Efficient Language Model Inference

Ask about this topic

Overview

The field studies how to serve language models with less computation, memory, time, and energy while preserving useful outputs. Approaches include quantization and sparsity, faster decoding such as speculative and parallel generation, KV-cache and context compression, and smaller or specialized models routed to tasks they can handle. For reasoning models, early stopping and adaptive compute allocation aim to spend more tokens on difficult questions and fewer on easy ones. The central challenge is that savings depend on the model, workload, hardware, and serving setup, and reducing token counts or latency does not always reduce total cost or energy without harming accuracy or reliability.

Latest papers

CardsList

321 papers64 papers in the last four weeks, up 68% on the four weeks before. 0.4% of all new papers.

May 9, 2026

Reasoning Compression with Mixed-Policy Distillation

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, when solving the same problems, larger reasoning models can often produce more concise traces, whereas smaller reasoning models tend to generate longer and more redundant trajectories. This is especially problematic in real-world deployment, where memory, latency, and serving-cost constraints often favor smaller models. Our observations suggest that reasoning compression can be transferred from large models to small ones rather than enforced through explicit length constraints. Based on this insight, we propose Mixed-Policy Distillation (MPD), a reasoning compression framework that transfers concise reasoning behavior from a larger-sized teacher to a smaller student by distilling teacher-compressed student trajectories. Unlike on-policy distillation, which aligns the student with teacher distributions over verbose student trajectories, or off-policy distillation, which relies on teacher-generated trajectories and may suffer from distribution mismatch, MPD combines the strengths of both. Given a student-sampled trajectory, the teacher rewrites it into a more concise reasoning trace, and the student is trained via KL-based alignment on the compressed trajectory. This preserves student-policy exploration while injecting teacher-guided compression. Experiments on Qwen3-1.7B show that MPD reduces token usage by up to 27.1% while improving performance across multiple reasoning benchmarks, demonstrating an effective approach to efficient small-model reasoning.

Han Yang, Mingyan Wu, Bailan He +4

Technical University of Munich · GESIS – Leibniz Institute for the Social Sciences · Northeastern University +5

Language Model DistillationEfficient Language Model InferencePolicy DistillationCoT CompressionLarge Reasoning Models
AskPDF
May 9, 2026

Hint Tuning: Less Data Makes Better Reasoners

Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning uniformly regardless of problem difficulty. We propose Hint Tuning, a data-efficient approach that teaches models to calibrate reasoning depth. Our key insight: the corresponding instruct model serves as an ideal difficulty probe. By testing what the instruct model can solve with varying guidance, we automatically construct training data across three states: No-Hint (direct answer), Sparse-Hint (minimal prefix), and Full-Hint (complete reasoning). This converts the abstract challenge of difficulty labeling into a measurable consistency check between the instruct and reasoning models. With only 1K self-annotated samples, Hint Tuning achieves 24--66% token reduction (31.5% average) across mainstream reasoning models (Qwen3-Thinking, DeepSeek-R1-Distill) at multiple scales (4B--32B) while maintaining competitive accuracy on five benchmarks. Unlike methods requiring massive distillation datasets or expensive RL, we achieve superior efficiency through simple alignment with the instruct model's capabilities. Code and data are available at https://github.com/redai-infra/hint-tuning.

Siqi Fan, Minghao Li, Xiaoqian Ma +6

University of Electronic Science and Technology of China · Xiaohongshu Inc. · National University of Singapore

Overthinking in Language ModelsLLM Fine-TuningEfficient Language Model ReasoningEfficient Language Model InferenceLarge Reasoning Models
AskPDF
May 8, 2026

Reliable Chain-of-Thought via Prefix Consistency

Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority voting (MV), a test-time technique called self-consistency. When we truncate a CoT partway through and regenerate the remainder, we observe that traces with correct answers reproduce their original answer more often than traces with wrong answers. We use this difference as a reliability signal, prefix consistency, that weights each candidate answer by how often it reappears under regeneration. It requires no access to token log-probabilities or self-rating prompts. Across five reasoning models and four math and science benchmarks, prefix consistency is the best correctness predictor in most settings, and reweighting votes by it reaches Standard MV plateau accuracy at up to 21x fewer tokens (median 4.6x). Our code is available at https://github.com/naoto-iwase/prefix-consistency.

