Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Saturday 15 August

Artificial Intelligence

SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion

Large language model (LLM) agents can continually improve without parameter updates by converting historical experience into reusable procedural knowledge. However, existing methods often consolidate experience based on semantic similarity or LLM judgments, which may merge superficially related but behaviorally incompatible strategies and thereby degrade performance. To address the issue, we propose SkillCommit, an online skill evolution framework that continuously transforms experience into a hierarchical library of reusable skills. Rather than generalizing from individual experiences immediately, SkillCommit first preserves each experience as an instance-specific patch, retaining its locally validated behavior. As patches accumulate, SkillCommit abstracts those sharing a common behavioral mechanism into higher-level skills. Specifically, for each incoming skill, embedding-based retrieval first identifies candidate related skills. Cross-instance replay and an LLM-based mechanism check determine whether these skills transfer across cases and share a common underlying mechanism. Candidates that pass both checks are abstracted into a higher-level skill and committed only if it preserves the validated behavior of all constituent skills. Experiments on RuleArena, OpenExempt and KOR-Bench demonstrate that SkillCommit consistently improves agent performance across diverse domains. Moreover, the learned skills transfer across model scales and families, enabling cross-model experience transfer.
Read the full abstract

Computer Vision

From "What-If" to "What-Is": Counterfactual Thinking-Inspired Semantic Alignment for Visual Brain Decoding

Visual brain decoding reconstructs visual content perceived by a person from neural measurements such as fMRI, providing a computational approach to studying how visual information is represented in the brain. Recent multimodal representations and diffusion priors have improved reconstruction realism. However, visually plausible reconstructions may contain incorrect objects, attributes, or relations because a strong generative prior can complete content not sufficiently specified by the decoded representation. Conventional reconstruction metrics mainly assess the final image and may therefore obscure such semantic errors. We propose ConceptAlign, a counterfactual semantic alignment framework for visual brain decoding. ConceptAlign pools decoded visual tokens and projects them into a frozen text-embedding space, aligning the representation with the ground-truth caption while separating it from scene-preserving near-miss alternatives. Generated offline by an LLM, these alternatives modify one critical object, attribute, or relation while retaining the scene. A margin-based objective learns fine-grained semantic boundaries between the observed stimulus and plausible but incorrect interpretations without requiring LLM calls during inference. We introduce a systematic three-level semantic evaluation framework covering foundational discriminability, counterfactual description discrimination, and representational geometry. Experiments on the Natural Scenes Dataset show that ConceptAlign improves reconstruction measures, counterfactual semantic discrimination, and representational alignment over the MindEye2 backbone. Matched negative-source ablations, independent LLM and human-written alternatives, and human evaluation support the effectiveness and robustness of the supervision, with favorable patterns in fine-grained conflicts, limited-data decoding, and cross-subject structure.
Read the full abstract

All authors Kaitao Yan, Chi Liu, Congcong Zhu, Huajie Chen, Gengshen Wu, Minghao Wang, Xiaotong Han, Tianqing Zhu

Numerical Analysis · Cross-listed from quant-ph

Exact and Efficient Circuit Construction for Block Encoding Matrix Polynomials

A recent interpolation-based Quantum Signal Processing (QSP) framework by Alase bypasses the phase-finding procedures required in conventional QSP, allowing for a direct encoding of the target polynomial into a quantum circuit. However, this approach assumes access to a diagonal block encoding of function values without providing an explicit circuit construction. In this work, we address this gap by developing an explicit circuit construction method for diagonal block encodings. The resulting algorithm achieves a computational cost of $\mathcal{O}(d\log d)$ for explicitly constructing block encodings of matrix polynomials, improving upon the best-known theoretical bounds of previous methods. Numerical results confirm this scaling, demonstrating that circuit parameters for polynomial degrees up to $10^7$ can be computed in about a minute on a standard CPU.
Read the full abstract

Computer Vision

A Unified Backbone–Expert Framework with Relation-Token and Residual–Classifier Interfaces for Automatic Modulation Recognition

Automatic modulation recognition (AMR) faces distinct representation bottlenecks under varying observation lengths, where a single model architecture often fails to excel. To address this, we propose a unified backbone-expert framework with a common convolutional state-space backbone and two specialized interfaces. For short sequences, we inject explicit lag-aware complex-plane descriptors as relation tokens before encoding to compensate for information loss. For long sequences, we design a gated multi-scale residual refinement module to correct the feature map, combined with a fixed-averaging classifier collaboration to harness complementary evidence. Our framework achieves overall average accuracies of 67.28 \pm 0.14% on RML2016.10b and 87.19 \pm 0.77% on HisarMod2019 (mean \pm sample standard deviation over three runs), respectively. The framework's efficacy is further validated through three-seed ablations, native-length cross-configuration tests, and controlled window studies, confirming the benefit of expert-interface decoupling over one-size-fits-all architectures.
Read the full abstract

