask about this topic

Latest papers 206

30 papers in the last four weeks, up 58% on the four weeks before. 0.2% of all new papers.

Apr 28, 2026

Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling

Large Language Models (LLMs) now exhibit remarkable reasoning capabilities through test-time compute scaling (TTS), with impressive performance across math and coding benchmarks. In parallel, research in model compression has developed pruning methods that seek to remove redundant/detrimental parameters without sacrificing task performance. The intersection of these two research advancements lays the foundation for our work. Specific to reasoning LLMs, prior work has shown that structured pruning (methods which remove entire set of layer blocks), significantly degrades TTS reasoning performance. However, in this work, we revisit this assumption and investigate whether unstructured pruning (methods that carefully remove only certain redundant/detrimental weights) exhibits similar limitations. Surprisingly, our extensive experiments across four reasoning benchmarks on two reasoning LLMs: s1.1-7B and Qwen3-8B, consistently show that unstructured pruning augments TTS performance compared to structured pruning, and at times can even outperform the unpruned full-weight LLMs. Furthermore, we also empirically study the impact of different layer-wise sparsity allocation strategies, which are an important parametric choice for instantiating these unstructured methods. These findings challenge the conventional notion that pruning always reduces TTS performance and in fact, suggest that carefully undertaken pruning can retain TTS effectiveness.

Ocean Monjur, Shahriar Kabir Nahin, Anshuman Chhabra

Bellini College of AI, Cybersecurity, and Computing University of South Florida Tampa, FL, USA

LLM Pruning Test-Time Scaling Neural Network Pruning

Apr 22, 2026

Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations

While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from fixed generation distributions. In this work, we introduce a test-time compute allocation framework that jointly adapts where computation is spent and how generation is performed. Our method begins with a warm-up phase that identifies easy queries and assembles an initial pool of question-response pairs from the test set itself. An adaptive phase then concentrates further computation on unresolved queries while reshaping their generation distributions through evolving in-context demonstrations -- conditioning each generation on successful responses from semantically related queries rather than resampling from a fixed distribution. Experiments across math, coding, and reasoning benchmarks demonstrate that our approach consistently outperforms existing baselines while consuming substantially less inference-time compute.

Bowen Zuo, Dongruo Zhou, Yinglun Zhu

University of California, Riverside · 2Indiana University Bloomington

Efficient Inference Test-Time Optimization Test-Time Scaling In-Context Learning Inference-Time Compute Allocation

Apr 20, 2026

Bridging the Reasoning Gap in Vietnamese with Small Language Models via Test-Time Scaling

The democratization of ubiquitous AI hinges on deploying sophisticated reasoning capabilities on resource-constrained devices. However, Small Language Models (SLMs) often face a "reasoning gap", particularly in non-English languages like Vietnamese, where they struggle to maintain coherent chains of thought. This paper investigates Test-Time Scaling strategies for the Qwen3-1.7B architecture within the context of Vietnamese Elementary Mathematics. We introduce Vi-S1K, a high-fidelity reasoning dataset localized via a Gemini 2.5 Flash-Lite powered pipeline, and Vi-Elementary-Bench, a dual-resource benchmark for rigorous evaluation. Using an LLM-as-a-Judge protocol, we reveal that the base model possesses robust latent knowledge (Accuracy: 4.05/5.00) but suffers from a severe "formatting gap" in communication. Supervised Fine-Tuning (SFT) acts as a critical "reasoning unlocker", yielding a 77% improvement in Explanation Quality and bridging the gap between raw calculation and pedagogical coherence. Furthermore, our analysis of prompting strategies uncovers a significant trade-off: structured frameworks like ReAct impose a "cognitive tax" on the 1.7B parameter capacity, degrading performance relative to pure Chain-of-Thought (CoT) combined with Self-Consistency. These findings establish a deployment hierarchy for SLMs, demonstrating that SFT combined with simplified test-time scaling is superior to complex agentic workflows for edge-based reasoning.

Bui The Trung, Do Minh Duc, Nguyen Van Vinh +1

Computer Science and Engineering VNU Vietnam Japan University Hanoi, Vietnam · Information Science JAIST Ishikawa, Japan · Faculty of Information VNU University of Engineering and Technology Hanoi, Vietnam +1

Supervised Fine-Tuning Mathematical Reasoning Benchmarks Test-Time Scaling Small Language Models

Apr 19, 2026

Efficient Test-Time Scaling via Temporal Reasoning Aggregation

Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit methods typically rely on single-step confidence signals, which are often unreliable for detecting reasoning convergence in multi-step settings. To mitigate this limitation, we propose TRACE, a training-free framework for efficient test-time scaling that determines when to terminate reasoning based on temporal aggregation of multi-step evidence rather than instantaneous signals. TRACE detects reasoning convergence over time by aggregating two complementary signals across recent reasoning steps: answer consistency, capturing the persistence of predicted answers, and confidence trajectory, modeling the temporal evolution of model confidence. Benefiting from these two factors, TRACE can accurately determine whether the reasoning process has converged, thereby promptly halting inference and effectively avoiding redundant reasoning steps. Extensive experiments on multiple challenging benchmarks show that TRACE reduces reasoning token usage by 25-30% on average while maintaining accuracy within 1-2% of full-length reasoning, consistently outperforming existing dynamic reasoning methods.

