Token Communications

In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, making small language models (SLMs) attractive for on-device deployment. For such models, a key design choice is how the available function surface is presented. Two approaches are to represent each function with a dedicated Functional Token (FT) or provide function schemas directly in the prompt. FTs enable compact inference but are restricted to functions learned during training, whereas Schema-in-Prompt (SIP) can generalize to unseen functions at the cost of longer prompts and higher inference overhead. We introduce a benchmark of 9,822 single-turn examples spanning 79 vehicle functions derived from Android Automotive, including held-out functions and requests requiring refusal. We compare both approaches under matched fine-tuning across four SLMs from 270M to 1.7B parameters. On functions seen during training, scaling provides limited benefit: the 270M model can match the 1.7B model, while the strongest overall performance occurs at 0.6B. On held-out functions, FT achieves zero accuracy by construction, whereas SIP generalizes and improves substantially with scale. On out-of-scope requests, FT can invoke an unavailable function it was trained to emit, while SIP more reliably refuses based on the functions offered. This flexibility comes with higher memory use and latency. Our theoretical analysis explains how SIP enables generalization and why longer schema contexts increase inference cost. Overall, function-surface representation, rather than model scale alone, determines the capabilities and failure modes of SLM-based vehicle function calling.

Asynchronous reinforcement learning has become the standard way to scale training for large language models (LLM), but the resulting policy lag biases the critic toward the stale behavior policy. Existing work on asynchronous LLM training corrects the actor and leaves this bias unaddressed, while the off-policy value correction of classical RL does not carry over to long-horizon agentic tasks, since a short correction horizon leaves the regression target free of the reward and a long one lets the product of importance ratios drift exponentially with the trajectory length. We propose BRACE, an anchored Bellman-residual correction for stale value models. BRACE bounds the correction horizon to a prefix of policy tokens and anchors a constant-weight Monte-Carlo tail beyond it, which separates policy correction from reward propagation. BRACE delivers a $9.8\%$ relative improvement in mean@1 on BrowseComp-Plus over the strongest baseline, runs $2.46\times$ faster per step than synchronous training, and remains stable $50$ updates off-policy.

On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses. We therefore shift our focus from agreement to teacher-student mismatch, and find that mismatch tokens can be mainly categorized into two types: student-excess tokens and student-deficit tokens. Student-excess tokens are generated by the student but assigned near-zero probability by the teacher; their log-ratio corrections grow unbounded and destabilize the update. Student-deficit tokens, in contrast, are preferred by the teacher but rarely sampled by the student; their absence blocks the transfer of the teacher's reasoning patterns. To tackle these mismatch directions, we propose TIDE (Token-level Independent Deficit-Excess correction), which applies bounded Hellinger shaping to suppress the most severe sampled excesses and an analytic teacher top-$K$ injection to restore deficient probability mass without requiring deficit tokens to be sampled. Across mathematical reasoning benchmarks with multiple Qwen3 teacher-student pairs, TIDE consistently outperforms standard OPD and recent token-selection and reward-shaping baselines. Moreover, the gains of TIDE are more pronounced under strong teacher-student mismatch, where it improves Avg@8 from 6.9% to 20.3%, reduces average response length by a factor of 3.6, and substantially reduces formatting failures. Code is available at https://github.com/yzc-666/TIDE

Video token communication represents video content as discrete tokens that differ in their importance to reconstruction and exhibit temporal dependencies. When these tokens are packetized for wireless transmission, block fading can cause multiple important or correlated tokens to be lost together, severely degrading video reconstruction. To address this issue, we propose a loss-resilient wireless video token communication (WVTC) framework. WVTC evaluates token importance from the intrinsic predictive structure of video tokens, assigning high priority to structural I-tokens and measuring P-token importance by temporal neighborhood novelty. A shuffled mixed I/P-token packetization scheme disperses structural anchors and correlated temporal regions across packets. Using only current block channel state information, an online scheduler jointly considers packet importance density, MCS-dependent decoding reliability, block capacity, and importance concentration when allocating packets to fading blocks. At the receiver, a fine-tuned detokenizer reconstructs missing content from surviving tokens without retransmission. Numerical results demonstrate improved perceptual quality and more graceful degradation under increasing packet error rates.

LLM inference accounts for over 90% of AI operational energy, scaling directly with input token count---a critical inefficiency for telecom network analytics and numerical time-series data analysis (NTSDA), where raw multivariate KPI windows from 4G/5G cell sites expand into thousands of floating-point tokens. Vision-Language Models (VLMs) eliminate this mismatch by encoding time-series as 2D plots, achieving 3.6-10.4x input token reduction across Llama-3.2-90B, Qwen2.5-VL-72B, and Pixtral-12B architectures. This translates to 1.8-2.5x measured inference energy reduction, saving approximately 7.2 MJ/day at telecom edge deployments and CloudRAN that monitor 200 cells per 15-minute interval. Critically, efficiency gains do not sacrifice accuracy: a fine-tuned Llama-3.2-90B-Vision VLM achieves 220.7% higher precision than its text-only counterpart and outperforms LSTM and ARIMA baselines by over 144% on telecom anomaly detection. On public benchmarks, Pixtral-12B achieves a 20.6x improvement in J/F1 score at mean F1 = 0.82. At 24 KPIs, text representations exceed the 128K context window of most production LLMs, rendering text-only processing infeasible without truncation, while visual representations remain within standard limits. These results establish VLMs as an energy-efficient and accuracy-superior modality for numerical time-series workloads, providing empirical grounding for AI inference systems that treat energy consumption as a first-class engineering constraint.