Data Structures and Algorithms

Fair Division Meets Scheduling: Approximately Envy-Free Interval Scheduling

We study interval scheduling from the perspective of fair allocation. There are $m$ identical machines and a set of intervals, each specified by a start time, an end time, and a nonnegative weight. A schedule assigns a subset of the intervals to the machines so that no two intervals on the same machine overlap, and the goal is to maximize the total weight of scheduled intervals. Viewing machines as agents and intervals as goods, we require the schedule to be envy-free up to one item (EF1), and we measure efficiency against the offline optimum without fairness. In the offline setting, we give an algorithm that computes an EF1 schedule whose loss is at most a factor of $3/2$ in the unweighted regime, and we prove lower bounds of $\frac{3m-2}{2m-1}$, approaching $3/2$, in both the unweighted and the unit-length weighted regimes, so the price of fairness is $3/2$ in the limit. In the online setting, intervals arrive in nondecreasing order of start times; an arriving interval must be accepted or rejected, rejections are irrevocable, and an accepted interval may be revoked, and lost, at any time before it ends. For the unweighted regime we present Greedy-Balanced, a simple algorithm that maintains EF1 at every point in time and is $(2-\tfrac{1}{m})$-competitive against the offline optimum without fairness, and we prove a matching lower bound for every deterministic algorithm; the optimal deterministic fair competitive ratio is thus exactly $2-\tfrac{1}{m}$. Experiments on real-world benchmark instances show that Greedy-Balanced performs well beyond its worst-case guarantee, with an observed ratio never exceeding $1.306$.
Read the full abstract

Robotics

Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models

We ask whether a small, directly addressable hidden-state intervention can place a learned world model on an intended counterfactual future and then let the model's own dynamics carry that future forward. In a controlled two-object collision environment, we study a 192-dimensional recurrent model trained on factual and locally edited counterfactual trajectories. Candidate carriers are learned from training-only counterfactual-minus-factual hidden differences, and an affine map predicts carrier coordinates from the factual state and requested edit without access to the native counterfactual hidden state at test time. For bounded single-component velocity edits, rank 4 is the smallest tested rank on the preregistered grid that satisfies the development criteria. A one-shot rank-4 patch launches a 12-transition autonomous rollout without future observations, teacher forcing, repeated hidden-state correction, or physical-state clamping. The frozen procedure satisfies the preregistered 2-of-3 fresh-checkpoint replication rule and remains reusable at nearby anchors. The same Single-derived carrier and Single-only affine map also support bounded same-object two-component requests. Across the matched training regimes, broader counterfactual support was associated mainly with better Joint rollout accuracy and more additive Joint hidden responses. Composition-related structure is enriched in the rank-4 subspace but is not confined to it, and local recurrent diagnostics show strong one-step coupling from the carrier to the rest of the hidden state. A position-edit stress test fails the required specificity controls. Together, these results support a compact dynamics-effective intervention-entry interface, not a closed four-dimensional state or an intrinsic state dimension.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Beyond Effective Sample Size: Effective Number of Proposals for Adaptive Importance Sampling

Population-based adaptive importance sampling (AIS) methods use a set of proposal densities to approximate complex target distributions. Their performance is commonly assessed through effective sample size (ESS) and related weight-based diagnostics, which measure the concentration of normalized importance weights. However, a large ESS only indicates that the normalized sample weights are not strongly concentrated; it does not describe how the proposal components are arranged in the sampling space. In population-based AIS, several proposal components may generate samples in the same region of the target, so the sample weights can appear well balanced even though the effective number of distinct proposal components is small. This letter introduces the effective number of proposals (ENP), a similarity-aware proposal-level diagnostic for population-based AIS. ENP combines the total normalized weight assigned to each proposal with a redundancy measure computed from similarities among target-weighted samples, estimating the number of non-redundant empirical proposal contributions to the approximation. We establish basic effective-number properties and show that ENP detects proposal collapse and duplication missed by standard ESS. We also illustrate its use as a targeted feedback signal for proposal rejuvenation.
Read the full abstract

Cryptography and Security

An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning

Differentially private federated learning must balance privacy protection against model accuracy and training efficiency. Static gradient clipping applies a fixed threshold throughout training and across model layers, which can cause excessive clipping when the threshold is too small or unnecessarily large noise when it is too large. This paper presents DDP-SA-adaptive, an adaptive gradient clipping and noise adding mechanism for differentially private federated learning with secure aggregation. At each communication round, every client determines a separate clipping threshold for each model layer from the median of its per-sample gradient norms. The resulting layer-wise thresholds adapt to the evolving gradient distributions and calibrate the Laplace noise added before the updates are encoded and secret-shared among intermediate aggregation servers. We evaluate the proposed mechanism on a federated regression task in terms of efficiency, accuracy, privacy, convergence, clipping norm, and noise magnitude. Compared with the static DDP-SA baseline, DDP-SA-adaptive reduces the number of communication rounds by 6.81%, total training time by 19.21%, and average per-round training time by 13.33%, leading to improved training efficiency. It also reduces test loss by 98.74% and increases test R2 by 3.41%, leading to improved model accuracy. To attain R2 = 0.99, the adaptive mechanism operates with a privacy budget of approximately epsilon = 0.1, compared with epsilon = 0.4 for static DDP-SA, thus providing stronger privacy protection and achieving stronger privacy guarantees. These results demonstrate that round-wise, layer-wise adaptation can improve the privacy-accuracy-efficiency trade-off of differentially private federated learning.
Read the full abstract