Jiakun Li, Xingwei He, Kefan Li +3

School of Computer Science and Engineering, Beihang University · 3Hangzhou Innovation Institute, Beihang University · 2Qingdao Research Institute, Beihang University

Test-Time Scaling Efficient Language Model Inference LLM Reasoning

Apr 16, 2026

SCATR: Simple Calibrated Test-Time Ranking

Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: generating multiple candidate responses and selecting the best via a Best-of-N (BoN) strategy. Its effectiveness therefore hinges on the scoring function. Learned scorers such as process reward models (PRMs) can be strong, but they are expensive to train and run. Lightweight confidence heuristics based on token log-probabilities are much cheaper, yet we find that they often perform substantially worse. To improve on lightweight confidence heuristics without incurring the full cost of stronger learned scorers, we introduce SCATR, a simple and efficient BoN ranking method that learns a lightweight scorer from a small calibration set using hidden representations from the base model. Across coding and mathematical reasoning benchmarks, SCATR improves over prior confidence-based baselines by up to 9%. Relative to LoRA fine-tuning on the same calibration data, it achieves comparable accuracy with up to 8000x fewer trainable parameters and much lower compute, reducing training and inference latency by up to 150x and 1000x, respectively. SCATR is also competitive with strong PRM baselines, and in several settings improves accuracy by up to 7.8% on math and 4.2% on coding while enabling up to 1000x faster inference. Overall, SCATR offers a strong accuracy-efficiency trade-off for scalable test-time selection.

Divya Shyamal, Marta Knežević, Lan Tran +3

EPFL · MIT

Test-Time Scaling Best-of-N Sampling LLM Reranking Efficient Language Model Inference

Apr 16, 2026

(1D) Ordered Tokens Enable Efficient Test-Time Search

Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text, and AR generation predicts these tokens in a fixed order. A worthwhile question is whether token structures affect the ability to steer the generation through test-time search, where multiple candidate generations are explored and evaluated by a verifier. Using image generation as our testbed, we hypothesize that recent 1D ordered tokenizers with coarse-to-fine structure can be more amenable to search than classical 2D grid structures. This is rooted in the fact that the intermediate states in coarse-to-fine sequences carry semantic meaning that verifiers can reliably evaluate, enabling effective steering during generation. Through controlled experiments, we find that AR models trained on coarse-to-fine ordered tokens exhibit improved test-time scaling behavior compared to grid-based counterparts. Moreover, we demonstrate that, thanks to the ordered structure, pure test-time search over token sequences (i.e., without training an AR model) can perform training-free text-to-image generation when guided by an image-text verifier. Beyond this, we systematically study how classical search algorithms (best-of-N, beam search, lookahead search) interact with different token structures, as well as the role of different verifiers and AR priors. Our results highlight the impact of token structure on inference-time scalability and provide practical guidance for test-time scaling in AR models.

Zhitong Gao, Parham Rezaei, Ali Cy +7

1Swiss Federal Institute of Technology Lausanne (EPFL) · 2Apple

Image Tokenization Test-Time Scaling Autoregressive Image Generation

Apr 16, 2026

Scaling Test-Time Compute for Agentic Coding

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this premise: each attempt produces an extended trajectory of actions, observations, errors, and partial progress taken by the agent. In this setting, the main challenge is no longer generating more attempts, but representing prior experience in a form that can be effectively selected from and reused. We propose a test-time scaling framework for agentic coding based on compact representations of rollout trajectories. Our framework converts each rollout into a structured summary that preserves its salient hypotheses, progress, and failure modes while discarding low-signal trace details. This representation enables two complementary forms of inference-time scaling. For parallel scaling, we introduce Recursive Tournament Voting (RTV), which recursively narrows a population of rollout summaries through small-group comparisons. For sequential scaling, we adapt Parallel-Distill-Refine (PDR) to the agentic setting by conditioning new rollouts on summaries distilled from prior attempts. Our method consistently improves the performance of frontier coding agents across SWE-Bench Verified and Terminal-Bench v2.0. For example, by using our method Claude-4.5-Opus improves from 70.9% to 77.6% on SWE-Bench Verified (mini-SWE-agent) and 46.9% to 59.1% on Terminal-Bench v2.0 (Terminus 1). Our results suggest that test-time scaling for long-horizon agents is fundamentally a problem of representation, selection, and reuse.

