Efficient Language Model Inference

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.

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.

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.

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.

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.

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: \textit{overconfidence}, \textit{uncertainty}, and \textit{heavy revalidation}. Building on these insights, we propose \textbf{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 $1.75\times$ compared to LRM, while maintaining competitive accuracy relative to prior methods.

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.

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 $40\times$ speedup over AR baselines and up to a $10^3\times$ speedup over diffusion language models, demonstrating substantial efficiency advantages for language modeling.

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

Efficient context compression is critical for retrieval-augmented question answering in resource-constrained settings, where long retrieved contexts increase latency, memory use, and LLM reader cost. We propose a lightweight encoder-only framework for query-driven sentence pruning that preserves answer-critical evidence while aggressively reducing irrelevant context. Our method learns marginal contribution scores for sentences using counterfactual training signals and optimizes a contrastive ranking objective that separates critical evidence from noncritical context. Our approach scores all sentences from a single full-context encoding, enabling fast inference with low computational overhead. Experiments show that it maintains accuracy comparable to the strongest baseline while using 3.7$\times$ less peak memory and achieving nearly 3$\times$ lower compression latency, demonstrating an effective quality--efficiency trade-off for practical resource-constrained deployment.

Emerging 6G visions, reflected in ongoing standardization efforts within 3GPP, IETF, ETSI, ITU-T, and the O-RAN Alliance, increasingly characterize networks as AI-native systems in which high-level semantic reasoning layers operate above standardized control and data-plane functions. Although frontier-scale large language models (LLMs) such as Qwen2.5-7B and Olmo-3-7B demonstrate strong reasoning capability, their computational footprint limits deployment in latency-sensitive, edge-native infrastructures. This paper presents a systematic empirical study of the scaling behavior and deployment efficiency of compact language models for network-level semantic reasoning in AI-native 6G systems. Using 6G-Bench, a standardization-aligned benchmark comprising 30 decision-making tasks across five capability domains, we evaluate models ranging from 135M (SmolLM2-135M) to 7B parameters (Qwen2.5-7B), including mid-scale architectures such as Llama-3.2-1B, Granite-1B, and Qwen2.5-3B. Deterministic accuracy (pass@1) increases from 0.224 at 135M to 0.707 at 7B, but scaling gains are highly non-uniform. A pronounced stability transition occurs in the 1 to 1.5B range, where accuracy rises from 0.373 (Llama-3.2-1B) to 0.531 (Qwen2.5-1.5B) and the instability gap Delta_5 contracts from 0.356 to 0.138. Beyond 3B parameters, improvements diminish (+0.064 from 3B to 7B). Through single-query inference profiling and an Edge Score metric that normalizes accuracy by latency and memory footprint, we show that semantic reliability per unit edge resource does not scale monotonically with parameter count. Instead, mid-scale models (approximately 1.5 to 3B) achieve the most favorable balance between deterministic stability and computational efficiency, providing deployment-relevant guidance for AI-native 6G architectures. All scripts and results are publicly available at https://github.com/maferrag/6G-Bench

The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent model selection at inference time. While smaller models suffice for routine queries, complex tasks demand more capable models. However, static model deployment does not account for the complexity and domain of incoming queries, leading to suboptimal performance and increased costs. Dynamic routing systems that adaptively select models based on query characteristics have emerged as a solution to this challenge. This survey provides a systematic analysis of multi-LLM routing and cascading approaches, focusing on systems that route queries across a pool of independently trained LLMs at inference time. We cover diverse routing paradigms, including query difficulty, human preferences, clustering, uncertainty quantification, reinforcement learning, multimodality, and cascading. For each paradigm, we analyze representative methods and examine key trade-offs. Beyond taxonomy, we introduce a conceptual framework that characterizes routing systems along three dimensions: when decisions are made, what information is used, and how they are computed. This perspective highlights that practical systems are often compositional, integrating multiple paradigms under operational constraints. Our analysis demonstrates that effective multi-LLM routing requires balancing competing objectives. Choosing the optimal routing strategy depends on deployment and computational constraints. Well-designed routing systems can outperform even the most powerful individual models by strategically leveraging specialized capabilities across models while maximizing efficiency gains. Meanwhile, open challenges remain in developing and evaluating routing mechanisms that generalize across diverse architectures, modalities, and applications.