Cryptography and Security

SAEFUZZ: Smart Contract Vulnerability Detection through Statically Guided Evolutionary Fuzzing

The effectiveness of smart contract fuzzing depends strongly on whether generated transactions reach deep, state-dependent execution paths. Existing fuzzers often generate highly random call sequences, wasting executions on semantically invalid or low-value states and leaving vulnerabilities that require specific invocation orders unexplored. We present a lightweight method for generating fuzz test cases under bytecode-level static guidance. We construct an Ethereum virtual machine control-flow graph, extract paths containing vulnerability-relevant instructions, recover function selectors, and order externally callable functions according to storage read-write dependencies. A coverage-guided evolutionary strategy then generates, evaluates, recombines, and mutates executable seeds. Five dedicated runtime oracles target reentrancy, integer overflow or underflow, block-state dependence, unsafe delegate calls, and frozen Ether. The evaluation uses deployed Ethereum contracts, including labelled vulnerable contracts. SAEFUZZ detects most labelled vulnerable contracts, yielding 98.50% accuracy, 90.00% precision, and 81.82% recall. It also achieves 84.07% mean instruction coverage, with valid test cases accounting for 93.48% of generated cases. Ablation results indicate that static guidance, directed seed generation, and vulnerability-specific oracles each contribute to the final performance.
Read the full abstract

Artificial Intelligence

Constitutive Priors for Machine Intelligence: A Legitimacy Theory of the Artificial Physical World

Machine intelligence's push into the physical world is stuck on a gap: deployment demands auditable judgments from day one, fault samples are scarce or absent, and the norms defining "what counts as a fault" live in design documents, not in operational data. We argue this gap is structural, and locate where it can be legitimately closed. We divide the worlds machine intelligence faces into four (phenomenal, basic physical, artificial physical, artificial symbolic) along one axis of constraint strength, and give the Promulgation Criterion: extracting a prior framework from a world is legitimate if and only if the world is intentionally constituted (C1) and has left a readable generative archive (C2). On the criterion's two gradient axes, exactly one world is high on both: the artificial physical world (buildings, factories, infrastructure), whose norms precede their instances; the legitimate path is to extract the framework from the archive, not to induce it from data. We then show what shape such a framework must take: four construction goals force four incompatible carriers, hence at least four layers (syntax, concepts, knowledge, instances); on a closed concept layer fault localization is decidable in polynomial time, and every judgment is interrogable, traceable to a promulgated clause. The same criterion fixes the runtime division of labor with LLMs: promulgatable duties go to rule engines, on-site judgments beyond promulgation go to LLMs, and every generation sandwiched by promulgated clauses is auditable. The theory is falsifiable: four bets (P1-P4) with explicit falsification conditions – among them that the next large-scale AI breakthrough occurs in the artificial physical world. Evidence: formal proofs (Appendix A); two cases (Appendix B: a cooling plant; the Curiosity rover Sol 1536 anomaly); eight reverse-read lineages, from BACnet to RDF/OWL (Appendix C).
Read the full abstract

2608.15147 · 15 Aug · Major revision. Main paper (51 pp.) plus supplementary material (60 pp.): formal machinery, demonstrations, and witness dossiers moved to the supplement. New: LLM division-of-labor (Ch. 6); four predictions plus two structural corollaries (Ch. 7); I/O-logic semantics (A.1); non-identifiability boundary (A.2); sample-complexity separation (A.6); Curiosity Sol 1536 replay (B.2). Thesis unchanged

Machine Learning

PureTD: Reinforcement Learning for Backgammon Money Games with No Evaluation-time Search

We revisit Tesauro's TD-Gammon for backgammon money games in the setting of no evaluation-time search. Both checker play and cube action (use of the doubling cube) are learned from scratch via self-play reinforcement learning (RL), with minimal hand-coded logic and no expert features. In this setting, we demonstrate that pure self-play RL suffices to train models that reach near-state-of-the-art playing strength. Specifically, for cubeful money games, our search-free model evaluates faster and is substantially stronger than the open-source engines GNU Backgammon and Open Sage running a one-move (1-ply) look-ahead search. Our method of training a cubeful model also outperforms the standard approach of training a cubeless model and deriving cubeful equity with Janowski-style formulas, when the two models are equally sized.
Read the full abstract