Joongwon Kim, Wannan Yang, Kelvin Niu +13

1Meta Superintelligence Labs · University of Washington · 3New York University +4

AI Coding Agents Test-Time Scaling Long-Horizon LLM Agents

Apr 16, 2026

Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization

Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improving large language model performance. Yet deploying these techniques under finite inference budgets requires a decision that current systems largely ignore: which inputs deserve more compute, and which can be answered cheaply? We formalize this as a constrained optimization problem (maximize expected accuracy subject to an average compute budget) and solve it with a two-stage Solve-then-Learn pipeline. In the solve stage, Lagrangian relaxation decomposes the global constraint into per-instance sub-problems, each admitting a closed-form oracle action that optimally prices accuracy against cost. We prove that the induced cost is monotone in the dual variable, enabling exact budget targeting via binary search. In the learn stage, a lightweight classifier is trained to predict oracle actions from cheap input features, amortizing the allocation rule for real-time deployment. We establish that the task-level regret of the learned policy is bounded by its imitation error times the worst-case per-instance gap, yielding a clean reduction from constrained inference to supervised classification. Experiments on MATH and GSM8K with three LLMs (DeepSeek-V3, GPT-4o-mini, Qwen2.5-7B) show that our method consistently outperforms uniform and heuristic allocation baselines, achieving up to 12.8% relative accuracy improvement on MATH under matched budget constraints, while closely tracking the Lagrangian oracle upper bound with over 91% imitation accuracy.

Zhiyuan Zhai, Bingcong Li, Bingnan Xiao +2

Fudan University · ETH Zurich · Guangming Lab

Test-Time Scaling Constrained Optimization Inference-Time Compute Allocation

Apr 15, 2026

C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions

Neural network models with latent recurrent processing, where identical layers are recursively applied to the latent state, have gained attention as promising models for performing reasoning tasks. A strength of such models is that they enable test-time scaling, where the models can enhance their performance in the test phase without additional training. Models such as the Hierarchical Reasoning Model (HRM) and Artificial Kuramoto Oscillatory Neurons (AKOrN) can facilitate deeper reasoning by increasing the number of recurrent steps, thereby enabling the completion of challenging tasks, including Sudoku, Maze solving, and AGI benchmarks. In this work, we introduce confidence-based voting (C-voting), a test-time scaling strategy designed for recurrent models with multiple latent candidate trajectories. Initializing the latent state with multiple candidates using random variables, C-voting selects the one maximizing the average of top-1 probabilities of the predictions, reflecting the model's confidence. Additionally, it yields 4.9% higher accuracy on Sudoku-hard than the energy-based voting strategy, which is specific to models with explicit energy functions. An essential advantage of C-voting is its applicability: it can be applied to recurrent models without requiring an explicit energy function. Finally, we introduce a simple attention-based recurrent model with randomized initial values named ItrSA++, and demonstrate that when combined with C-voting, it outperforms HRM on Sudoku-extreme (95.2% vs. 55.0%) and Maze (78.6% vs. 74.5%) tasks.

Kenji Kubo, Shunsuke Kamiya, Masanori Koyama +3

Graduate School of Engineering, The University of Tokyo

Test-Time Scaling Neural Algorithmic Reasoning Recurrent Neural Networks Majority Voting

Apr 14, 2026

Parcae: Scaling Laws For Stable Looped Language Models

Traditional fixed-depth architectures scale quality by increasing training FLOPs, typically through increased parameterization, at the expense of a higher memory footprint, or data. A potential alternative is looped architectures, which instead increase FLOPs by sending activations through a block of layers in a loop. While promising, existing recipes for training looped architectures can be unstable, suffering from residual explosion and loss spikes. We address these challenges by recasting looping as a nonlinear time-variant dynamical system over the residual stream. Via a linear approximation to this system, we find that instability occurs in existing looped architectures as a result of large spectral norms in their injection parameters. To address these instability issues, we propose Parcae, a novel stable, looped architecture that constrains the spectral norm of the injection parameters via discretization of a negative diagonal parameterization. As a result, Parcae achieves up to 6.3% lower validation perplexity over prior large-scale looped models. Using our stable looped architecture, we investigate the scaling properties of looping as a medium to improve quality by increasing FLOPs in training and test-time. For training, we derive predictable power laws to scale FLOPs while keeping parameter count fixed. Our initial scaling laws suggest that looping and data should be increased in tandem, given a fixed FLOP budget. At test-time, we find that Parcae can use looping to scale compute, following a predictable, saturating exponential decay. When scaled up to 1.3B parameters, we find that Parcae improves CORE and Core-Extended quality by 2.99 and 1.18 points when compared to strong Transformer baselines under a fixed parameter and data budget, achieving a relative quality of up to 87.5% a Transformer twice the size.

Hayden Prairie, Zachary Novack, Taylor Berg-Kirkpatrick +1

University of California, San Diego · Together AI

Language Model Scaling Laws Recursive Language Models Test-Time Scaling Recurrent Transformers

Apr 14, 2026

Adaptive Test-Time Scaling for Zero-Shot Respiratory Audio Classification

Automated respiratory audio analysis promises scalable, non-invasive disease screening, yet progress is limited by scarce labeled data and costly expert annotation. Zero-shot inference eliminates task-specific supervision, but existing methods apply uniform computation to every input regardless of difficulty. We introduce TRIAGE, a tiered zero-shot framework that adaptively scales test-time compute by routing each audio sample through progressively richer reasoning stages: fast label-cosine scoring in a joint audio-text embedding space (Tier-L), structured matching with clinician-style descriptors (Tier-M), and retrieval-augmented large language model reasoning (Tier-H). A confidence-based router finalizes easy predictions early while allocating additional computation to ambiguous inputs, enabling nearly half of all samples to exit at the cheapest tier. Across nine respiratory classification tasks without task-specific training, TRIAGE achieves a mean AUROC of 0.744, outperforming prior zero-shot methods and matching or exceeding supervised baselines on multiple tasks. Our analysis show that test-time scaling concentrates gains where they matter: uncertain cases see up to 19% relative improvement while confident predictions remain unchanged at minimal cost.