Tool-using large language model agents frequently replan, retry failed operations, delegate tasks, and resume after crashes. These behaviors can cause one user authorization to be requested and executed multiple times under freshly issued token identifiers, even when each individual token is single-use. We call this failure semantic replay: exceeding the execution budget of a token-independent authorization instance rather than merely reusing an old token identifier. We show that identifier-local token consumption cannot prevent fresh reissuance unless the issuer retains monotonic durable state over the authorized action, confirmation event, and remaining execution budget. We introduce CapLease, an authorization-consumption layer that follows proposal- and authority-level defenses, binds an authenticated user confirmation to a canonical action, and enforces transactional Issue-Prepare-Commit transitions. Across LLM-agent replanning, retry, delegation, concurrency, confirmation-replay, and crash-recovery scenarios, identifier-local tokens permit fresh semantic reissuance, whereas CapLease and an equally stateful Server Ledger prevent duplicate admission and, with an idempotent sink, duplicate external effects. Our results identify durable authorization state, rather than token representation alone, as the systems requirement for replay-resistant agent execution.

Large language models (LLMs) largely rely on Transformers, where self-attention provides global token interaction but does not explicitly encode the locality of natural language. We study whether lightweight depthwise convolutions can supply this local inductive bias without materially increasing model size. Our macro-level ablation compares convolution at 17 locations in a Qwen3 Transformer block and finds the best results when convolution is applied to the projected queries, keys, and values before attention. A subsequent micro-level study favors a residual depthwise convolution with kernel size $k=3$, without additional normalization or activation. Across Qwen3 models and several pre-training data budgets, this design improves the average accuracy on seven downstream benchmarks while adding less than $0.01\%$ parameters. A representation-level case study further suggests that the convolution makes repeated token IDs more sensitive to their immediate context. These results support depthwise convolution as a lightweight complement to self-attention for modeling short-range token interactions.

Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These adaptations, however, are largely general-purpose models that treat MRI as one modality among many; large-scale, MRI-specific modelling and benchmarking remain limited, even though MRI's low soft-tissue contrast leaves many boundaries effectively invisible on individual slices. We present SAMRI-3D, a benchmark and method for 3D MRI segmentation with SAM2. The SAMRI-3D benchmark is the largest MRI-only evaluation to date - 10,392 volumes from 34 datasets (27 public, 7 in-house) spanning 12 anatomical domains and 10+ sequences, with explicit seen/unseen splits. Freezing the image encoder and fine-tuning only the lightweight decoder and memory modules raises mean Dice from 0.58 (zero-shot SAM2) to 0.76, surpassing recent SAM-based medical models (SAMed-2 0.69, Medical-SAM2 0.49, SAM-Med3D 0.37) with strong statistical significance. To target invisible boundaries, we introduce Global Volume Tokens (GVT): persistent memory tokens trained with a Truncated Signed Distance Field (TSDF) reconstruction objective that is discarded at inference (zero added cost). This full model, SAMRI-3D, attains the best accuracy (0.78) and lowest variance across all 34 datasets and, uniquely, shows no drop on 8 held-out datasets (0.79 unseen vs. 0.78 seen); per-sequence analysis confirms the TSDF objective helps most where per-slice contrast is weakest. We will release the benchmark, code, and models in this paper.

Single-stream autoregressive decoding of large language models is bound by memory bandwidth: each generated token requires one full forward pass through the target model, and successive passes cannot be parallelized. Speculative decoding restructures this computation: a small draft model proposes $K$ tokens autoregressively, the target model scores all of them in one batched pass, and a rejection-sampling rule provably preserves the target model's output distribution. We present a from-scratch, device-agnostic (CUDA/MPS/CPU) implementation and an empirical study across five draft/target backend configurations on a consumer Apple-silicon laptop. Distribution equivalence is verified at three levels, culminating in a two-sample test over roughly 9,200 real-model tokens per method ($χ^2 = 162.5$, dof $= 200$, $p = 0.976$) and exact greedy-sequence agreement. The best configuration reaches a measured $1.61\times$ wall-clock speedup at $K=6$, on an acceptance profile declining from 69.7% at $K=1$ to 37.8% at the optimum, while three of five configurations decelerate, either because the draft fails to out-speed a small target or because the quantized Metal backend executes "parallel" verification serially, an effect we isolate and quantify. The failures are as instructive as the successes: speculative decoding pays off only when verification is genuinely batch-parallel and the draft/target latency gap is real.

Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accumulated attention mass, treated here as signal energy, and keeping the heaviest. On schema-dense input streams such as nested JSON, this score acts as a non-stationary filter that disproportionately retains noise: a non-content sink role (delimiters or whitespace) carries an order of magnitude more energy than any content role, and structural KEY tokens are over-retained at roughly 1.8x the rate of the answer-carrying VALUE tokens, collapsing exact-match accuracy from 88% to 0% at a 5% budget as the signal-to-noise ratio of the retained state degrades. A counterfactual experiment establishes that suppressing KEY tokens is the best deployable filter. Our retraining-free, role-conditional allocation over SnapKV's windowed score, governed by a single tuned hyperparameter, closes 63-98% of the H2O gap at sub-20% budgets and, at higher budgets, modestly matches or exceeds full-cache accuracy -- a small, seed-sensitive denoising effect (borderline significant at B=0.50; not distinguishable from zero at B=0.30 over four seeds). A 15 MB linear role probe supplies these labels at negligible inference cost, though matching parser-level downstream accuracy remains open.

Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, inside the same finite prompt used for the current task. This creates a practical allocation problem: every token spent on coordination is unavailable to task instructions or evidence when a call is assembled under a fixed context budget. We introduce the Roundtable Context Window Test (RCWT), a controlled protocol for measuring this task-budget displacement effect. RCWT varies coordination content while controlling total budget, position order, task family, and scoring. In the main context-dependent recall task at $W=4096$, three commercial models remain near baseline through moderate overhead and then degrade sharply once residual reference evidence falls to a few hundred tokens. Window-scaling summaries are consistent with a task-specific residual-budget interpretation rather than a fixed percentage threshold, but we treat this as descriptive evidence rather than a universal law. To test whether the fixed-budget cliff persists when task evidence remains intact, we add an intact-task ablation: the full task/reference block is kept present while coordination tokens increase by expanding total prompt length. In that setting, all tested calls return every scored field correctly across GPT-4.1-mini, Claude Haiku 4.5, and Gemini 2.5 Flash up to a 95% coordination ratio. This ablation narrows the claim: the main RCWT cliff is best read as task-budget displacement, not as proof that coordination volume alone causes semantic interference in the original open-ended task. RCWT is therefore a measurement primitive for context-allocation budgeting, not a complete theory of multi-agent benefit or session-level coordination.

On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent rollouts yield noisy gradients; already-mastered tokens yield redundant ones. This creates waste at three scales (tokens, training phases, and prompts) yet existing methods supervise uniformly. We introduce SEAD, which uses entropy as a unified probe of this competence-dependent degradation at three scales: (1) joint teacher-student entropy partitions tokens into zones receiving tailored divergences or zero gradient (approx. 50% skipped); (2) a cosine schedule anneals from forward to reverse KL as competence grows; (3) a competence-gated curriculum introduces prompts easy-to-hard. These components are symbiotically necessary: token selection requires coherent rollouts (curriculum), annealing requires monotonic improvement (also curriculum). On OLMo-3 (7B to 32B), SEAD achieves +4.8 avg accuracy over vanilla OPD across six math benchmarks, with ablations confirming super-additive interactions.

Sparse autoencoders (SAEs) provide useful decompositions of Transformer residual streams, but their learned features are usually named post hoc rather than directly connected to the Transformer's token vocabulary. We introduce Vocabulary-Aligned Sparse Autoencoder (VASAE), a method that trains SAE features under vocabulary-aligned anchoring and assigns each feature an intrinsic token name: the token string whose embedding is nearest to that feature. Without reducing reconstruction quality compared with a standard SAE, VASAE produces dictionaries with vocabulary-aligned features. Using a 0.8 cutoff on the nearest-token alignment score, dictionaries trained on GPT-2-small post-residual streams align about 90% of features in layers 0--10. In Llama-3.1-8B, representative shallow and middle-layer dictionaries contain strongly aligned features, including 92.8% in the shallow layer, while the representative final-layer dictionary shows limited alignment. After subtracting the sentence-level mean sparse code, case studies show that many remaining intrinsic token names are relevant to nearby input tokens. These results suggest that vocabulary-aligned anchoring can connect learned features to intrinsic token names during training, complementing post hoc interpretation of learned dictionaries.

Pretrained biological language models expose per-token probability distributions through masked-token prediction, providing the likelihood interface central to sequence design, variant scoring, and mechanistic interpretation. Yet these distributions are learned from broad unlabeled corpora and are not naturally conditioned on task-specific biological contexts such as interaction partners, cellular environments, or therapeutic interventions. Existing contextual matching methods often distort this interface through pooled embeddings, contrastive latent spaces, or task-specific prediction heads. We introduce LOGICA (Logit-space Contrastive Alignment), a framework for context-conditioned prediction that performs contrastive learning directly in output-logit space. Using gated cross-modal adapters compatible with each model's native token head, LOGICA preserves the pretrained likelihood interface and converts contextualized token log-likelihoods into matching scores. Alignment is defined through context-sensitive token probabilities rather than proximity in a shared embedding space, enabling learning from sparse paired data across models with distinct vocabularies, without a shared tokenizer or decoder. LOGICA is particularly effective for mutation-local variant ranking, where comparisons reduce to context-conditioned likelihoods of mutant tokens at perturbed sites. Across protein--ligand binding, TCR--peptide activity, and drug-conditioned resistance prediction, LOGICA improves over prior state-of-the-art methods, including matched latent-contrastive and conditional MLM baselines, while retaining a token-level interface for interpretation and generation. On held-out-gene single-mutation drug-resistance prediction, LOGICA improves AUC from near-random latent-space baselines of $\sim$0.55 to $\sim$0.65.

Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference mismatch and propose self-generated T2T, which performs a no-gradient draft pass, fills masked positions with predicted tokens, and supervises recovery in a second pass under these self-generated corruptions. We implement the update as a short LoRA continued-pretraining pass on LLaDA2.1-mini and evaluate on several benchmarks under the official Q-Mode T2T procedure with unchanged inference parameters. The method generally improves accuracy while reducing T2T edit intensity, mitigating failure modes such as final-digit transcription errors after otherwise correct reasoning and excessive self-correction before short factual answers.