Artificial Intelligence

ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models

Large Language Models (LLMs) have been increasingly adopted in Text-to-SQL systems, yet SQL errors remain a major obstacle in real-world Text-to-SQL inference pipelines. Existing SQL correction approaches either rely on large-scale, high-quality training data with substantial overhead, or adopt single-path agentic workflows that are brittle to early mistakes and prone to error propagation. To develop a practical SQL correctness system for industrial scenarios, we present a training-free framework that formulates SQL correction as a plan-guided, tree-structured debugging process. By maintaining multiple correction strategies and enabling backtracking, the framework mitigates error accumulation during iterative refinement. We further integrate execution-based verification and clause-level diagnostic tools to support strategy pruning and precise error localization. We evaluate the system on the BIRD-Critic benchmark and observe consistent accuracy gains over strong LLM backbones and representative agent-based baselines, achieving a 9.42% improvement over the previous state-of-the-art method. The framework is also deployed in the Torch Log Service (TLS) of Volcano Engine to support an online Text-to-TLS API. In production, it improves execution accuracy from 36.77% to 53.61% on real user queries with a representative strong LLM backbone (GPT-5). These results demonstrate the effectiveness and stability of our approach in real-world deployments.
Read the full abstract

All authors Xinmei Huang, Jie Song, Peng Li, Fuxin Jiang, Jing Zhang, Tieying Zhang, Jianjun Chen, Chenming Liu, Tao Yang, Maoyin Liu, Wenda Li, Hong Chen, Cuiping Li

Artificial Intelligence · Cross-listed from stat.ML

A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors

Pretrained diffusion models represent image distributions through a continuum of progressively smoothed distributions. This multiscale structure organizes generation from global structure to fine detail and supports high-quality, diverse samples. We exploit the same multiscale diffusion prior for linear imaging inverse problems. Rather than using the pretrained model only as a denoiser in an outer iteration, we define a surrogate likelihood whose center is aligned with the clean-image coordinate and whose covariance accounts for residual diffusion uncertainty. This construction defines an explicit surrogate posterior path, from which we derive continuous posterior dynamics. A tunable Langevin component supports target tracking and allows the amount of posterior exploration to be adapted to the application. We prove endpoint consistency and a finite-horizon tracking bound and, in the exact-score setting, first-order weak accuracy. For computation, we derive the Posterior-Dynamics Implicit–Explicit sampler (PD-IMEX), a stable method using one score evaluation per diffusion scale and an implicit data-consistency update. Experiments on deblurring, super-resolution, and inpainting show strong reconstruction quality at 100 score evaluations, coarse-grid stability, and controllable fidelity–diversity behavior.
Read the full abstract

All authors Zhaoqiang Liu, Tongyao Pang, Ruibing Wang, Yang Zheng

Artificial Intelligence

Translating finite-domain integer constraint models to CP/SMT/ILP/PB/SAT solvers with CPMpy

Constraint solving is a declarative approach for solving combinatorial satisfaction and optimization problems. The user specifies their problem through constraints and decision variables, and a generic solver is used to find a solution. Several constraint-solving technologies exist, and certain solvers perform well on certain problems. Therefore, it is useful to try different solvers given a particular application. However, each solving paradigm supports different types of constraints and decision variables. Our goal is to translate high-level constraint satisfaction and optimization problems into any lower-level formalism, including CP, SMT QF-LIA, ILP, PB and (Max)SAT. This allows for comparing different solving technologies for a particular problem, without requiring a user to manually remodel it for each solving paradigm. We define a high-level language of logical and arithmetic operations, and useful additional functions and constraints, which are known as global constraints in the CP community. We then present a modular framework for transforming our high-level modeling language to CP/SMT/ILP/PB and (Max)SAT solvers. While many transformations are partly described in the literature, we observe that they can be implemented through a modular waterfall of smaller components, where lower-level paradigms reuse the transformations of higher-level paradigms. Two recurring challenges are handling the negation of arbitrary subexpressions and avoiding the introduction of auxiliary variables. Additionally, we take special care linearizing non-linear operators for ILP, PB and SAT-solvers. The transformation waterfall is implemented and evaluated in the open-source CPMpy library. Our results show that constraint models significantly change throughout the transformations, and that optimizations to the linearization of constraints are essential for ILP and PB solvers.
Read the full abstract

All authors Tias Guns, Ignace Bleukx, Hendrik Bierlee, Jo Devriendt, Emilio Gamba, Orestis Lomis, Wout Piessens, Thomas Sergeys, Dimos Tsouros, Wout Vanroose, Hélène Verhaeghe