Naoto Iwase, Yuki Ichihara, Mohammad Atif Quamar +1

Nagoya University · Nara Institute of Science and Technology · Mohamed bin Zayed University of Artificial Intelligence +1

Self-Consistency DecodingReasoning Consistency in Language ModelsLLM ReliabilityEfficient Language Model InferenceSelf-Consistency in Language ModelsLLM Reasoning+2
AskPDF
May 8, 2026

Confidence-Aware Alignment Makes Reasoning LLMs More Reliable

Large reasoning models often reach correct answers through flawed intermediate steps, creating a gap between final accuracy and reasoning reliability. Existing alignment strategies address this with external verifiers or massive sampling, limiting scalability. In this work, we introduce CASPO (Confidence-Aware Step-wise Preference Optimization), a framework that aligns token-level confidence with step-wise logical correctness through iterative Direct Preference Optimization, without training a separate reward model. During inference, we propose Confidence-aware Thought (CaT), which leverages this calibrated confidence to dynamically prune uncertain reasoning branches with negligible O(V) latency. Experiments across ten benchmarks and multiple model families show that CASPO consistently improves reasoning reliability and inference efficiency. CASPO scales to Qwen3-8B-Base and surpasses tree-search baselines on AIME'24 and AIME'25 without using reward-model data. We also release a step-wise dataset with confidence annotations to support fine-grained analysis of reasoning reliability. Code is available at https://github.com/Thecommonirin/CASPO.

Kejia Chen, Jiawen Zhang, Yihong Wu +5

Zhejiang University · Université de Montréal · Sun Yat-sen University +1

LLM AlignmentDirect Preference OptimizationEfficient Language Model ReasoningLanguage Model CalibrationLLM ReliabilityLLM Uncertainty Estimation+2
AskPDF
May 7, 2026

A Few Good Clauses: Comparing LLMs vs Domain-Trained Small Language Models on Structured Contract Extraction

This paper evaluates whether a domain trained Small Language Model (SLM) can outperform frontier Large Language Models on structured contract extraction at radically lower cost. We test Olava Extract, a self hosted legal domain Mixture of Experts model, against five frontier models. Olava Extract achieved the strongest aggregate performance in the study, with a macro F1 of 0.812 and a micro F1 of 0.842, while reducing inference cost by 78% to 97% compared with the frontier models tested. It also achieved the highest precision scores, producing fewer hallucinated and unsupported extractions, an important distinction in legal workflows where hallucinations create operational risk and downstream review burden. The findings shows that high performing, human comparable legal AI no longer requires the largest externally hosted models. More broadly, they challenge the assumption that commercially valuable enterprise AI capability must remain tied to ever larger models, massive infrastructure expenditure, and centrally hosted providers.

Nicole Lincoln, Nick Whitehouse, Jaron Mar +1

Onit AI Labs, Onit Inc., New Zealand

Legal NLPMixture-of-Experts Language ModelsDocument Information ExtractionSmall Language ModelsLLM Information ExtractionEfficient Language Model Inference
AskPDF
May 6, 2026

SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States

Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can process millions of token contexts end-to-end, but they suffer from high token consumption and attention dilution. In parallel, specialized LTU agents often sacrifice fidelity through task-agnostic abstractions like graph construction or indexing. We identify a key insight for LTU: query-relevant information is typically sparse relative to the full document, so effective reasoning should rely on a query-sufficient subset rather than the entire context. To address this, we propose SCOUT, a new paradigm for LTU that shifts from passive processing to active information foraging. It treats the document as an explorable environment and answers from a compact, provenance-grounded epistemic state. Guided by state-level gap diagnosis, SCOUT adaptively alternates between coarse-to-fine exploration and anchored state updates that progressively contract its epistemic state toward query sufficiency. Experiments show that SCOUT matches state-of-the-art proprietary models while reducing token consumption by up to 8x. Moreover, SCOUT remains stable as context length scales, substantially alleviating the practical cost-performance trade-off.

Zhenliang Zhang, Wenqing Wang, Yong Hu +4

Peking University · WeChat, Tencent · Work done during an internship at WeChat, Tencent

Document UnderstandingLong-Context QAInformation RetrievalLong-Context InferenceEfficient Language Model Inference
AskPDF
May 4, 2026

Gated Subspace Inference for Transformer Acceleration

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and a residual, computes the linear-layer output on the subspace component via a cached low-rank weight image at reduced memory bandwidth, and applies a per-token gate that determines whether the residual correction is computed or skipped. The gate ensures that the output distribution is preserved to within a controllable tolerance. Validation on three model families (GPT-2 124M, GPT-J 6B, OPT 6.7B) on AMD MI300X demonstrates effective speedups of 3.0x to 10.5x on linear-layer weight reads with perplexity ratios below 1.00 and top-1 token agreement above 98%. The method requires no retraining, no architectural modification, and no approximation of the attention mechanism. At the operating point (k = 256, ε = 0.05) on GPT-J 14 6B, the accelerated model produces character-for-character identical output to the baseline.