The integration of Foundation Models (FMs) and wireless communications is driving the evolution of image communication from bit-accurate transmission toward task-oriented transmission. However, existing task-oriented image communication methods still face three major challenges: insufficient task-oriented Token representation, inadequate collaboration between Visual Tokens and Task Tokens, and limited interpretability of task decisions. To address these challenges, we propose an Explainable Task-Oriented Token Communication (ET-TokenCom) framework. By treating Tokens as unified units for information representation and transmission, the proposed framework constructs an end-to-end communication link that spans visual perception, wireless transmission, and task reasoning. At the transmitter, the ET-TokenCom framework extracts Visual Tokens from images to preserve low-level visual information. Meanwhile, Task Tokens generated by the FM are introduced to represent the target information and decision intent required by the current task. A Cross-Modal Attention (CMA) fusion mechanism is further designed, enabling Task Tokens to explicitly guide the selection, weighting, and transmission of Visual Tokens. At the receiver, the framework integrates Token decoding with an explainable output mechanism, where attention heatmaps are generated to highlight critical perceptual regions under different task objectives and reveal the influence of Task Tokens on the outputs. Finally, simulation results validate the effectiveness and robustness of the proposed ET-TokenCom framework.

Standard dot-product self-attention computes, in a single layer, only pairwise (order-2) interactions between tokens; representing a generic order-$k$ interaction is known to require either super-quadratic resources in one layer or composition across depth. We introduce \textbf{Quantum Higher-Order Attention (QHA)}, a shallow, hardware-realizable quantum attention head that, via data re-uploading and an all-to-all non-Clifford entangler, synthesizes order-$k$ token interactions inside the circuit and exposes them through a local single-qubit read-out. We prove (i) an expressivity separation: any single standard self-attention layer with embedding dimension $m$, $H$ heads and $p$-bit precision satisfying $mHp=o(N/\log\log N)$ cannot represent the order-$k$ correlation family that one QHA head represents with circuit depth $O(\log k)$ ($O(k)$ two-qubit gates); and (ii) a trainability guarantee for its local-design instantiation: with a local read-out and $O(\log n)$ depth the gradient variance is $Ω(1/\mathrm{poly}(n))$ (no barren plateau), which we confirm empirically -- while being explicit that the more expressive all-to-all instantiation we benchmark is trained empirically and shows exponentially decaying gradients. Empirically, at a $6.5\times$ smaller parameter budget, QHA generalizes hidden-subset parity of every order $k\le6$ from disjoint inputs, whereas the larger classical attention head collapses past order~2; consistent with theory, the size of the advantage tracks the target's Fourier degree - largest for parity and shrinking when low-order structure is present. As an application, QHA serves as a compact high-order interaction detector across three domains - genetic epistasis, learning-parity-with-noise, and graph triangle detection - reaching the noise ceiling at the smallest parameter budget where field-standard linear methods fail.

As AI systems evolve from passive models into autonomous active agents capable of initiating actions, collaborating, and delegating tasks, the traditional boundaries of software systems blur. Traditional authorization and delegation frameworks, built around fixed principals, explicit requests, and static scopes, are insufficient to govern agentic systems. Agentic AI demands richer authorization semantics: agents must inherit and delegate permissions, act under time-limited authority, and coordinate through shared protocols. Existing Identity and Access Management (IAM) systems fail to fully capture this notion of agency, lacking mechanisms for recursive delegation, contextual boundaries, and dynamic scoping as executable governance primitives. Unlike access delegation standards such as OAuth 2.0, we treat delegation as a contractual term rather than merely a static token-based consent credential. This paper proposes a compositional governance framework that introduces primitives indispensable for agentic AI. We define types of delegation and their permissions and accountability implications, and we introduce a notion of resource scope attenuation to bound agentic access envelopes. These concepts are expressed as general relational definitions that can be composed into existing authorization domains (e.g., financial systems). To operationalize this composition, we define a compositional operator that overlays new agentic semantics, such as recursive delegation chains, onto existing relational policies without rewriting them. We substantiate this framework through formal proofs and empirical evaluation, showing that it provides a formal yet practical foundation for accountable authorization in agentic AI systems.

This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a continuous manifold, token interface, allowing visual tokens to operate as standalone entities within the architecture. Exploiting this discovery, we propose V-LynX, a scalable framework that integrates novel modalities into Video LLMs by repurposing the internalized interface. Departing from conventional paradigms that necessitate heavy modality-specific encoders or paired supervision, V-LynX employs a lightweight auxiliary pathway in parallel with the frozen vision encoder. Our method integrates new sensory inputs with intrinsic video priors by aligning both attention responses and statistical distributions using unpaired unimodal data sets. This ensures manifold compatibility while preserving the integrity of the Video LLMs. Extensive benchmarks demonstrate that V-LynX achieves SOTA and efficiency across audio-visual QA, 3D reasoning, high-frame-rate, and multi-view video understanding. The code is available at https://github.com/park-jungin/lynx.