Computer Vision

HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generation

Diffusion-based methods have dominated the HOI generation, as they enable critical contact fusions or signals to guide the diffusion process. However, they often result in high artifacts and unstable interaction quality due to error accumulation during iterative denoising. In this work, we propose HOIMask, the first generative masked framework for modeling HOI motion in discrete space. HOIMask first encodes both motion sequences and contact-aware signals into discrete 2D human and object token maps via HOI Vector Quantization (VQ), preserving fine-grained spatial-temporal structure beyond conventional 1D representations. On this basis, a generative masked modeling framework is employed to jointly capture human-object interaction dynamics, leveraging a transformer architecture designed to model complex spatial-temporal and interaction dependencies. To generate more coherent and physically plausible motions, we further introduce a novel contact-aware reconstruction guidance in discrete space during inference, which fuses contact signals to optimize HOI tokens that forces the generated motion with higher spatio-temporal consistency. With craftily designed motion interaction tokens, dedicated architecture and guidance strategy, HOIMask outperforms state-of-the-art diffusion-based methods, generating more realistic and semantically aligned HOI motions. Please refer to https://jyhflash.github.io/HOIMask/ for more results.
Read the full abstract

All authors Yihong Ji, Jinsong Zhang, He Hu, Hongbo Xu

Robotics

StructRL: Structured Action-Space Exploration for Flow-Based VLAs

Flow-based Vision-Language-Action (VLA) models are now widely used for continuous robotic manipulation, and online reinforcement learning (RL) is emerging as a key technique for adapting them to new tasks. Existing RL methods typically inject stochasticity inside the denoising chain, often through isotropic or temporally independent noise. However, effective robot exploration calls for structured noise: temporally smooth and scaled differently across action groups. We show that simply switching the in-chain noise to a structured form does not suffice: noise added at an intermediate flow time can be weakened by the remaining denoising steps before execution, a phenomenon we call Structured Noise Dilution. We propose StructRL, which avoids dilution by relocating policy stochasticity to the action space via three coupled choices: (i) a deterministic ODE decoder, (ii) structured noise injected directly in the action space, and (iii) last-step replay, where policy-gradient updates avoid assigning likelihoods to intermediate denoising states. This keeps structured exploration tied to the executed action while providing a tractable training signal for the flow decoder. Across three flow-based VLA models on multiple simulated manipulation benchmarks and two real-world tasks, StructRL improves exploration efficiency and OOD performance over prior in-chain baselines, demonstrating the effectiveness of structured action-space exploration for adapting flow-based VLA with RL. Project page: https://flyfaerss.github.io/structrl/
Read the full abstract

All authors Jiarui Yang, Bin Zhu, Jingjing Chen, Na Zou, Yanwei Fu, Jianggang Zhu, Yu-Gang Jiang

Artificial Intelligence

ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Revisions

Designing an ABR algorithm for a network scenario takes an engineer months, and large language models (LLMs) now do this work in hours. But either way, the algorithm is fixed once it is deployed. It fits the networks seen during its design and falls behind on the networks that arrive afterwards. We ask whether an ABR algorithm can keep being designed after deployment, revised as each new network arrives, without becoming worse on any network it already serves. We propose ReForge, which keeps a pool of existing ABR policies unchanged and lets an LLM revise only the rules that decide which policy chooses the next bitrate. When a new network arrives, the LLM reads how the current rules and every policy perform on the networks served so far and rewrites the rules. The rewrite is deployed only if a replay in simulation shows that it improves the served networks as a whole and makes none of them worse. A fast GPU simulator that replays every episode exactly makes this acceptance test cheap enough to run for every revision. We evaluate ReForge on nine real-world network datasets, with new networks arriving one at a time. The revisions raise the mean QoE from 1.43 to 1.79, past the best single policy at 1.66 and close to the 1.86 of selecting the best policy for each dataset, while the QoE on the networks served first does not drop. The gain also holds in a real video player. All code, data, and records will be available.
Read the full abstract

Software Engineering

Mobile App Rewrites via Dual Boot

We term the mechanism dual boot: the ability to host two mobile application variants within a single binary with a boot-time variant selection. This mechanism, combined with build-generated symbol resolution maps and linker retain lists, also enables two additional capabilities not inherent to the mechanism alone: (1) in-binary A/B experimentation between full application variants, and (2) graceful deprecation of the legacy variant without user disruption: preserving app store listing, branding, and install base. We frame the complete lifecycle as the first application of the Strangler Fig pattern to native mobile platforms. We validate the architecture across three evaluation scenarios, with improvements in developer productivity, experimentation capability and flexibility. The system contributed to a complete iOS application rewrite, from initial embedding through multi-segment experimentation to full deprecation of the legacy variant, without losing users throughout the 10-month evaluation.
Read the full abstract

All authors Gaurav Nijhara, Jasmit Kaur Saluja, Pritesh Shah, Dustin Shahidehpour, Hari Panjwani

Systems and Control · Cross-listed from math.OC

Consensusability of Continuous-Time Multi-Agent Systems With Unbounded Heterogeneous Constant Delays: A Signed Laplacian Perspective