Tsai-Ning Wang, Herman Teun den Dekker, Lin-Lin Chen +2

Eindhoven Artificial Intelligence Systems Institute, The Netherlands

Respiratory Sound Classification Test-Time Scaling

Apr 14, 2026

CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature escalations to costlier models or experts due to under-confidence and inefficient compute scaling. CascadeDebate addresses this gap by inserting multi-agent deliberation directly at each tier's escalation boundary. Confidence-based routers activate lightweight agent ensembles only for uncertain cases, enabling consensus-driven resolution of ambiguities internally without invoking higher-cost upgrades. Our unified architecture alternates single-model inference with selective multi-agent deliberation across model scales, culminating in human experts as the final fallback. This design scales test-time compute dynamically according to query difficulty. Across five benchmarks spanning science, medicine, and general knowledge, CascadeDebate outperforms strong single-model cascades and standalone multi-agent systems by up to 26.75 percent. An online threshold optimizer proves essential, boosting accuracy by 20.98 to 52.33 percent relative improvement over fixed policies and enabling elastic adaptation to real-world distributions.

Raeyoung Chang, Dongwook Kwon, Jisoo Lee +1

Sogang University · Kwangwoon University · Seoul National University +1

LLM Routing Multi-Agent Debate Test-Time Scaling

Apr 13, 2026

Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel and aggregated into a final response. While such scaling has proven effective for chain-of-thought reasoning, agentic tasks pose unique challenges: trajectories are long, multi-turn, and tool-augmented, and outputs are often open-ended. Aggregating only final answers discards rich information from trajectories, while concatenating all trajectories exceeds the model's context window. To address this, we propose AggAgent, an aggregation agent that treats parallel trajectories as an environment. We equip it with lightweight tools to inspect candidate solutions and search across trajectories, enabling it to navigate and synthesize information on demand. Across six benchmarks and three model families (GLM-4.7, Qwen3.5, MiniMax-M2.5), AggAgent outperforms all existing aggregation methods-by up to 5.3% absolute on average and 10.3% on two deep research tasks-while adding minimal overhead, as the aggregation cost remains bounded by a single agentic rollout. Our findings establish agentic aggregation as an effective and cost-efficient approach to parallel test-time scaling.

Yoonsang Lee, Howard Yen, Xi Ye +1

Princeton Language and Intelligence, Princeton University

Test-Time Scaling Long-Horizon Agent Tasks Long-Horizon LLM Agents

Apr 12, 2026

When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling

Scaling test-time compute through extended chains of thought has become a dominant paradigm for improving large language model reasoning. However, existing research implicitly assumes that longer thinking always yields better results. This assumption remains largely unexamined. We systematically investigate how the marginal utility of additional reasoning tokens changes as compute budgets increase. We find that marginal returns diminish substantially at higher budgets and that models exhibit ``overthinking'', where extended reasoning is associated with abandoning previously correct answers. Furthermore, we show that optimal thinking length varies across problem difficulty, suggesting that uniform compute allocation is suboptimal. Our cost-aware evaluation framework reveals that stopping at moderate budgets can reduce computation significantly while maintaining comparable accuracy.

Shu Zhou, Rui Ling, Junan Chen +3

Nanjing University · Baidu · Nanjing University of Finance & Economics

Overthinking in Language Models Test-Time Scaling Efficient Language Model Reasoning

Apr 9, 2026

MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought

Large Language Models (LLMs) still suffer from severe hallucinations and catastrophic forgetting during causal reasoning over massive, fragmented long contexts. Existing memory mechanisms typically treat retrieval as a static, single-step passive matching process, leading to severe semantic dilution and contextual fragmentation. To overcome these fundamental bottlenecks, we propose MemCoT, a test-time memory scaling framework that redefines the reasoning process by transforming long-context reasoning into an iterative, stateful information search. MemCoT introduces a multi-view long-term memory perception module that enables Zoom-In evidence localization and Zoom-Out contextual expansion, allowing the model to first identify where relevant evidence resides and then reconstruct the surrounding causal structure necessary for reasoning. In addition, MemCoT employs a task-conditioned dual short-term memory system composed of semantic state memory and episodic trajectory memory. This short-term memory records historical search decisions and dynamically guides query decomposition and pruning across iterations. Empirical evaluations demonstrate that MemCoT establishes a state-of-the-art performance. Empowered by MemCoT, several open- and closed-source models achieve SOTA performance on the LoCoMo benchmark and LongMemEval-S benchmark.