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the input sequence length due to the global attention layers inside these models. This limits both their scalability and efficiency. In this work, we address this challenge with a simple yet general strategy: restricting the number of key/value tokens that each query interacts with during global attention. To achieve effective token selection, we introduce a two-stage framework. First, an inter-frame selection step operates at the frame level to identify frames that should be preserved. Second, an intra-frame selection step further discards more redundant tokens within the selected frames. Our analysis highlights the advantage of a diversity-based strategy for inter-frame selection, which ensures broad coverage of the scene. For intra-frame selection, we show that layer-aware sparsification is necessary, with the selection process guided by the entropy of the global attention pattern. Our approach offers a superior speed-accuracy trade-off compared to existing solutions. Extensive experiments show that it accelerates visual geometry transformers by over 85% for scenes with 500 images while maintaining, or even improving, baseline performance, which hints that how our token selection strategy can play a crucial role in future applications of visual geometry transformers. Our project website is available at https://zsh2000.github.io/good-token-hunting.github.io.

Large language models (LLMs) increasingly rely on long-context processing, but expanding context windows introduces substantial computational and financial costs. Existing context reduction approaches, including retrieval and memory compression methods, are typically evaluated using performance and efficiency metrics independently, limiting systematic comparison and deployment-aware decision-making. This paper introduces The Efficiency Frontier, a unified framework for cost--performance optimization in LLM context management. The framework models context strategy selection as a deployment-aware optimization problem that jointly accounts for task performance, token cost, and preprocessing reuse through amortized cost modeling. Unlike existing evaluations that compare methods in isolation, the proposed framework enables decision-oriented analysis. It identifies when different context management strategies become preferable under varying operational conditions. Experiments on HotpotQA reveal distinct operational regimes and transition boundaries between retrieval-based and preprocessing-based strategies. Results show that deployment-aware optimization reduces effective token usage by approximately 25% at comparable performance, enabling more cost-efficient deployment of large language model systems, while amortized memory compression achieves over 50% lower token cost relative to full-context prompting in higher-performance settings. Overall, the proposed framework provides a principled and practical foundation for evaluating and deploying scalable, efficient, and sustainable LLM systems across enterprise, scientific, and public-sector applications.

Tokens are becoming the basic units through which foundation models represent and process information for understanding and inference. However, traditional wireless communication, centered on bit-level fidelity, faces a mismatch between what is transmitted reliably and what downstream models actually consume. This mismatch calls for a communication design that directly accounts for token-level task relevance and downstream model requirements, rather than treating all transmitted bits as equally important. In this paper, we propose TONIC, a token-centric semantic communication framework for task-oriented wireless systems. The transmitter converts each source sample into a sequence of tokens, estimates token-level task relevance, and allocates protection through utility-aware unequal error protection under a fixed channel-use budget. At the receiver, token-level confidence is used to gate unreliable decisions, turning harmful substitutions into recoverable erasures before a Transformer-based completion model restores the masked tokens for final task inference. Our framework combines transmitter-side semantic-aware protection with receiver-side confidence-aware gating in a modular and interpretable architecture, rather than relying solely on fully black-box end-to-end learning. We further establish a utility-aware Bayes-risk interpretation for the receiver-side gating rule and study its interaction with unequal protection and completion. Experimental results on image classification show that TONIC consistently outperforms separation-based schemes, the pixel-domain DeepJSCC baseline, and token-domain baselines under matched communication budgets over AWGN, Rayleigh, and Rician channels.

Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial? Empirical evidence reveals a striking paradox: CoT often provides marginal or even negative gains on factual and open-ended tasks while multiplying token consumption. In this work, we show that LLM reasoning is not a static property of tasks or models, but a \emph{dynamic decoding state} that emerges during generation. Through systematic analysis, we find early-stage entropy dynamics provide a reliable signal of this state: tasks benefiting from CoT exhibit consistent entropy reduction, while others display unstable or increasing patterns. This behavior can be interpreted as a phase-transition-like shift from a high-entropy exploratory regime to a low-entropy structured reasoning regime. Based on these insights, we propose \textbf{EDRM} (Entropy Dynamics-based Reasoning Manifold), a lightweight and training-free routing framework that leverages early decoding entropy to adaptively select inference strategies. EDRM embeds entropy trajectories into a compact and interpretable manifold representation, enabling both zero-shot deployment and fine-grained instance-level adaptation. Across 15 benchmarks and 4 LLMs of varying scales and architectures, EDRM consistently outperforms static baselines. At the dataset level, EDRM achieves \textbf{41--55%} token reduction while improving accuracy with as few as 50 calibration samples. At the instance level, it further improves accuracy by up to \textbf{4.7%} while maintaining \textbf{27--45%} token savings. These results suggest that reasoning should be invoked selectively rather than by default, and demonstrate the effectiveness of entropy-driven decoding control for efficient and adaptive LLM inference.

Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict between these tasks, as a single token space is forced to support both high-level semantic abstraction and low-level pixel reconstruction. We propose WinTok, a concise hybrid tokenizer that achieves a win-win performance by explicitly decoupling the two objectives. WinTok supplements pixel tokens with a set of learnable semantic tokens, effectively mitigating cross-task interference without incurring the computational overhead of dual tokenizers. To further enhance understanding capability, we introduce an asymmetric token distillation mechanism: the semantic tokens are guided by pretrained semantic embeddings from any visual foundation model, enabling them to inherit strong discriminative power while maintaining flexibility. Across 10 challenging benchmarks, WinTok delivers consistent improvements in reconstruction, understanding, and generation. Trained on only 50M open-source data, WinTok surpasses the strong baseline UniTok by 11.2% in classification accuracy and achieves a competitive reconstruction rFID of 0.41, despite using substantially less training data. Code is released at https://github.com/markywg/WinTok.