The consensus of continuous-time multi-agent systems with unbounded and heterogeneous constant delays is investigated by combining frequency-domain analysis and algebraic graph theory. Several types of signed Laplacians are constructed to characterize consensusability under delays. The core results are established based on the defined delay-embedded signed Laplacian, where a small-delay link creates a cooperative interaction and a possibly unbounded large-delay link creates an antagonistic interaction between the agents. The dividing line between small and large delays is given by $\tau_{ij}=\pi/2\lambda_{\max}(L_0)$, where $\lambda_{\max}(L_0)$ refers to the maximum eigenvalue of the conventional graph Laplacian. It is proved that the consensusability is preserved if the delay-embedded signed Laplacian is positive semi-definite with a simple zero eigenvalue. Moreover, we derived some consensus conditions in terms of the extended effective resistance which measures the overall coupling between two sets of agents. The obtained results provide new insights into the mechanism of delayed consensus from the interplay between the small-delay-induced cooperativeness and large-delay-induced antagonism in the underlying network topology.
Read the full abstract

All authors Yue Song, Mengqi Xue, Jiazuo Hou, Yuxi Lu, Qi Liu

Artificial Intelligence

Platform Adaptation Under Governance Interventions: Actor Best-Response Modeling and an External Public-Case Benchmark

Digital platforms govern by changing rules: rankings, monetization thresholds, moderation standards, verification systems, disclosure requirements, appeal processes, and access policies. These interventions are rarely absorbed passively. Creators, sellers, advertisers, moderators, users, developers, and strategic operators adapt to the new reward surface. This paper develops a platform-adaptation model for evaluating governance interventions as transitions in adaptive multi-actor information systems. The model represents actor best response, strategic gaming opportunity, moderation burden, user-incentive movement, enforcement response, externality formation, and downstream platform stability. We evaluate the model on 72 external public platform-governance cases covering media monetization, ranking systems, verification, delivery platforms, marketplaces, app stores, community platforms, and creator ecosystems. Across 9 methods and 648 method-case evaluations, the full platform-adaptation simulator achieves mean adaptation quality of 0.836338, compared with 0.669731 for a risk-register baseline, 0.589457 for causal-loop analysis, 0.492750 for generic governance critique, 0.369492 for engagement-only optimization, and 0.331965 for baseline policy review. Paired comparisons show a win rate of 1.00 against all tested baselines and channel ablations. The contribution is an information-systems theory and measurement framework showing why platform governance evaluation fails when it treats policy rules as static controls rather than interventions into adaptive actor-response fields.
Read the full abstract

Computation and Language

Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models

We systematically compare word order preferences in decoder-only language models across 192 artificial languages and typologically diverse natural languages. On artificial languages, models exhibit a left-branching preference that aligns with neither natural language universals nor human word order learning biases. On natural languages, monolingual models show no clear base word order bias at small scales, but as data grows, a preference for right-branching subject-verb-object (SVO) languages emerges while SOV falls behind despite being the most frequent order cross-linguistically. This SVO advantage extends to multilingual models and correlates with language resource level and data quality rather than word order. Thus, the same architecture exhibits opposite preferences on artificial and natural languages, establishing that word order biases observed in practice are data-driven. Since highly-resourced languages are overwhelmingly SVO, these biases risk gradually reducing word order diversity, particularly in languages that productively use multiple word orders, with the widespread adoption of LLMs.
Read the full abstract

Operating Systems

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state. However, the system behavior of these workloads—where latency, cost, and bottlenecks arise—remains poorly characterized, leaving serving systems to rely on assumptions built for conventional inference. We present AgentSysBench, a benchmark suite and measurement toolkit with ten representative agentic applications and unified systems-level instrumentation. Across controlled deployments and production traces, we identify six properties that distinguish agentic workloads from conventional LLM serving: (1) execution is heavyweight and stateful, with non-LLM components dominating latency in 5 of 10 applications and sandbox working-set memory peaking at 28 GB per session; (2) applications compose components with heterogeneous resource affinity—GPU-bound inference, memory-bound retrieval, CPU-bound sandboxes—whose task latencies diverge by up to 32x; (3) bottlenecks shift across requests, models, and deployments; (4) production sessions hold state idle for minutes to hours between active steps; (5) a control-plane tax—auxiliary LLM calls and context overhead from tool schemas and observations—crowds out productive compute and context; and (6) production traces from three applications reveal heavy cross-request redundancy in search queries and web fetches, exposing a large caching opportunity. Four design explorations demonstrate that these findings are actionable: task-aware serving reduces latency by 29–40%, communication-aware placement by up to 4.5x, state offloading reduces memory usage by 4.6x, and tool-result caching removes 35.2% of redundant search calls and saves 19.3% of aggregate search latency.
Read the full abstract