Prompting schemes such as Chain of Thought, Tree of Thoughts, and Graph of Thoughts can significantly enhance the reasoning capabilities of large language models. However, most existing schemes require users to define static, problem-specific reasoning structures that lack adaptability to dynamic or unseen problem types. Additionally, these schemes are often under-optimized in terms of hyperparameters, prompts, runtime, and prompting cost. To address these limitations, we introduce Framework of Thoughts (FoT)--a general-purpose foundation framework for building and optimizing dynamic reasoning schemes. FoT comes with built-in features for hyperparameter tuning, prompt optimization, parallel execution, and intelligent caching, unlocking the latent performance potential of reasoning schemes. We demonstrate FoT's capabilities by implementing three popular schemes--Tree of Thoughts, Graph of Thoughts, and ProbTree--within FoT. We empirically show that FoT enables significantly faster execution, reduces costs, and achieves better task scores through optimization. We release our codebase to facilitate the development of future dynamic and efficient reasoning schemes.

Artificial intelligence and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, personalised explanations, and inquiry-driven learning. However, most AI-based learning systems rely on continuous internet connectivity and cloud-based computation, limiting their use in bandwidth-constrained environments. This paper presents Arapai, an offline-first large language model architecture designed for AI-assisted learning in low-connectivity settings. The system performs all inference locally using quantized language models and incorporates hardware-aware model selection to enable deployment on low-specification, CPU-only devices. By removing dependence on cloud infrastructure, the system provides curriculum-aligned explanations and structured academic support through natural-language interaction. To support learners at different educational stages, the system includes adaptive response levels that generate explanations at varying levels of complexity: Simple English, Lower Secondary, Upper Secondary, and Technical. The system was evaluated with 120 students and 9 instructors from secondary and tertiary institutions under limited-connectivity conditions. Results indicate stable operation on legacy hardware, acceptable response times of 1-3 seconds for typical queries, and positive user perceptions of its effectiveness in supporting self-directed learning.

Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and early token commitments in discrete reasoning traces. Recent latent reasoning approaches attempt to optimize efficiency by performing reasoning within continuous hidden states. However, many such methods optimize latent states end to end without a trained interface for intermediate textual readout, and several representative configurations use a pre-defined number of latent steps during inference. In this work, we introduce \textbf{PLaT} (\textbf{P}lanning with \textbf{La}tent \textbf{T}houghts), a framework that decouples latent planning from verbalization. The Planner deterministically evolves latent planning states, while an independent Decoder provides textual readouts when needed. Answer-aware textual stopping allows the latent rollout to use a problem-dependent number of groups rather than a pre-specified chain length. PLaT achieves competitive coverage at larger $k$ in several mathematical settings, with lower Pass@1: on Llama-1B GSM8K, it reaches 80.59% Pass@128 versus CODI's 72.37%. These results support PLaT as a candidate-generation interface supplying multiple textual readouts for downstream verification or reranking.

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. To address this challenge, we introduce the Step-Tagging framework, a lightweight sentence-classifier enabling real-time annotation of the type of reasoning steps that an LRM is generating. To monitor reasoning behaviors, we introduced ReasonType: a novel taxonomy of reasoning steps. Building on this framework, we demonstrated that online monitoring of the count of specific steps can produce effective interpretable early stopping criteria of LRM inferences. We evaluate the Step-tagging framework on three open-source reasoning models across standard benchmark datasets: MATH500, GSM8K, AIME and non-mathematical tasks (GPQA and MMLU-Pro). We achieve 20 to 50% token reduction while maintaining comparable accuracy to standard generation, with largest gains observed on more computation-heavy tasks. This work offers a novel way to increase control over the generation of LRMs, and a new tool to study behaviors of LRMs.

Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning. It consists of generating multiple responses, or ``samples", from a large language model (LLM) and selecting the most frequent answer. This procedure can naturally be viewed as a majority vote or empirical mode estimation. Despite its effectiveness, self-consistency is prohibitively expensive at scale when naively applied to datasets, and it lacks a unified theoretical understanding of sample efficiency and scaling behavior. In this paper, we provide the first comprehensive analysis of SC's scaling behavior and its variants, drawing on mode estimation and voting theory. We derive and empirically validate power law scaling for self-consistency across datasets, and analyze the sample efficiency for fixed-allocation and dynamic-allocation sampling schemes. From these insights, we introduce Blend-ASC, a novel variant of self-consistency that dynamically allocates samples to questions during inference, achieving state-of-the-art sample efficiency. Our approach uses 4.8 times fewer samples than vanilla SC on average, outperforming both fixed- and dynamic-allocation SC baselines, thereby demonstrating the superiority of our approach in terms of efficiency. In contrast to existing variants, we note that Blend-ASC is hyperparameter-free, supports batching, and can fit any budget of samples, ensuring it can be easily applied to any self-consistency application.