Haodong Lei, Junming Liu, Yirong Chen +2

Southeast University Nanjing, Jiangsu, China · Shanghai Artificial Intelligence Laboratory Shanghai, China

Memory-Augmented Language Models Test-Time Scaling Causal Reasoning in Language Models

Apr 7, 2026

$S^3$ : Stratified Scaling Search for Test-Time in Diffusion Language Models

Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, naive best-of-

K

sampling is fundamentally limited because it repeatedly draws from the same base diffusion distribution, whose high-probability regions are often misaligned with high-quality outputs. We propose

S^3

(Stratified Scaling Search), a classical verifier-guided search method that improves generation by reallocating compute during the denoising process rather than only at the final output stage. At each denoising step,

S^3

expands multiple candidate trajectories, evaluates them with a lightweight reference-free verifier, and selectively resamples promising candidates while preserving diversity within the search frontier. This procedure effectively approximates a reward-tilted sampling distribution that favors higher-quality outputs while remaining anchored to the model prior. Experiments with LLaDA-8B-Instruct on MATH-500, GSM8K, ARC-Challenge, and TruthfulQA demonstrate that

S^3

consistently improves performance across benchmarks, achieving the largest gains on mathematical reasoning tasks while leaving the underlying model and decoding schedule unchanged. These results show that classical search over denoising trajectories provides a practical mechanism for test-time scaling in DLMs.

Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +6

University of Oklahoma · Stanford University · University of Göttingen +2

Test-Time Scaling Diffusion Language Model Decoding Diffusion Language Models

Apr 6, 2026

Decocted Experience Improves Test-Time Inference in LLM Agents

There is growing interest in improving LLMs without updating model parameters. One well-established direction is test-time scaling, where increased inference-time computation (e.g., longer reasoning, sampling, or search) is used to improve performance. However, for complex reasoning and agentic tasks, naively scaling test-time compute can substantially increase cost and still lead to wasted budget on suboptimal exploration. In this paper, we explore context as a complementary scaling axis for improving LLM performance, and systematically study how to construct better inputs that guide reasoning through experience. We show that effective context construction critically depends on decocted experience. We present a detailed analysis of experience-augmented agents, studying how to derive context from experience, how performance scales with accumulated experience, what characterizes good context, and which data structures best support context construction. We identify decocted experience as a key mechanism for effective context construction: extracting essence from experience, organizing it coherently, and retrieving salient information to build effective context. We validate our findings across reasoning and agentic tasks, including math reasoning, web browsing, and software engineering.

Maohao Shen, Kaiwen Zha, Zexue He +6

Massachusetts Institute of Technology · Stanford University · MIT-IBM Watson AI Lab +2

LLM Context Management Memory-Augmented Language Model Agents In-Context Learning Test-Time Scaling

Apr 3, 2026

FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models

Recent Large Reasoning Models (LRMs) like DeepSeek-R1 have demonstrated remarkable success in complex reasoning tasks, exhibiting human-like patterns in exploring multiple alternative solutions. Upon closer inspection, however, we uncover a surprising phenomenon: The First is The Best, where alternative solutions are not merely suboptimal but potentially detrimental. This observation challenges widely accepted test-time scaling laws, leading us to hypothesize that errors within the reasoning path scale concurrently with test time. Through comprehensive empirical analysis, we characterize errors as a forest-structured Forest of Errors (FoE) and conclude that FoE makes the First the Best, which is underpinned by rigorous theoretical analysis. Leveraging these insights, we propose RED, a self-guided efficient reasoning framework comprising two components: I) Refining First, which suppresses FoE growth in the first solution; and II) Discarding Subs, which prunes subsequent FoE via dual-consistency. Extensive experiments across five benchmarks and six backbone models demonstrate that RED outperforms eight competitive baselines, achieving performance gains of up to 19.0% while reducing token consumption by 37.7% ~ 70.4%. Moreover, comparative experiments on FoE metrics shed light on how RED achieves effectiveness.

Kehan Jiang, Haonan Dong, Zhaolu Kang +2

School of Software and Microelectronics, Peking University · State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University

Efficient Language Model Reasoning Large Reasoning Models Test-Time Scaling Reasoning Consistency in Language Models

Apr 2, 2026

Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets

Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation. When computation is normalized, single-agent systems (SAS) can match or outperform MAS, yet the theoretical basis and evaluation methodology behind this comparison remain unclear. We present an information-theoretic argument, grounded in the Data Processing Inequality, suggesting that under a fixed reasoning-token budget and with perfect context utilization, single-agent systems are more information-efficient. This perspective further predicts that multi-agent systems become competitive when a single agent's effective context utilization is degraded, or when more compute is expended. We test these predictions in a controlled empirical study across three model families (Qwen3, DeepSeek-R1-Distill-Llama, and Gemini 2.5), comparing SAS with multiple MAS architectures under matched budgets. We find that SAS consistently match or outperform MAS on multi-hop reasoning tasks when reasoning tokens are held constant. Beyond aggregate performance, we conduct a detailed diagnostic analysis of system behavior and evaluation methodology. We identify significant artifacts in API-based budget control (particularly in Gemini 2.5) and in standard benchmarks, both of which can inflate apparent gains from MAS. Overall, our results suggest that, for multi-hop reasoning tasks, many reported advantages of multi-agent systems are better explained by unaccounted computation and context effects rather than inherent architectural benefits, and highlight the importance of understanding and explicitly controlling the trade-offs between compute, context, and coordination in agentic systems.