Token economics has emerged as a useful lens for understanding resource allocation, value creation, and pricing in large language model systems. While recent work has increasingly treated tokens as economic primitives, there remains a substantial gap between high-level economic theory and the computational realities of modern AI infrastructure. This paper identifies and analyzes the key computational challenges that arise when token-economic principles are implemented in real-time inference systems. We argue that computational feasibility is not merely one dimension of token economics, but its governing constraint: these challenges are driven by fundamental tensions among fine-grained valuation, low-latency execution, and allocation optimality under uncertainty. To structure this problem space, we introduce the notion of \textbf{Computational Token Economics} and propose the \textbf{Token Economics Trilemma} -- a conditional no-free-lunch principle that captures the inherent trade-offs among granularity, real-time performance, and optimality. We further categorize the main technical challenges into three areas: real-time value accounting, constrained resource allocation, and economic-aware system architecture. Rather than presenting a complete solution, this paper aims to define a research agenda for bridging token economics and AI system design, highlighting open problems at the intersection of computational economics, machine learning systems, and AI infrastructure.

Deploying AI agents for repetitive periodic tasks exposes a critical tension: Large Language Models (LLMs) offer unmatched flexibility in tool orchestration, yet their inherent stochasticity causes unpredictable failures, and repeated invocations incur prohibitive token costs. We present the LOOP SKILL ENGINE, a system that achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm. On its first run, the agent executes the task with full LLM reasoning while the system transparently intercepts and records the complete tool-call trajectory. A greedy length-descending template extraction algorithm then converts this recording into a parameterized, branch-free Loop Skill -- a deterministic execution plan that captures the task's functional intent while parameterizing time-dependent and result-dependent variables. All subsequent executions bypass the LLM entirely: the engine resolves template variables against real-time values and replays the tool sequence deterministically. We prove two theorems: (1) Replay Determinism -- the step sequence of a validated Loop Skill is invariant across all future executions; (2) Write Safety -- concurrent access to persistent configuration is serialized through reentrant locks and atomic file replacement. Across a benchmark of periodic agent tasks spanning intervals from 5 minutes to 24 hours, the Loop Skill Engine reduces monthly token consumption by 93.3%--99.98% and cuts execution latency by 8.7x while eliminating output non-determinism. A multi-layer degradation strategy guarantees that tasks never stall. We release the engine as part of the buddyMe open-source agent framework.

From pre-training to query-time augmentation, web-scraped data helps to improve the quality and contextual relevancy of content generated by large language models (LLMs). However, large-scale web scraping to feed LLMs can affect site stability and raise legal, privacy, or ethics concerns. If website owners wish to limit LLM-related web scraping on their site, due to these or other concerns, they may turn to scraper access control mechanisms like the Robots Exclusion Protocol. To be most effective, such mechanisms require site owners to first identify the scrapers that they wish to restrict (e.g., via User-Agent strings). Existing mechanisms to identify LLM-related scrapers rely on voluntary disclosure by companies, one-off experiments by researchers, or crowd-sourced reports -- methods that are neither reliable nor scalable. This paper proposes a novel technique for accurately and automatically inferring LLM-related scrapers. We host dynamic websites that serve unique canary tokens to each visiting scraper, then prompt LLMs for information about our sites. If an LLM consistently generates outputs containing tokens unique to a scraper, it provides evidence of exposure to that scraper. Via experiments across 22 production LLM systems, we demonstrate that our approach can reliably identify which scrapers feed which LLM, including several that are not publicly known or disclosed by the companies. Our approach provides a promising avenue for unprivileged third parties to infer which scrapers serve data to which LLMs, potentially enabling better control over unwanted scraping.

Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the assumption of conditional independence at high confidence levels, which ensures negligible discrepancy between the marginal and joint distributions. However, the stringent confidence thresholds required to preserve accuracy severely constrain the scalability of parallelism. Through systematic token-level statistical analysis, we reveal that a substantial proportion of tokens converge to their correct predictions early in the denoising process yet fail to reach standard confidence thresholds, confirming that current confidence-based criteria are overly conservative. In response, we introduce LEAP (Lookahead Early-Convergence Token Detection for Accelerated Parallel Decoding). LEAP is a training-free, plug-and-play method that leverages future context filtering and multi-sequence superposition to detect early-converging tokens. By validating the alignment between early convergence and correctness, we enable reliable early decoding of these tokens. Benchmarking across diverse domains demonstrates that LEAP significantly lowers inference latency and decoding steps. Compared to confidence-based decoding, the average number of denoising steps is reduced by about 30%. On the GSM8K dataset, combining LEAP with dParallel accelerates decoding to 7.2 tokens per step while preserving model precision. LEAP effectively breaks the reliance on high-confidence priors, offering a novel paradigm for parallel decoding.