Voice agents face a fundamental tension: the reasoning, retrieval, and tool use that make foundation models capable are iterative and slow, while conversational interaction demands responses on a millisecond timescale. Smaller, real-time models meet the latency bar but cannot match foundation models on complex tasks, leaving current voice agents to trade away either responsiveness or capability. We introduce conversational infill, where a small talker model both immediately generates contextually grounded responses to hide the latency of an external reasoner model and fluently integrates streamed reasoner knowledge into its responses during inference. We curate a 290,571-example synthetic dataset spanning six domains and demonstrate that this task is learnable across seven widely used small language models ranging from 135M to 1.7B parameters. Our system implementation, ConvFill, sustains millisecond-level time-to-first-response while closing the accuracy gap to within 6.3% of the corresponding frontier reasoner performance. In a live user study (n=18) with talker deployments running on an Apple M2 SoC, participants rank ConvFill on par with frontier models overall, prefer it for retrieval-heavy tasks, and rate it significantly more responsive. These results show that conversational infill unlocks a new point on the latency-capability Pareto frontier, offering a practical path toward voice agents that are both responsive and highly capable. Code, models, and datasets are available at https://github.com/vysri/conversational-infill.

Inference optimizations are routinely evaluated by throughput alone, without verifying output correctness. We conduct a forensic analysis of batch speculative decoding and find that several widely-used implementations silently produce corrupted outputs (repetitive tokens, <unk> symbols) while reporting competitive speed; failures invisible to metrics like ROUGE. We trace the root cause to the ragged tensor problem: variable token acceptance desynchronizes position IDs, attention masks, and KV-cache across a batch. We formalize the synchronization invariants (rectangular alignment and position-ID contiguity) that valid batched inference must preserve and show that maintaining them incurs superlinear alignment overhead under contiguous layouts. EQSPEC enforces the invariants without custom kernels; EXSPEC schedules same-length sequences to bypass realignment. On SpecBench across three model families, EXSPEC reaches 3 x throughput at batch size 8 with 95% exact match to standard decoding; residual divergence traces to floating-point non-determinism, not synchronization error. Code:https://github.com/eBay/spec_dec

The field of artificial intelligence (AI) has taken a tight hold on broad aspects of society, industry, business, and governance in ways that dictate the prosperity and might of the world's economies. The AI market size is projected to grow from {$}189 billion in 2023 to {$}4.8 trillion by 2033. Currently, AI is dominated by large language models (LLMs) that exhibit linguistic and visual intelligence. However, training these models requires a massive amount of data scraped from the web as well as large amounts of energy (50-60 GWh to train GPT-4). Despite these costs, these models often hallucinate, a characteristic that prevents them from being deployed in critical application domains. In contrast, the human brain consumes only 20W of power. What is needed is the next level of AI evolution in which lightweight domain-specific multimodal models, especially compact models with 10--20B parameters for bounded domains, with higher levels of intelligence can reason, plan, and make decisions in dynamic environments with real-time data and prior knowledge, while learning continuously and evolving in ways that enhance future decision-making capability. This will define the next wave of AI, progressing from today's large models, trained with vast amounts of data, to nimble energy-efficient domain-specific agents that can reason and think in a world full of uncertainty. To support such agents, hardware will need to be reimagined to allow system-level energy efficiencies $\geq {1000X}$ over the state of the art for targeted domain tasks, subject to accuracy, latency, and coverage constraints. Such a vision of future AI systems is developed in this work.

Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's operational capability boundary, leading to long but unproductive reasoning. In this paper, we study whether LRMs expose early signals predictive of such cases, and whether these signals can be used to mitigate unproductive reasoning. In black-box settings, we find that reasoning expressions contain failure-predictive signals. In white-box settings, we show that the hidden states of the last input token contain information that is predictive of whether a question will not be solved correctly under our evaluation setup. Building on these observations, we propose two test-time monitoring strategies: reasoning expression monitoring and hidden states monitoring, that reduce token usage by 62.7-93.6%, substantially improving efficiency and reliability while largely preserving accuracy.