Stephen J. Thomas

Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015

Transformer InferenceLLM Inference AccelerationEfficient Language Model Inference
AskPDF
May 1, 2026

When Less is Enough: Efficient Inference via Collaborative Reasoning

In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightweight model work together to solve a task. Relying on a single large model to perform end-to-end reasoning and prediction often incurs substantial inference cost. In contrast, DUET decomposes inference into two stages: the capable model produces a reasoning signal, and the lightweight model interprets this signal to generate the final answer, allowing reasoning-intensive computation to be handled by the capable model while non-reasoning-intensive components are delegated to the lightweight model without sacrificing task performance. To achieve this objective, we propose a length-penalized joint training objective that encourages the capable model to transmit only the information that is sufficient for the lightweight model to solve the task. As a result, DUET maintains strong reasoning performance with substantially lower inference cost than end-to-end inference using a large model alone, saving up to 60% of the large model's output tokens on challenging reasoning benchmarks, including AIME and GPQA.

Yilei Chen, Sharut Gupta, Yannis Paschalidis +2

Boston University · MIT CSAIL · Biohub

Efficient Language Model ReasoningEfficient Language Model InferenceLLM ReasoningLarge Reasoning Models
AskPDF
May 1, 2026

Component-Aware Self-Speculative Decoding in Hybrid Language Models

Speculative decoding accelerates autoregressive inference by drafting candidate tokens with a fast model and verifying them in parallel with the target. Self-speculative methods avoid the need for an external drafter but have been studied exclusively in homogeneous Transformer architectures. We introduce component-aware self-speculative decoding, the first method to exploit the internal architectural heterogeneity of hybrid language models, isolating the SSM/linear-attention subgraph as a zero-cost internal draft. We evaluate this on two architecturally distinct hybrid families: Falcon-H1 (parallel: Mamba-2 + attention per layer) and Qwen3.5 (sequential: interleaved linear and attention layers), with a pure Transformer control (Qwen2.5). Parallel hybrids achieve acceptance rates of alpha = 0.68 at draft length k=2 under greedy decoding, while sequential hybrids yield only alpha = 0.038 -- an 18x gap attributable to how each architecture integrates its components. The property is scale-invariant: Falcon-H1 at 3B reproduces the rates observed at 0.5B. We further show that perplexity degradation from a companion ablation study predicts speculative viability without running speculative decoding: a 3.15x ratio (Falcon) maps to alpha = 0.37 at k=4, while 81.96x (Qwen) maps to alpha = 0.019. For sequential hybrids, generic LayerSkip achieves 12x higher acceptance rates than the component-aware strategy. The composition pattern of hybrid models -- not merely the presence of alternative components -- determines whether component-level self-speculation is viable.

Hector Borobia, Elies Seguí-Mas, Guillermina Tormo-Carbó

VRAIN – Valencian Research Institute for Artificial Intelligence, Universitat Politècnica de València, Valencia, Spain · Department of Economics and Social Sciences, Universitat Politècnica de València, Valencia, Spain · Department of Business Organisation, Universitat Politècnica de València, Valencia, Spain

Speculative DecodingLanguage ModelingEfficient Language Model InferenceHybrid Language Models
AskPDF
May 1, 2026

Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding

Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for sparse Mixture-of-Experts (MoE) models. As the draft tree grows, different branches activate different experts, expanding the union of activated experts and substantially increasing target-side verification cost. We propose EVICT, a training-free, hyperparameter-free, and lossless adaptive verification method for MoE speculative decoding. EVICT makes every verified token count by truncating the draft tree before target verification and retaining only the cost-effective prefix. It leverages fine-grained drafter signals to estimate candidate benefit, combines them with offline-profiled verification cost, and remains highly compatible with the high-performance graph-based serving framework SGLang. Extensive experiments on diverse MoE backbones and benchmarks show that EVICT achieves up to 2.35x speedup over autoregressive decoding and an average 1.21x speedup over the state-of-the-art baseline EAGLE-3, while significantly reducing unnecessary expert activations during verification.

Lehan Pan, Ziyang Tao, Ruoyu Pang +3

University of Science and Technology of China · Tianyijiaotong Technology Ltd., Suzhou, China

Mixture-of-Experts InferenceSpeculative DecodingEfficient Language Model Inference
AskPDF
Apr 29, 2026

Select to Think: Unlocking SLM Potential with Local Sufficiency

Small language models (SLMs) offer efficient deployment, yet they often lag behind their larger counterparts (LLMs) in reasoning. Existing remedies either invoke an LLM at points of reasoning divergence, incurring substantial latency and cost, or rely on standard distillation, which is limited by the SLM's capacity to accurately mimic the LLM's complex generative distribution. We address this dilemma by identifying local sufficiency: at divergence points, the LLM's preferred token often resides within the SLM's top-K next-token predictions, even when failing to emerge as the SLM top-1 choice. We therefore propose Select to Think (S2T), which reframes the LLM's role from open-ended generation to selection among the SLM's proposals, simplifying the supervision signal to discrete candidate rankings. Leveraging this, we introduce S2T-Local, which distills the selection logic into the SLM, empowering it to perform autonomous re-ranking without inference-time LLM dependency. Empirically, a 1.5B SLM's top-8 candidates contain the 32B LLM's choice with a 95% hit rate, and S2T-Local improves the 1.5B SLM's Math Avg. over greedy decoding by 24.1% relative gain, matching the efficacy of 8-path self-consistency with single-trajectory efficiency.