All authors Chaokun Chang, Yukun Zhou, Kaihua Fu, Dakai An, Tianyu Feng, Hanfeng Lu, Sheng Yao, Pu Guo, Yinghao Yu, Yizhou Shan, Bo Li, Binhang Yuan, Wei Wang

Machine Learning

Decision-Driven Regularization: A Blended Model for Learning and Optimization

In contextual optimization, the decision-maker seeks optimal decisions to minimize a cost function, that varies based on observed features. This context is common in many business applications ranging from on-demand delivery and retail operations to portfolio optimization and inventory management. In this paper, we study the learning and optimization approach, which first learns how outcomes result from the features, and then selects optimal decisions based on these outcomes. We focus on the integrated learning and optimization literature, and identify that a lack of control for prediction accuracy can lead to overfitting and a loss of decision effectiveness against simple separate learning and optimization models. Instead, we propose a bi-objective formulation that balances prediction accuracy and cost minimization, termed decision-driven regularization. It also addresses ambiguity in the definition of the cost function via a surrogate that depends on a new hyperparameter. We additionally show that alternative perspectives for formulating the problem, namely robust optimization and regret minimization, lead to models that are closely related to our proposed model. As a consequence, our framework generalizes models such as SPO+. Our model is shown to be numerically superior to other benchmarks, such as OLS, Random Forest, XGBoost, SPO+, Perturbation Gradient, and Learning and Rank, in our synthetic studies.
Read the full abstract

All authors Gar Goei Loke, Qinshen Tang, Yangge Xiao, Xun Zhang

Systems and Control

Voltage Stability Assessment with Path-Coupled Load Growth and Corrective Generator Response

Voltage stability margin assessment is essential for the secure operation of renewable-dominated power systems. Conventional continuation-based methods evaluate the margin along predefined load-growth paths with fixed generator partic- ipation, while practical operation allows generators to be redis- patched to alleviate voltage stress and reshape the power-flow trajectory as the system approaches voltage collapse. This paper proposes a path-coupled margin assessment approach that incor- porates corrective generator response into static voltage stability margin assessment. In the proposed approach, the load-growth direction and generator response direction are simultaneously determined at each continuation step, enabling the assessment trajectory to account for generator response while tracing the system toward voltage collapse. The voltage stability margin is then evaluated by the cumulative active load increase along this coupled trajectory. Based on the obtained trajectory and collapse point, a feasible redispatch direction is further derived to improve the margin of the current operating state. The economic cost of voltage stability enhancement is quantified through a marginal stability cost, providing an economic indicator for additional sta- bility support. Case studies on various test systems demonstrate that the proposed framework can effectively capture the impact of corrective generator redispatch on voltage stability assessment, provide effective guidance for margin enhancement, and quantify the cost associated with voltage stability improvement.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Sufficient Dimesion Reduction via Generalized Stein's Lemma

Sufficient dimension reduction (SDR) seeks the minimal subspace of the predictors that captures the full conditional distribution of the response, which is known as the central subspace (CS). When the response is multivariate, the problem becomes considerably more challenging, particularly when the sample size is limited. Existing methods face different limitations:inverse regression approaches rely on strong distributional assumptions and matrix inversion, and their multi-response extensions suffer from severe slice sparsity; forward regression methods depend on computationally intensive iterative smoothing whose cost grows with the response dimension; and deep learning-based approaches demand large amounts of labeled data. To circumvent these shortcomings, we propose an SDR framework based on the generalized Stein's lemma. Our method constructs a cross-moment matrix between the multivariate response and the marginal score function of the predictors, and recovers the CS via its singular value decomposition. The proposed method does not rely on the linearity condition, avoids matrix inversion as well as iterative smoothing, and can leverage unlabeled data when available. We establish convergence guarantees for the proposed estimator under standard regularity conditions. Moreover, we propose a practical rank-selection algorithm to estimate the dimension of the CS. Extensive simulation studies and a real data application demonstrate that the proposed methods consistently outperform existing approaches across a variety of settings, particularly in moderate-dimensional, label-scarce scenarios with high noise levels.
Read the full abstract

Distributed Computing

Collective Communication for Distributed LLM Systems: Planning, Runtime Adaptation, and Computation Coordination

Distributed large language model (LLM) systems increasingly rely on collective communication primitives such as AllReduce (AR), ReduceScatter (RS), AllGather (AG), and AlltoAll (A2A). In modern LLM training and serving clusters, heterogeneous GPU interconnects, multi-NIC networking, mixed parallelism strategies, low-latency inference requests, and high-throughput training pipelines have motivated increasingly diverse ways to plan, execute, and overlap collective communication. This paper presents a tutorial-style, collective-centric taxonomy for collective communication. We organize recent advances into three layers: communication planning, which generates topology-aware collective schedules; communication execution and adaptation, which maps these schedules onto GPU runtimes and hardware in real clusters; and computation-communication coordination, which turns collective optimization into end-to-end training and inference benefits. We further discuss open challenges and future opportunities for collective communication in distributed LLM systems.
Read the full abstract