Dat Tran, Douwe Kiela

Stanford University

Multi-Agent LLM Systems Multi-Agent Systems Multi-Agent Reasoning AI Agent Benchmarks Test-Time Scaling Multi-Hop Reasoning

Apr 1, 2026

Test-Time Scaling Makes Overtraining Compute-Optimal

Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling laws, such as Chinchilla, do not address. We present Train-to-Test (

T^2

) scaling laws that jointly optimize model size, training tokens, and number of inference samples under fixed end-to-end budgets.

T^2

modernizes pretraining scaling laws with pass@

k

modeling used for test-time scaling, then jointly optimizes pretraining and test-time decisions. Forecasts from

T^2

are robust over distinct modeling approaches: measuring joint scaling effect on the task loss and modeling impact on task accuracy. Across eight downstream tasks, we find that when accounting for inference cost, optimal pretraining decisions shift radically into the overtraining regime, well-outside of the range of standard pretraining scaling suites. We validate our results by pretraining heavily overtrained models in the optimal region that

T^2

scaling forecasts, confirming their substantially stronger performance compared to pretraining scaling alone. Finally, as frontier LLMs are post-trained, we show that our findings survive the post-training stage, making

T^2

scaling meaningful in modern deployments.

Nicholas Roberts, Sungjun Cho, Zhiqi Gao +7

University of Wisconsin-Madison · Stanford University

Scaling Laws Language Model Scaling Laws Test-Time Scaling LLM Training Language Model Pretraining

Apr 1, 2026

Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming

We study how to scale reasoning token budgets for competitive programming through two complementary approaches: training-time reinforcement learning (RL) and test-time parallel thinking. During RL training, we observe an approximately log-linear relationship between validation accuracy and the average number of generated reasoning tokens over successive checkpoints, and show two ways to shift this training trajectory: verification RL warmup raises the starting point, while randomized clipping produces a steeper trend in the observed regime. As scaling single-generation reasoning during RL quickly becomes expensive under full attention, we introduce a multi-round parallel thinking pipeline that distributes the token budget across threads and rounds of generation, verification, and refinement. We train the model end-to-end on this pipeline to match the training objective to the test-time structure. Starting from Seed-OSS-36B, the full system with 16 threads and 16 rounds per thread matches the underlying RL model's oracle pass@16 at pass@1 using 7.6 million tokens per problem on average, and surpasses GPT-5-high on 456 hard competitive programming problems from AetherCode.

Qianfan Zhang, Tianyu Guo, Xuandi Ren +4

Princeton University · UC Berkeley · Stanford University +1

Test-Time Scaling Large Reasoning Models RL for Code Generation Competitive Programming

Mar 30, 2026

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world problems. To sustain this capability on long-horizon tasks, reliable verification is critical during both training and inference. A major bottleneck in existing paradigms stems from the lack of explicit verification mechanisms in QA data synthesis, trajectory construction, and test-time scaling. Errors introduced at each stage propagate downstream and degrade the overall agent performance. To address this, we present Marco DeepResearch, a deep research agent optimized with a verification-centric framework design at three levels: (1)~QA Data Synthesis: We introduce verification mechanisms to graph-based and agent-based QA synthesis to control question difficulty while ensuring answers are unique and correct; (2)~Trajectory Construction: We design a verification-driven trajectory synthesis method that injects explicit verification patterns into training trajectories; and (3)~Test-time scaling: We use Marco DeepResearch itself as a verifier at inference time and effectively improve performance on challenging questions. Extensive experimental results demonstrate that our proposed Marco DeepResearch agent significantly outperforms 8B-scale deep research agents on most challenging benchmarks, such as BrowseComp and BrowseComp-ZH. Crucially, under a maximum budget of 600 tool calls, Marco DeepResearch even surpasses or approaches several 30B-scale agents, like Tongyi DeepResearch-30B.

Bin Zhu, Qianghuai Jia, Tian Lan +6

Alibaba International Digital Commerce

Deep Research Agents LLM Agent Training LLM Agent Verification Test-Time Scaling

Mar 29, 2026

Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3

Majority voting over multiple LLM attempts improves mathematical reasoning, but correlated errors limit the effective sample size. A natural fix is to assign different reasoning strategies to different voters. The approach, Diverse Prompt Mixer, is tested on the AIMO 3 competition: 3 models, 23+ experiments, 50 IMO-level problems, one H100 80 GB, 5-hour limit. Every prompt-level intervention fails. High-temperature sampling already decorrelates errors; weaker strategies reduce accuracy more than they reduce correlation. Across an 8-point capability gap at equal N=8 and every optimization tested, model capability dominates. The gap between the best majority-vote score (42/50) and pass@20 (~45.5) is selection loss, not prompt loss. A verifier-based selector could close it. Prompt engineering cannot.