Wenxuan Ye, Yangyang Zhang, Xueli An +2

1Technical University of Munich · 3Ludwig Maximilian University of Munich · 2Huawei Technologies +2

Small Language ModelsEfficient Language Model ReasoningLLM RerankingLanguage Model DistillationEfficient Language Model InferenceLLM Reasoning
AskPDF
Apr 27, 2026

Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs

Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still struggle with multi-step reasoning under tight compute and token budgets. Existing test time reasoning methods such as self consistency (sampling multiple rationales and voting), Tree-of-Thoughts (search over intermediate thoughts), and critique revise loops improve performance, but often at high token cost and without fine-grained step-level control. This project1 aims to address that gap: can Small Language Models (SLMs) reason reliably using the same or fewer tokens? This question is both scientific and practical. Scientifically, it probes whether process supervision and simple test-time controls (such as token budgets and rejection of redundant steps) can substitute for model scale or large sampling counts. Practically, many deployments (on-device, low-latency, or cost-constrained settings) cannot afford huge models or dozens of sampled rationales per query. A method that improves SLM reasoning at fixed cost would therefore be directly useful.

Sagnik Chatterjee, Atharva Patil, Sricharan Ramesh

CoT ReasoningSmall Language ModelsEfficient Language Model ReasoningProcess SupervisionEfficient Language Model InferenceLLM Reasoning
AskPDF
Apr 27, 2026

Nautile-370M: Spectral Memory Meets Attention in a Small Reasoning Model

We present Nautile-370M, a 371-million-parameter small language model designed for efficient reasoning under strict parameter and inference budgets. Nautile-370M uses a hybrid backbone in which two SeqCond Attention (SCA) layers, a linear-time spectral sequence operator inspired by SeqCondenser, alternate with one transformer layer. This design aims to retain the long-context efficiency and state-tracking benefits of structured sequential models while preserving the expressive token-to-token routing of attention. The model was trained on a single Cloud TPU v4-64 pod slice provided through the Google TPU Research Cloud (TRC) program; the subsequent reinforcement learning stage was carried out on a single NVIDIA DGX Spark. We prove that the SCA readout mechanism can exactly retrieve any individual token from the prefix summary and can reproduce any output of softmax attention as a special case, establishing that SCA is at least as expressive as full self-attention in the continuous limit. We also describe the training data pipeline and outline a reinforcement learning stage specialized for reasoning, verification, and response quality.

Maixent Chenebaux

Trickstr

Self-AttentionSmall Language ModelsAttention MechanismsEfficient Language Model InferenceNeural Network Expressivity
AskPDF
Apr 27, 2026

Stabilizing Efficient Reasoning with Step-Level Advantage Selection

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead through length-based rewards or pruning, many approaches are post-trained under a much shorter context window than base-model training, a factor whose effect has not been systematically isolated. We first show that short-context post-training alone, using standard GRPO without any length-aware objective, already induces substantial reasoning compression-but at the cost of increasingly unstable training dynamics and accuracy degradation. To address this, we propose Step-level Advantage Selection (SAS), which operates at the reasoning-step level and assigns a zero advantage to low-confidence steps in correct rollouts and to high-confidence steps in verifier-failed rollouts, where failures often arise from truncation or verifier issues rather than incorrect reasoning. Across diverse mathematical and general reasoning benchmarks, SAS improves average Pass@1 accuracy by 0.86 points over the strongest length-aware baseline while reducing average reasoning length by 16.3%, yielding a better accuracy-efficiency trade-off.

Han Wang, Xiaodong Yu, Jialian Wu +4

UNC Chapel Hill · Advanced Micro Devices, Inc.

RL for Language Model ReasoningEfficient Language Model ReasoningEfficient Language Model InferenceFine-Grained Credit AssignmentLarge Reasoning Models
AskPDF
Apr 24, 2026

Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought

While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal reasoning methods have emerged with shorter generation lengths by leveraging continuous representations, yet their performance lags behind verbalized CoT. We propose Abstract Chain-of-Thought\textbf{Abstract Chain-of-Thought}, a discrete latent reasoning post-training mechanism in which the language model produces a short sequence of tokens from a reserved vocabulary in lieu of a natural language CoT, before generating a response. To make previously unseen ''abstract'' tokens useful, we introduce a policy iteration-style warm-up loop that alternates between (i.) bottlenecking from a verbal CoT via masking and performing supervised fine-tuning, and (ii.) self-distillation by training the model to generate abstract tokens from the prompt alone via constrained decoding with the codebook. After warm-up, we optimize the generation of abstract sequences with warm-started reinforcement learning under constrained decoding. Abstract-CoT achieves up to 11.6×11.6\times fewer reasoning tokens while demonstrating comparable performance across mathematical reasoning, instruction-following, and multi-hop reasoning, and generalizes across language model families. We also find an emergent power law distribution over the abstract vocabulary, akin to those seen in natural language, that evolves across the training phases. Our findings highlight the potential for post-training latent reasoning mechanisms that enable efficient inference through a learned abstract reasoning language.

Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo

IBM Research AI

Efficient Language Model ReasoningImplicit Reasoning in Language ModelsEfficient Language Model InferenceLanguage Model Post-TrainingLLM ReasoningLatent Reasoning+1
AskPDF
Apr 23, 2026

An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation

This paper presents a highly efficient Retrieval-Augmented Generation (RAG) system built specifically for Ukrainian document question answering, which achieved 2nd place in the UNLP 2026 Shared Task. Our solution features a custom two-stage search pipeline that retrieves relevant document pages, paired with a specialized Ukrainian language model fine-tuned on synthetic data to generate accurate, grounded answers. Finally, we compress the model for lightweight deployment. Evaluated under strict computational limits, our architecture demonstrates that high-quality, verifiable AI question answering can be achieved locally on resource-constrained hardware without sacrificing accuracy.

Mykola Trokhymovych, Yana Oliinyk, Nazarii Nyzhnyk

Pompeu Fabra University · Independent Researcher

Retrieval-Augmented GenerationHybrid RetrievalEfficient Language Model Inference
AskPDF
Apr 23, 2026

Thinking with Reasoning Skills: Fewer Tokens, More Accuracy

Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration, and to retrieve these skills at inference time to guide future reasoning. Unlike the prevailing reasoning from scratch paradigm, our approach first recalls relevant skills for each query, helping the model avoid redundant detours and focus on effective solution paths. We evaluate our method on coding and mathematical reasoning tasks, and find that it significantly reduces reasoning tokens while improving overall performance. The resulting lower per-request cost indicates strong practical and economic potential for real-world deployment.

Guangxiang Zhao, Qilong Shi, Xusen Xiao +3

Qiyuan Tech · Tsinghua University · The University of Hong Kong +1

Efficient Language Model ReasoningEfficient Language Model InferenceLLM Mathematical ReasoningLLM Reasoning
AskPDF
Apr 22, 2026

TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that LRMs are still inefficient, over-generating verification and reflection steps. Additionally, the high-level role of each reasoning step and how different step types contribute to the generation of correct answers, is largely underexplored. To address this challenge, we introduce TRACES (Tagging of the Reasoning steps enabling Adaptive Cost-Efficient early-Stopping), a lightweight framework that tags reasoning steps in real-time, and enable adaptive, cost-efficient early stopping of large-language-model inferences. Building on this framework we monitor reasoning behaviors during inferences, and we find that LRMs tend to shift their reasoning behavior after reaching a correct answer. We demonstrate that the monitoring of the specific type of steps can produce effective interpretable early stopping criteria. We evaluate the TRACES framework on three mathematical reasoning benchmarks, namely, MATH500, GSM8K, AIME and two knowledge and reasoning benchmarks, MMLU and GPQA respectively. We achieve 20 to 50% token reduction while maintaining comparable accuracy to standard generation.

Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo +1

IBM Research Europe · Trinity College Dublin · Dublin, Ireland +1

Reasoning Trace AnalysisEarly StoppingEfficient Language Model ReasoningLLM Inference EfficiencyEfficient Language Model InferenceLLM Reasoning+2
AskPDF
Apr 22, 2026

Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework

Cross-lingual chain-of-thought (XCoT) with self-consistency markedly enhances multilingual reasoning, yet existing methods remain costly due to extensive sampling of full trajectories across languages. Moreover, multilingual LLM representations vary strongly by language, hindering direct feature comparisons and effective pruning. Motivated by this, we introduce UL-XCoT, the first efficient unified logic cross-lingual reasoning framework that minimizes redundancy in token usage and latency, yielding the greatest efficiency under limited sampling budgets during inference. Specifically, UL-XCoT (1) achieves less languages by selecting, per query, a small candidate language set in a language-invariant unified logic space, (2) enables less tokens by monitoring logic-space trajectory dynamics during decoding to prune low-quality reasoning paths, and (3) aggregates the remaining high-quality trajectories via voting. Experiments on PolyMath across 18 languages and MMLU-ProX-Lite across 29 languages with DeepSeek-R1-DistillQwen-7B demonstrate that UL-XCoT achieves competitive accuracy while sharply cutting over 50% decoding token cost versus prior sampling baselines. UL-XCoT also delivers more stable gains on low-resource languages, underscoring consistently superior robustness where standard XCoT self-consistency method fails.