Accurate uncertainty quantification remains a key challenge for standard LLMs, prompting the adoption of Bayesian and ensemble-based methods. However, such methods typically necessitate computationally expensive sampling, involving multiple forward passes to effectively estimate predictive uncertainty. In this paper, we introduce an approach enabling uncertainty estimation in LLMs without incurring the heavy inference latency typically associated with sampling methods. Specifically, we distill uncertainty-aware teachers - originally requiring multiple forward passes - into single-pass students, fine-tuned using LoRA. We compare two distinct distillation strategies: one in which the student employs traditional softmax-based outputs, and another in which the student leverages Dirichlet-distributed outputs to explicitly model epistemic uncertainty via evidential learning. Empirical evaluation on classification tasks demonstrate that such students can achieve comparable predictive and uncertainty quantification performance relative to their teachers, while requiring only a single forward pass.

Reasoning LLMs trained with long chain-of-thought often overthink: they spend tokens on redundant reflection and transitions that inflate cost without improving accuracy. Static activation steering (e.g.\ SEAL) suppresses such content with a fixed vector, but applies the same strength regardless of how redundant the current chunk actually is. We describe PID-steering, a training-free, decoding-time method that modulates the steering strength with a PID controller driven by a lightweight chunk-level redundancy classifier. On a subset of GSM8K with DeepSeek-R1-Distill-Qwen-1.5B, the method improves accuracy from 85.7% to 89.6% (+3.9 pp) while cutting average output length from 1026 to 790 tokens ($-$23%). We report it as a small-scale proof of concept rather than a benchmark result.

Chain-of-Thought (CoT) prompting trades inference speed for reasoning accuracy. Existing compressors force a compromise as static gradient techniques treat tokens independently, severing sequential logic, while uncertainty-based pruning ignores the final answer. We introduce Adaptive GoGI-Skip, a framework that resolves this tension by non-linearly coupling Goal-Gradient Importance (GoGI) with Adaptive Dynamic Skipping (ADS). GoGI quantifies each token's functional contribution to answer correctness via gradient sensitivity. ADS leverages runtime entropy to dynamically modulate the GoGI threshold, preserving low-gradient tokens essential for structural coherence at high-uncertainty junctions. Trained on 7,472 MATH traces, our policy transfers zero-shot to AIME, GPQA, and GSM8K, reducing token volume by $>$45% and accelerating inference up to 2.0$\times$ without accuracy loss. These results suggest that thinking-optimal compression demands synergy between teleological goals and epistemic uncertainty.

The emergence of Transformer-based Large Language Models (LLMs) has substantially augmented the capabilities of Natural Language Processing (NLP), thereby intensifying the demand for computational resources. Therefore, enhancing efficiency based on factors like computational requirements, energy consumption, carbon footprint and financial cost has become a vital area of research. This motivates us to conduct a survey on Transformer-based LLMs in NLP from the perspective of efficiency. In this survey of 312 articles, the efficiency-improvement endeavors have been systematically discussed targeting various aspects such as data curation, model design, model downsizing, and dynamic inferencing. This has been augmented with efficiency considerations in model adaptation strategies like pre-training, fine-tuning, prompt-engineering and Retrieval-Augmented Generation (RAG). Furthermore, a statistical analysis followed by an in-depth evaluation of the efficiency and efficacy of more than 30 renowned NLP models has been performed on 13 evaluation benchmarks. This paper offers valuable insights for researchers, professionals as well as scholars, and explores the trend of research toward sustainable practices in NLP.

State--prediction separation (SPS) relieves a language model's hidden state of two competing burdens---summarizing the context and predicting the next token---by splitting the forward pass into a state stream and a prediction stream. The separation works, but it is expensive: the prediction stream is a second pass over the whole backbone, costing $\sim$1.9$\times$ the pretraining FLOPs, and even more in terms of wall-clock time when using a flexible attention mask. This paper makes state--prediction separation almost free. We take the separation to its limit with a free pause token: a prediction stream that writes no keys or values at all and so rides the sequence's existing positions. It improves next-token prediction of a standard Transformer by 2-3 centinats in practice on a 1B parameter model, and because it adds no position it costs nothing at inference---no added context length, no KV cache, no decode steps, and essentially no latency, with the growth in inference flops typically irrelevant as it is not the active bottleneck on throughput. The cost is therefore entirely in training where we use four mechanisms to drive it down: a two-pass split that keeps FlashAttention kernels viable, the $w{=}0$ prediction window, a shared gated FFN that evaluates one FFN per position rather than one per stream, and phasing the separation onto the tail of the run. Together these bring the overhead versus an optimized pretraining pipeline to $1.33\times$ wall-clock while recovering ~94% of the gain compared to SPS, and to as low as $1.09\times$ along a graceful quality/compute tradeoff. Furthermore, the FFN optimization reduces the raw flops required at inference time. The result is an isoflop, isoparameter, and isotoken improvement over standard next token trained transformers.