Natapong Nitarach

LLM Reasoning LLM Prompting Language Model Ensembles Test-Time Scaling Self-Consistency Decoding

Mar 24, 2026

Caterpillar of Thoughts: The Optimal Test-Time Algorithm for Large Language Models

Large language models (LLMs) can often produce substantially better outputs when allowed to use additional test-time computation, such as sampling, chain of thought, backtracking, or revising partial solutions. Despite the growing empirical success of such techniques, there is limited theoretical understanding of how inference time computation should be structured, or what constitutes an optimal use of a fixed computation budget. We model test-time computation as an algorithm interacting with a Markov chain: at any point, the algorithm may resume generation from any previously observed state. That is, unlike standard Markov chains where the states are drawn passively, we allow the algorithm to backtrack to any previously observed state of the Markov chain at any time. Many of the existing test-time algorithms, such as Chain-of-Thought (CoT) (Wei et al., 2023), Tree-of-Thoughts (ToT) (Yao et al., 2023), or Best-of-

k

(Brown et al., 2024) could be seen as specific algorithms in this model. We prove that while backtracking can reduce the number of generations exponentially, a very limited form of backtracking is theoretically sufficient. Namely, we show that the optimal algorithm always generates a caterpillar tree. That is, if we remove the leaves of the state tree generated by the optimal algorithm, we obtain a path. Motivated by our characterization of the optimal algorithm, we present Caterpillar of Thoughts (CaT), a new test-time computation algorithm, reducing the number of token/state generations. Our empirical evaluation shows that CaT, compared to ToT, achieves a better success rate while also reducing the number of token generations.

Amir Azarmehr, Soheil Behnezhad, Alma Ghafari

Northeastern University

Inference-Time Optimization Efficient Language Model Reasoning Test-Time Scaling LLM Inference Acceleration

Mar 19, 2026

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must culminate in formally structured expressions. Yet, current LM evaluations of mathematical and scientific reasoning rely heavily on simplified answer formats such as numerical values or multiple choice options due to the convenience of automated assessment. In this paper we provide three contributions for improving reasoning over mathematical objects: (i) we build and release training data and benchmarks for deriving mathematical objects, the Principia suite; (ii) we provide training recipes with strong LLM-judges and verifiers, where we show that on-policy judge training boosts performance; (iii) we show how on-policy training can also be used to scale test-time compute via aggregation. We find that strong LMs such as Qwen3-235B and o3 struggle on Principia, while our training recipes can bring significant improvements over different LLM backbones, while simultaneously improving results on existing numerical and MCQA tasks, demonstrating cross-format generalization of reasoning abilities.

Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim +18

FAIR at Meta · CMU · UCLA

LLM Mathematical Reasoning Mathematical Reasoning Benchmarks LLM Post-Training Reward Modeling Test-Time Scaling

Mar 15, 2026

Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements

Multimodal Large Language Model (MLLM)-based Graphical User Interface (GUI) agents develop rapidly, with visual grounding that maps natural language instructions to target UI elements serving as the core capability. Existing GUI agents typically fine-tune MLLM on massive datasets to handle challenges in understanding instructions and UI interfaces, which not only incurs high data annotation costs but also makes performance dependent on data quality and distribution. To avoid such cumbersome yet ineffective training, we notice that complex UI interfaces can be decomposed into basic visual elements directly understandable by common MLLMs. Consequently, we propose ZoomUI that leverages inference scaling to guide common MLLMs in progressively anchor instruction elements to increasingly detailed interface elements. Specifically, ZoomUI first optimizes the latent thinking to transform original instruction into element visual features description, and subsequently leverages internal attention to iteratively zoom in target element interface region. Evaluations on extensive benchmarks demonstrate that ZoomUI reaches or even surpasses SOTA baselines.

Ziwei Liu, Tao Feng, Borui Kang +2

Department of Computer Science and Technology, Sichuan University, China · Department of Computer Science and Technology, Tsinghua University, China · School of Computer Science, Nanjing University, China +1

GUI Agents GUI Grounding Multimodal Large Language Models Test-Time Scaling

Mar 11, 2026

Ranking Reasoning LLMs under Test-Time Scaling

Test-time scaling evaluates reasoning LLMs by sampling multiple outputs per prompt, but ranking models in this regime remains underexplored. We formalize dense benchmark ranking under test-time scaling and introduce Scorio, a library that implements statistical ranking methods such as paired-comparison models, item response theory (IRT) models, voting rules, and graph- and spectral-based methods. Across

20

reasoning models on four Olympiad-style math benchmarks (AIME'24, AIME'25, HMMT'25, and BrUMO'25; up to

N=80

trials), most full-trial rankings agree closely with the Bayesian gold standard

\mathrm{Bayes}_{\mathcal{U}}@80

(mean Kendall's

τ_b = 0.93

--

0.95

), and

19

--

34

methods recover exactly the same ordering. In the single-trial regime, the best methods reach

τ_b \approx 0.86

. Using greedy decoding as an empirical prior (

\mathrm{Bayes}_{\mathbf{R}_0}@N

) reduces variance at

N=1

by

16

--

52\%

, but can bias rankings when greedy and stochastic sampling disagree. These results identify reliable ranking methods for both high- and low-budget test-time scaling. We release Scorio as an open-source library at https://github.com/mohsenhariri/scorio.