Chenyuan Zhang, Qiguang Chen, Xie Chen +6

Harbin Institute of Technology, Shenzhen · Shanghai Innovation Institute · Central South University +3

Cross-Lingual Reasoning in Language ModelsCoT ReasoningEfficient Language Model ReasoningEfficient Language Model InferenceCross-Lingual Transfer
AskPDF
Apr 20, 2026

Neural Garbage Collection: Learning to Forget while Learning to Reason

Chain-of-thought reasoning has driven striking advances in language model capability, yet every reasoning step grows the KV cache, creating a bottleneck to scaling this paradigm further. Current approaches manage these constraints on the model's behalf using hand-designed criteria. A more scalable approach would let end-to-end learning subsume this design choice entirely, following a broader pattern in deep learning. After all, if a model can learn to reason, why can't it learn to forget? We introduce Neural Garbage Collection (NGC), in which a language model learns to forget while learning to reason, trained end-to-end from outcome-based task reward alone. As the model reasons, it periodically pauses, decides which KV cache entries to evict, and continues to reason conditioned on the remaining cache. By treating tokens in a chain-of-thought and cache-eviction decisions as discrete actions sampled from the language model, we can use reinforcement learning to jointly optimize how the model reasons and how it manages its own memory: what the model evicts shapes what it remembers, what it remembers shapes its reasoning, and the correctness of that reasoning determines its reward. Crucially, the model learns this behavior entirely from a single learning signal - the outcome-based task reward - without supervised fine-tuning or proxy objectives. On Countdown, AMC, and AIME tasks, NGC maintains strong accuracy relative to the full-cache upper bound at 2-3x peak KV cache size compression and substantially outperforms eviction baselines. Our results are a first step towards a broader vision where end-to-end optimization drives both capability and efficiency in language models.

Michael Y. Li, Jubayer Ibn Hamid, Emily B. Fox +1

Stanford University

LLM CompressionMemory-Efficient OptimizationRL for Language Model ReasoningEfficient Language Model ReasoningKV-Cache CompressionEfficient Language Model Inference
AskPDF
Apr 20, 2026

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference

While distributed device-edge speculative decoding enhances resource utilization across heterogeneous nodes, its performance is often bottlenecked by conventional token-level verification strategies. Such rigid alignment leads to excessive rejections, significantly diminishing the accepted sequence length and increasing interaction rounds under fluctuating wireless conditions. In this paper, we propose WISV (Wireless-Informed Semantic Verification), a novel distributed speculative decoding framework that goes beyond strict token-level matching via a channel-aware semantic acceptance policy. WISV integrates a lightweight decision head into the edge-side target LLM to dynamically evaluate speculative tokens by synthesizing high-dimensional hidden representations with instantaneous channel state information (CSI). To optimize the trade-off between verification fidelity and communication overhead, we further design two tailored communication protocols: full-hidden upload and mismatch-first selective-hidden upload. Extensive simulations using a 1B drafter and an 8B target model demonstrate that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency compared to vanilla speculative decoding across tested settings, while maintaining a negligible task accuracy drop (<1%). Finally, we validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server, confirming its real-world efficacy in accelerating edge-deployed LLM inference.

Zixuan Liu, Zhiyong Chen, Nan Xue +4

Cooperative Medianet Innovation Center and the Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Speculative DecodingEfficient Language Model Inference
AskPDF
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 ScalingEfficient Language Model InferenceLLM Reasoning
AskPDF
Apr 19, 2026

Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancy

In LLM-based code generation, multiple code candidates are often generated in parallel from the same prompt -- for example, in best-of-N sampling or multi-candidate code completion. These requests can share KV caches through a common prefix, yet the extent to which their Mixture-of-Experts (MoE) expert routing overlaps, and how this overlap varies across layers, remains insufficiently understood. We study Qwen3.5-35B-A3B-FP8 (256 routed experts, top-8) by performing tree-search-based branching generation from a shared prefix (851 completed codes, temperature 0.7) and analyzing the results with a compiler-output-based alignment (gcc -S -O0 assembly) that controls for token-identity confounds. Our findings are threefold: (1) At positions where both sequences generated the same token, Jaccard similarity reaches 0.649 (40x random), while even at positions with different tokens it remains 0.175 (11x random). (2) A layer-wise decomposition reveals a crossing pattern: same-token routing similarity exceeds different-token similarity across all layers, but dips in the middle layers (L14-20), while different-token similarity peaks in the middle layers at 14x random. (3) In tree-search code generation, 67% of successfully compiled codes concentrate in the top three assembly-equivalent groups, and 99.6% of within-group differences consist of comments and blank lines. We show that diversity in top-P search, including beam search, poses a significant challenge. These results refine the "context-independent routing" claim of prior work through layer-wise decomposition and suggest opportunities for improving search efficiency in LLM code generation.

Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino +1

Graduate School of Informatics, Nagoya University, Japan · Information Technology Center, Nagoya University, Japan

Expert RoutingEfficient Language Model InferenceLLM Code Generation
AskPDF
Apr 17, 2026

RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning

Large reasoning models (LRMs) enhance problem-solving capabilities by generating explicit multi-step chains of thought (CoT) reasoning; however, they incur substantial inference latency and computational overhead. To mitigate this issue, recent works have explored model collaboration paradigms, where small reasoning models (SRMs) generate intermediate reasoning steps to achieve a better accuracy--latency trade-off. Despite recent progress, effectively and efficiently detecting and mitigating SRM failures in collaborative systems remains a key challenge. To address this issue, we analyze SRM inference in both the generated text and hidden-state spaces, and identify three types of failure modes: overconfidence, uncertainty, and heavy revalidation. Building on these insights, we propose RankGuide, a framework that improves the efficiency and effectiveness of SRM--LRM collaboration through tensor-rank-guided routing and steering. Specifically, RankGuide leverages a routing signal that incorporates tensor-rank signals derived from consecutive hidden states to detect when SRMs are likely to fail and selectively invoke LRMs. In addition, we introduce a tensor-rank-filtered steering vector extraction method to modulate the reasoning trajectory of SRMs, thereby improving their generation quality. By improving both routing and steering through tensor-rank signals, RankGuide enables SRM--LRM collaborative systems to achieve more efficient reasoning with fewer steps and improved accuracy. Experiments on multiple reasoning benchmarks demonstrate the efficacy of RankGuide in reducing latency by up to 1.75×1.75\times compared to LRM, while maintaining competitive accuracy relative to prior methods.

Jiayi Tian, Yupeng Su, Ryan Solgi +2

University of California, Santa Barbara · Intel Labs

LLM RoutingEfficient Language Model InferenceActivation SteeringMulti-LLM CollaborationLarge Reasoning Models
AskPDF
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 ScalingBest-of-N SamplingLLM RerankingEfficient Language Model Inference
AskPDF
Apr 16, 2026

Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching

Flow matching retains the generation quality of diffusion models while enabling substantially faster inference, making it a compelling paradigm for generative modeling. However, when applied to language modeling, it exhibits fundamental limitations in representing complex latent distributions with irregular geometries, such as anisotropy and multimodality. To address these challenges, we propose a mixture-of-experts flow matching (MoE-FM) framework, which captures complex global transport geometries in latent space by decomposing them into locally specialized vector fields. Building on MoE-FM, we develop a non-autoregressive (NAR) language modeling approach, named YAN, instantiated with both Transformer and Mamba architectures. Across multiple downstream tasks, YAN achieves generation quality on par with both autoregressive (AR) and diffusion-based NAR language models, while requiring as few as three sampling steps. This yields a 40×40\times speedup over AR baselines and up to a 103×10^3\times speedup over diffusion language models, demonstrating substantial efficiency advantages for language modeling.

Aihua Li

Duke University

Non-Autoregressive Text GenerationFlow MatchingDiffusion Language Model InferenceFlow-Based Generative ModelingEfficient Language Model Inference
AskPDF
Apr 16, 2026

TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models

Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning. Recent work explores using Small Reasoning Models (SRMs) to accelerate LRM inference. In this paper, we systematically characterize the capability boundaries of SRMs and identify three common types of reasoning risks: (1) path divergence, where SRMs lack the strategic ability to construct an initial plan, causing reasoning to deviate from the most probable path; (2) cognitive overload, where SRMs fail to solve particularly difficult steps; and (3) recovery inability, where SRMs lack robust self-reflection and error correction mechanisms. To address these challenges, we propose TrigReason, a trigger-based collaborative reasoning framework that replaces continuous polling with selective intervention. TrigReason delegates most reasoning to the SRM and activates LRM intervention only when necessary-during initial strategic planning (strategic priming trigger), upon detecting extraordinary overconfidence (cognitive offload trigger), or when reasoning falls into unproductive loops (intervention request trigger). The evaluation results on AIME24, AIME25, and GPQA-D indicate that TrigReason matches the accuracy of full LRMs and SpecReason, while offloading 1.70x - 4.79x more reasoning steps to SRMs. Under edge-cloud conditions, TrigReason reduces latency by 43.9% and API cost by 73.3%. Our code is available at https://github.com/QQQ-yi/TrigReason

Yi Zhao, Yajuan Peng, Cam-Tu Nguyen +4

AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Shanghai Key Laboratory for Intelligent Information Processing, Fudan University · State Key Laboratory for Novel Software Technology, Nanjing University +2

Efficient Language Model ReasoningLLM Inference AccelerationEfficient Language Model InferenceMulti-Agent ReasoningMulti-LLM CollaborationLarge Reasoning Models
AskPDF
Apr 14, 2026