Agentic LLM workloads put bit-identical tokens at shifted positions every turn, voiding prefix caches at the first byte of divergence. Operators report cache-hit regressions ranging from moderate slowdowns to severe TTFT spikes of 10-16s on unchanged content. Prior position-independent caching systems correct RoPE on the full $d_K$-dimensional key, an architectural cost imposed by GQA, not by caching itself. Multi-Head Latent Attention, deployed at scale in DeepSeek-V2/V3/R1, Kimi-K2/Moonlight, GLM-5, and Mistral Large 3, factors each KV row into a position-free $c_{KV}$ and a 64-dim $k_r$ correctable in closed form; this structure motivates content-addressed caching as a natural fit rather than a GQA workaround. We present Irminsul, which extends SGLang's radix cache with content-hash keying over CDC-chunked segments and a $δ$-rotation rule for $k_r$. We evaluate three native MLA-MoE deployments - DeepSeek-V2-Lite (16B/2.4B), Kimi Moonlight-16B-A3B, and JoyAI-Flash (48B/3B) - with output-consistency on all three and recovery measured on the two endpoints; Irminsul recovers up to ~83% of prompt tokens above exact-prefix on agentic traffic while delivering 63% prefill energy savings per cache hit. We argue that content-addressed caching belongs in the serving stack as a first-class primitive, not a retrofit over prefix matching.

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.

The increasing use of token-based representations in language-driven applications has motivated wireless token communication, where tokens are treated as fundamental units for transmission. However, conventional communication systems overlook dependencies among tokens and allocate transmission resources uniformly, leading to inefficient use of limited wireless resources under channel impairments. In this paper, we propose a context-aware token communication framework that leverages a masked language model (MLM) as a shared contextual model between the transmitter (Tx) and receiver (Rx). At the Rx, we develop a context-aware token detection method that integrates channel likelihoods with MLM-based contextual priors under a Bayesian formulation, enabling robust token inference over noisy channels. At the Tx, we propose a context-aware token masking strategy that selectively omits tokens that can be reliably inferred at the Rx, allowing the available power budget to be concentrated on more informative tokens. These components are jointly designed through a shared MLM, establishing a unified Tx-Rx framework for efficient token transmission and detection. Simulation results demonstrate that the proposed framework significantly improves reconstruction performance compared to conventional and existing token communication schemes, achieving up to 1.77X and 1.63X performance gains on the Europarl corpus and WikiText-103 datasets, respectively.

Token communication has emerged as a promising framework for efficient wireless transmission by representing source data as compact semantic tokens. However, transmitting full semantic tokens still incurs considerable communication overhead. In this paper, we propose an evolving semantic token communication system with a parametric memory network over MIMO fading channels. Specifically, only an equal-length prefix of each semantic token is transmitted, which reduces transmission cost while preserving a consistent token structure for receiver-side recovery. At the receiver, a parametric memory network is introduced to reconstruct the missing suffix information from the received token prefixes, where semantic memory is stored implicitly in the network parameters. To realize this design, full semantic tokens are first organized into a codebook, and truncated tokens are paired with the codeword labels of their corresponding full tokens. Based on these token-label pairs, kNN-based teacher distributions are constructed to fine-tune a pretrained GPT-2-based recovery module, which learns to infer the codeword distribution of each incomplete token and recover the corresponding complete semantic token. In addition, an online evolution strategy is developed to periodically update the parametric memory network and the entire system using newly observed test samples, thereby improving adaptability under distribution shifts. Experimental results demonstrate that the proposed method consistently outperforms the existing evolving memory benchmark under different channel conditions and channel bandwidth ratios, with up to 1.09 dB PSNR improvement.

We present PolyKV, a system in which multiple concurrent inference agents share a single, asymmetrically compressed KV cache pool. Rather than allocating a separate KV cache per agent -- the standard paradigm -- PolyKV writes a compressed cache once and injects it into N independent agent contexts via HuggingFace DynamicCache objects. Compression is asymmetric: Keys are quantized at int8 (q8_0) to preserve softmax stability, while Values are compressed using TurboQuant MSE -- a Fast Walsh-Hadamard Transform (FWHT) rotation followed by 3-bit Lloyd-Max quantization with centroids tuned to N(0,1). We evaluate across two model scales (SmolLM2-1.7B-Instruct and Llama-3-8B-Instruct), three context lengths (600-7,194 tokens), and up to 15 concurrent agents. PolyKV achieves a stable 2.91x compression ratio across all configurations. On Llama-3-8B with 15 agents sharing a 4K-token context, PolyKV reduces KV cache memory from 19.8 GB to 0.45 GB -- a 97.7% reduction -- while maintaining only +0.57% perplexity degradation and a mean BERTScore F1 of 0.928. PPL delta does not grow with agent count and improves as context length increases, inverting to -0.26% at 1,851 coherent tokens. To our knowledge, no prior work combines a single shared, lossy-compressed KV pool with multi-reader concurrent agent access.

The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of tokens, three questions naturally arise: (1) Where do AI agents spend the tokens? (2) Which models are more token-efficient? and (3) Can agents predict their token usage before task execution? In this paper, we present the first systematic study of token consumption patterns in agentic coding tasks. We analyze trajectories from eight frontier LLMs on SWE-bench Verified and evaluate models' ability to predict their own token costs before task execution. We find that: (1) agentic tasks are uniquely expensive, consuming 1000x more tokens than code reasoning and code chat, with input tokens rather than output tokens driving the overall cost; (2) token usage is highly variable and inherently stochastic: runs on the same task can differ by up to 30x in total tokens, and higher token usage does not translate into higher accuracy; instead, accuracy often peaks at intermediate cost and saturates at higher costs; (3) models vary substantially in token efficiency: on the same tasks, Kimi-K2 and Claude-Sonnet-4.5, on average, consume over 1.5 million more tokens than GPT-5; (4) task difficulty rated by human experts only weakly aligns with actual token costs, revealing a fundamental gap between human-perceived complexity and the computational effort agents actually expend; and (5) frontier models fail to accurately predict their own token usage (with weak-to-moderate correlations, up to 0.39) and systematically underestimate real token costs. Our study offers new insights into the economics of AI agents and can inspire future research in this direction.