Mohsen Hariri, Michael Hinczewski, Jing Ma +1

Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH, USA · Department of Physics, Case Western Reserve University, Cleveland, OH, USA

LLM Evaluation Test-Time Scaling

Mar 4, 2026

$V_1$ : Unifying Generation and Self-Verification for Parallel Reasoners

Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in significantly better task outcomes. However, a critical bottleneck is verification: sampling is only effective if correct solutions can be reliably identified among candidates. While existing approaches typically evaluate candidates independently via scalar scoring, we demonstrate that models are substantially stronger at pairwise self-verification. Leveraging this insight, we introduce

V_1

, a framework that unifies generation and verification through efficient pairwise ranking.

V_1

comprises two components:

V_1

-Infer, an uncertainty-guided algorithm using a tournament-based ranking that dynamically allocates self-verification compute to candidate pairs whose relative correctness is most uncertain; and

V_1

-PairRL, an RL framework that jointly trains a single model as both generator and pairwise self-verifier, ensuring the verifier adapts to the generator's evolving distribution. On code generation (LiveCodeBench, CodeContests, SWE-Bench) and math reasoning (AIME, HMMT) benchmarks,

V_1

-Infer improves Pass@1 by up to

10%

over pointwise verification and outperforms recent test-time scaling methods while being significantly more efficient. Furthermore,

V_1

-PairRL achieves

7

--

9%

test-time scaling gains over standard RL and pointwise joint training, and improves base Pass@1 by up to 8.7% over standard RL in a code-generation setting.

Harman Singh, Xiuyu Li, Kusha Sareen +14

UC Berkeley · Mila · Together AI +1

Test-Time Scaling RL for Language Model Reasoning RL for Code Generation

Mar 3, 2026

Parallel Test-Time Scaling with Multi-Sequence Verifiers

Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it is hindered by two key bottlenecks: accurately selecting the correct solution from the candidate pool, and the high inference latency from generating many full solutions. We argue that both challenges are fundamentally linked to verifier calibration, as a well-calibrated verifier improves answer selection and enables early-stopping strategies to reduce latency. However, existing non-generative verifiers are limited as they score each candidate in isolation, overlooking rich contextual information across the set of candidates. To address this, we introduce the Multi-Sequence Verifier (MSV), a lightweight verifier that predicts each candidate's correctness conditioned on the full sampled set. MSV achieves improved calibration, which directly enhances best-of-N selection performance and empowers a novel early-stopping framework. Across challenging mathematical reasoning benchmarks, MSV improves best-of-64 accuracy by up to 6% relative to strong baselines, and in the early-stopping setting reaches the same accuracy as baselines with less than half the latency.

Yegon Kim, Seungyoo Lee, Chaeyun Jang +2

Graduate School of AI, KAIST, Seoul, South Korea

LLM Answer Verification Test-Time Scaling LLM Inference Efficiency

Mar 3, 2026

Form Follows Function: Recursive Stem Model

Recursive reasoning models such as Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM) show that small, weight-shared networks can solve compute-heavy and NP puzzles by iteratively refining latent states, but their training typically relies on deep supervision and/or long unrolls that increase wall-clock cost and can bias the model toward greedy intermediate behavior. We introduce Recursive Stem Model (RSM), a recursive reasoning approach that keeps the TRM-style backbone while changing the training contract so the network learns a stable, depth-agnostic transition operator. RSM fully detaches the hidden-state history during training, treats early iterations as detached "warm-up" steps, and applies loss only at the final step. We further grow the outer recursion depth

H

and inner compute depth

L

independently and use a stochastic outer-transition scheme (stochastic depth over

H

) to mitigate instability when increasing depth. This yields two key capabilities: (i)

>20\times

faster training than TRM while improving accuracy (

\approx 5\times

reduction in error rate), and (ii) test-time scaling where inference can run for arbitrarily many refinement steps (

\sim 20,000 H_{\text{test}} \gg 20 H_{\text{train}}

), enabling additional "thinking" without retraining. On Sudoku-Extreme, RSM reaches 97.5% exact accuracy with test-time compute (within ~1 hour of training on a single A100), and on Maze-Hard (

30 \times 30

) it reaches ~80% exact accuracy in ~40 minutes using attention-based instantiation. Finally, because RSM implements an iterative settling process, convergence behavior provides a simple, architecture-native reliability signal: non-settling trajectories warn that the model has not reached a viable solution and can be a guard against hallucination, while stable fixed points can be paired with domain verifiers for practical correctness checks.

Navid Hakimi

Neural Algorithmic Reasoning Algorithmic Reasoning Test-Time Scaling