RPRA: Predicting an LLM-Judge for Efficient but Performant Inference

Large language models (LLMs) face a fundamental trade-off between computational efficiency (e.g., number of parameters) and output quality, especially when deployed on computationally limited devices such as phones or laptops. One way to address this challenge is by following the example of humans and have models ask for help when they believe they are incapable of solving a problem on their own; we can overcome this trade-off by allowing smaller models to respond to queries when they believe they can provide good responses, and deferring to larger models when they do not believe they can. To this end, in this paper, we investigate the viability of Predict-Answer/Act (PA) and Reason-Predict-Reason-Answer/Act (RPRA) paradigms where models predict -- prior to responding -- how an LLM judge would score their output. We evaluate three approaches: zero-shot prediction, prediction using an in-context report card, and supervised fine-tuning. Our results show that larger models (particularly reasoning models) perform well when predicting generic LLM judges zero-shot, while smaller models can reliably predict such judges well after being fine-tuned or provided with an in-context report card. Altogether, both approaches can substantially improve the prediction accuracy of smaller models, with report cards and fine-tuning achieving mean improvements of up to 55% and 52% across datasets, respectively. These findings suggest that models can learn to predict their own performance limitations, paving the way for more efficient and self-aware AI systems.

Dylan R. Ashley, Gaël Le Lan, Changsheng Zhao +7

Meta Platforms, Inc., Menlo Park, United States of America · The Swiss AI Lab IDSIA (USI-SUPSI), Lugano, Switzerland · Università della Svizzera italiana, Lugano, Switzerland +2

Language Model CascadingLanguage Model Performance PredictionLanguage Model Self-AssessmentEfficient Language Model InferenceEvaluation Awareness in Language ModelsLLM Routing
AskPDF
Apr 13, 2026

EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models

The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, automotive and robotic computing platforms, and high-performance embedded systems, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads efficiently, the autoregressive decoding phase is dominated by GEMV operations that are inherently memory-bound, resulting in poor utilization and prohibitive energy costs at the edge. In this work, we present EdgeCIM, a hardware-software co-design framework for accelerating autoregressive decoding of SLMs on edge devices in latency-critical applications. At its core is a CIM macro, implemented in 65 nm, coupled with a tile-based mapping strategy that balances pipeline stages, maximizing parallelism while alleviating DRAM bandwidth bottlenecks. Our simulator enables design space exploration of SLMs up to 4B parameters, identifying hardware configurations that optimize latency and energy according to a configurable objective function. On LLaMA3.2 3B (INT4), EdgeCIM achieves 1.76x and 3.21x higher throughput than NVIDIA Jetson AGX Orin and Orin Nano Super operating in MAXN mode, respectively, and 7.07x higher throughput than Qualcomm's Snapdragon-X Elite. Extensive benchmarks on TinyLLaMA 1.1B, LLaMA3.2 (1B, 3B), Phi 3.5 mini 3.8B, Qwen2.5 (0.5B, 1.5B, 3B), SmolLM2 1.7B, SmolLM3 3B, and Qwen3 (0.6B, 1.7B, 4B) reveal that our accelerator, at INT4 precision, achieves on average 336.4 tokens/s and 173 tokens/J. These results establish EdgeCIM as a compelling solution towards real-time, energy-efficient, latency-critical SLM inference at the edge.

Jinane Bazzi, Mariam Rakka, Fadi Kurdahi +2

King Abdullah University of Science and Technology, Thuwal, Saudi Arabia. · the University of California Irvine, Irvine, CA, USA. · Rain Neuromorphics Inc., San Francisco, CA, USA

On-Device Language Model InferenceEfficient Language Model InferenceCompute-in-MemoryHardware-Software Co-DesignSmall Language Models
AskPDF
Apr 10, 2026

SLM Finetuning for Natural Language to Domain Specific Code Generation in Production

Many applications today use large language models for code generation; however, production systems have strict latency requirements that can be difficult to meet with large models. Small language models with a few billion parameters are resource efficient but may suffer from limited reasoning, hallucinations, or poor retention of longer context. Fine tuning improves task specific accuracy by embedding domain knowledge directly into model weights, reducing reliance on runtime context. We previously implemented a baseline natural language to code generation approach using a retrieval augmented generation pipeline that dynamically selected few shot examples to embed domain specific language context for a large language model. In this study, we evaluate small language models for generating domain specific language from natural language by fine tuning variants of Mistral and other models on a dataset of natural language code pairs. Our results show that the fine-tuned models achieve improved performance and latency on test datasets compared to larger models. We also demonstrate that the trained model can be further fine-tuned for customer specific scenarios without degrading general performance, helping resolve production issues. Load testing followed by production deployment confirmed optimal performance in terms of latency and quality. These findings demonstrate that task specific fine tuning with small language models provides an efficient, faster, and cost-effective alternative to large language models for domain specific language generation.

Renjini R. Nair, Damian K. Kowalczyk, Marco Gaudesi +1

Microsoft

Code GenerationFine-TuningSmall Language ModelsEfficient Language Model Inference
AskPDF