All authors Xuebin Song, Menghao Zhang, Yuezheng Liu, Jinyi Xia, Shucan Yang, Xiaohe Hu, Chunming Hu, Mingwei Xu

Artificial Intelligence

Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads

Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms parameterized by step count, tool invocations, and context expansion. We evaluate this decomposition empirically within a strictly scoped measurement study: a LangGraph-based CUDA-kernel-synthesis agent (AgentK), a 4-bit quantization family (Q4 K M), a single NVIDIA H100 GPU, and four LLM backbones across 1,920 trajectories. Focusing on peak-memory forecasting behavior, we report two primary observations. First, closed-form analytical models achieve competitive accuracy when provided with two empirical constants: loaded-weight VRAM and a fixed activation-memory overhead. Supplied with live GPU readings and ground-truth trajectory parameters, the closed-form model matches or outperforms the best learned baseline on three of the four backbones (test MAPE 2.2-4.4% vs. 3.4-6.5%, p = 0.76). The exception is the smallest backbone (Phi-4-mini), where minimal VRAM variance (CV 0.3%) causes dynamic modeling to underperform simple regression. Second, compile success strictly bifurcates by backbone capacity (from 5.7% for Phi-4-mini to 62.0% for Qwen2.5-Coder-14B), demonstrating that functional code synthesis remains constrained by intrinsic LLM capabilities rather than available memory. Furthermore, because overall peak-memory variance is remarkably low across all backbones (CV 0.3-9.4%), learned prompt-feature regression offers statistically insignificant improvements over a constant-mean baseline. Consequently, we find no justification for deploying complex predictive VRAM models in highly quantized, weight-dominated regimes. We release the evaluated corpus and anonymized framework to support replication.
Read the full abstract

Computer Vision

Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples

Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transferability poses serious security threats to DNNs in practical applications. Input transformation techniques are widely used to enhance adversarial transferability by increasing the diversity of input images. However, existing methods primarily rely on local operations with limited degrees of freedom (DOF), such as block-wise shuffling and resizing, overlooking global perspective transformations that naturally arise from viewpoint changes. In this work, we propose a Perspective-Invariant Attack (PIA), which introduces a multi-DOF vertex sampling strategy that systematically covers the perspective transformation hierarchy from 2-DOF translation to 8-DOF projective mapping. By generating geometrically diverse input variations, PIA effectively reduces overfitting of adversarial perturbations to the surrogate model, thereby improving adversarial transferability. We further propose PIA-Mix, a generic extension that maintains a complementary transformation pool and efficiently combines our perspective transformation with auxiliary methods for improved transferability. Extensive experiments involving various DNN architectures, advanced defense mechanisms, and multimodal large language models (LLMs) demonstrate that PIA and PIA-Mix outperform state-of-the-art transfer-based attacks.
Read the full abstract

Computer Vision

Fast Test-Time Refinement for Robust Learned Image Compression

Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings. However, the high representational capacity endowed by deep neural networks (DNNs) comes at the expense of increased adversarial vulnerability. This hinders their adoption as trusted standardized codecs. Recent work has sketched test-time refinement (TTR) as a defense in gray-box scenarios, despite its original purpose of improving benign RD performance. Unfortunately, extensive iterations of TTR incur prohibitive overhead, while the robustness mechanism lacks theoretical understanding. Moreover, TTR has not been evaluated in white-box settings or against attacks beyond $\ell_2$-bounded rate and untargeted distortion objectives. To bridge these gaps, we present a systematic study. Our study reveals an Asymmetric Adversarial Trajectory (AAT) property in LIC systems: transitioning from adversarial to benign regions is significantly easier than the reverse process, where adversarial examples can often be roughly recovered within only 1-2 steps. We provide a two-dimensional Tube Model to explain this phenomenon. Based on AAT, we propose a Fast Test-Time Refinement (FTTR) framework for practical and robust LIC systems. We establish that the robustness arises from the contraction of adversarial regions induced by the Input-as-Label property of LIC systems, rather than from obfuscated gradients. Extensive evaluations with diverse strong adaptive attacks across multiple LIC systems demonstrate the promise of the proposed FTTR framework. The code is available at https://github.com/chinaliangjiaming/FTTR.git.
Read the full abstract

Machine Learning

Probability-Preserving Transformer for the Time-Dependent Schrödinger Equation

Solving the time-dependent Schrödinger equation (TDSE) via traditional numerical methods is computationally intensive. Transformer models offer a compelling alternative, but standard implementations rely on soft constraints that cannot rigorously guarantee probability conservation. Here, we introduce a Transformer architecture that enforces TDSE probability conservation as a hard constraint. The design intrinsically ensures unitarity across temporal evolution without requiring repeated retraining. Our empirical findings show that this hard-constraint approach is not only physically exact but also computationally superior to conventional soft-constraint methods.
Read the full abstract