Diffusion large language models (dLLMs) enable parallel text generation by iteratively denoising a fully masked sequence, unmasking a subset of masked tokens at each step. Existing decoding strategies rely on static confidence metrics computed at a single denoising step, ignoring temporal history and often leading to premature unmasking of unstable tokens. In this work, we theoretically establish that a token's temporal instability, quantified by the KL divergence between consecutive prediction distributions, provides a strict lower bound on its mutual information with the remaining masked context, indicating that temporally unstable tokens are inherently unsafe to unmask. Based on this insight, we propose Stability-Weighted Decoding (SWD), a training-free, plug-and-play strategy that incorporates temporal stability into token scoring and acts as a universal modulator for arbitrary score-based decoding policies. Experiments on code generation and mathematical reasoning benchmarks demonstrate that SWD consistently improves generation accuracy across representative scoring metrics and selection policies, and exhibits exceptional robustness, maintaining a significant performance lead over standard baselines across varying acceleration ratios.

Large language models (LLMs) now support contexts of up to 1M tokens, but their strengths and weaknesses on complex long-context tasks remain unclear. To study this, we focus on multi-document legal case summarization, where a single case often spans many documents exceeding 100K tokens. We systematically evaluate 12 frontier LLMs with Gavel, which consists of Gavel-Ref, a reference-based evaluation framework with checklist, residual-fact, and writing-style evaluations, and Gavel-Agent, a reference-free agent for evaluating factual coverage directly from source documents. Our results show that current models are more prone to omitting key information than hallucinating. They all perform well on simple checklist items, such as filing date, but struggle with rare and complex items, such as settlements. Performance also declines as case length increases. To meta-evaluate Gavel, we collect 160 hours of human annotations. Gavel-Agent reduces token usage by at least 36% compared to end-to-end and chunk-by-chunk methods while achieving competitive performance. Gavel-Agent also generalizes to the medical domain, performing the best with at least 77% fewer tokens.

Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespread ``blind signing'' (approving transactions without understanding them). Through interviews with 16 Web3 users, we find that effective explanations should be structured, risk-aware, and grounded at the token-flow level. Motivated by these findings, we formulate TxSum, a new domain-grounded NLP task for DeFi transaction explanation, and construct a dataset of 187 complex Ethereum transactions with 2,375 token-flow annotations and transaction-level summaries. We further introduce MATEX, a grounded multi-agent framework for high-stakes transaction explanation. It selectively retrieves external knowledge under uncertainty and audits explanations against raw traces to improve token-flow-level factual consistency. MATEX achieves the strongest overall explanation quality, especially on micro-level factuality and intent quality. It improves user comprehension on complex transactions from 52.9% to 76.5% over the strongest baseline and raises malicious-transaction rejection from 36.0% to 88.0%, while maintaining a low false-rejection rate on benign transactions.

Token communications (TokenCom) is an emerging generative semantic communication paradigm, where tokens serve as compact representation units across modalities. Their contextual dependencies can be exploited by pretrained large models for semantic recovery. In this paper, we propose token-domain multiple access (ToDMA), a large-model-driven semantic multiple access scheme for massive token communications. ToDMA integrates unsourced random access with context-aware token processing. It enables massive uncoordinated devices to transmit tokenized source representations over common uplink resources. Specifically, each token index is associated with a shared modulation codeword, exposing token-level structure to the receiver for context-aware recovery. At the receiver, compressed sensing is first employed to jointly detect active tokens and estimate their corresponding channel state information (CSI) from the superposed signals. The source token sequences are then reconstructed by exploiting the consistency of token-associated CSI across multiple token positions. In the presence of token collisions, some active tokens may remain unassigned, leading to missing entries in the reconstructed token sequences. To recover these tokens, candidate-restricted masked-token prediction is performed using pretrained contextual models, thereby leveraging token-level context to mitigate collision effects. Simulation results on both image and text transmission tasks demonstrate that ToDMA reduces access latency while maintaining favorable token recovery and semantic reconstruction quality, showing its scalability for semantic multiple access.

In this paper, we introduce token communications (TokCom), a large model-driven framework to leverage cross-modal context information in generative semantic communications (GenSC). TokCom is a new paradigm, motivated by the recent success of generative foundation models and multimodal large language models (GFM/MLLMs), where the communication units are tokens, enabling efficient transformer-based token processing at the transmitter and receiver. In this paper, we introduce the potential opportunities and challenges of leveraging context in GenSC, explore how to integrate GFM/MLLMs-based token processing into semantic communication systems to leverage cross-modal context effectively at affordable complexity, present the key principles for efficient TokCom at various layers in future wireless networks. In a typical image semantic communication setup, we demonstrate a significant improvement of the bandwidth efficiency, achieved by TokCom by leveraging the context information among tokens. Finally, the potential research directions are identified to facilitate adoption of TokCom in future wireless networks.