Computation and Language
Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations
Yeeun Chae, Yewon Choi, Seunghyun Lee et al. (+1 more)
Large
language models (LLMs) are increasingly used as synthetic survey respondents to estimate population response distributions. In cross-cultural survey simulation, evaluations should assess not only distributional fidelity within countries but also whether differences across countries are preserved. However, existing distance-based metrics such as Jensen–Shannon divergence (JSD) do not directly capture such cross-country differences. To address this limitation, we introduce Cultural Divergence Preservation (CDP), a reference-light diagnostic based on a one-time human calibration. CDP identifies reduced cross-country divergence as cultural flattening and increased divergence as cultural caricature. To evaluate CDP, we conduct experiments across four LLM backbones, three persona-based prompting methods, and two survey domains, the World Values Survey (WVS) and the Big Five Personality Test. The results reveal a systematic discrepancy between conventional fidelity metrics and CDP. Controlled experiments show that CDP changes monotonically as cross-country divergence is attenuated or amplified, while the corresponding changes in JSD remain relatively small. In our audit of real LLM generations, DeepPersona-Inspired prompting is frequently favored by conventional fidelity metrics but exhibits the strongest flattening in every model–domain block. CDP thus complements fidelity metrics by directly quantifying the attenuation or amplification of cross-country divergence.
Read the full abstract ▾
All authors Yeeun Chae, Yewon Choi, Seunghyun Lee, IL Im
Artificial Intelligence
Who Holds the Pen? Let Specifications, Not Agents, Sign Off
Haiqing Li, Xin Ma, Yinhao Wu et al. (+7 more)
Large
language model
agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they operate under external specifications such as task instructions, guidelines, output schemas, and reusable skills, these specifications typically remain context for the same model that acts and declares completion, leaving no independent specification authority boundary. We identify two resulting gaps. The understanding–execution gap arises when a requirement is understood but not satisfied in execution; the state–authority gap arises when an
agent's interpretation or completion claim does not establish the required state. On SkillsBench, using only
agent-visible
prompts, workspace information, and injected skill specifications, we extract 509 source-grounded task directions. Across seven models, only 79.6%–86.4% are satisfied, while completion-claim rates exceed official evaluator pass rates by 28.7–37.9 percentage points. We therefore separate
agent proposals from authoritative state.
Agents may plan, act, and request completion, but only admissible evidence from qualified providers may establish specification-governed state. SpecHarness operationalizes this principle by compiling visible specifications into source-linked obligations and governing execution and finalization through versioned obligation state. Verifiable requirements are mediated or validated at runtime, while ambiguous or subjective requirements remain advisory. Experiments on guideline-following and artifact-generation tasks show that specifications can serve not merely as behavioral guidance, but as authority over compliant execution and completion.
Read the full abstract ▾
All authors Haiqing Li, Xin Ma, Yinhao Wu, Wenliang Zhong, Feng Jiang, Thao M. Dang, Xiao Hu, Hehuan Ma, Yuzhi Guo, Junzhou Huang
Networking
Packet-Level In-Network Semantic Adaptation for Unstable Mobile Emergency Networks
Zhiyuan Ren, Tao Zhang and Wenchi Cheng
Mobile emergency networks can experience independently changing intermediate wireless links on timescales shorter than endpoint feedback can track. When an egress changes after packet emission, feedback affects only later source data, while the on-path node observes the current condition with the affected packet still mutable. This paper presents DINA, a packet-level in-network semantic adaptation method. An image is divided into self-describing spatial packets carrying coordinates, a current representation identifier, and payload. At each eligible node, an offline-trained frozen selector scores compatible operators, immediately transforms the packet, and forwards it without image reconstruction or cross-packet adaptation state. Later nodes can retain or further compact the packet through the same typed compatibility contract. The receiver places available packets by coordinate, fills missing regions with black, and runs a fixed machine task. We realize DINA in a 24-node
UAV environment using XDP and AF_XDP. In the primary forest-fire trace, DINA raises deadline tile coverage from 40.4% to 72.6% and classification accuracy from 77.5% to 95.0% relative to forwarding. In an independently trained RescueNet
segmentation case, it raises coverage from 65.6% to 91.7% and foreground mIoU from 0.486 to 0.541. Sufficient- and extreme-capacity profiles expose a no-gain boundary and a common task-failure boundary, respectively.
Read the full abstract ▾
Cryptography and Security · Cross-listed from quant-ph
Computational Cryptography from Pseudoentanglement
Ilia Ryzov, Manuel Goulão, Faedi Loulidi et al. (+1 more)
The advent of pseudoentanglement and computational
entanglement theory bootstrapped a wave of research at the intersection of computer science and information theory. In parallel, computational cryptography has undergone substantial development, prompted by the introduction of pseudorandom states and followed by the establishment of a baseline for the computational hardness required for
quantum cryptography, from which EFI pairs emerge as a central primitive. We study the connection between pseudoentanglement and computational cryptography through EFI pairs. Our goal is to enable the use of resources arising from computational
entanglement theory in the field of cryptography. For this, we establish the relation between operational instances of pseudoentanglement and the hierarchy of minimal assumptions for computational cryptography. We show that the existence of pseudoentanglement under two different operational definitions, with efficient state generation, is a sufficient condition for the existence of EFI pairs. Combined with a previously established result that the converse also holds under the second definition, this allows us to also demonstrate their equivalence. This places pseudoentanglement alongside other minimal assumptions in cryptography, not only offering an alternative perspective on this fundamental problem, but also building a bridge that allows insights from either area to inform the other. While proving these
theorems, we introduce and demonstrate technical lemmas in
quantum information and computational
entanglement theory, relating the computational
entanglement measures to the distance between states, establishing distinguishing conditions for mixtures of two families given pairwise distances between their states, and demonstrating the first continuity relation for a computational
entanglement measure.
Read the full abstract ▾
All authors Ilia Ryzov, Manuel Goulão, Faedi Loulidi, David Elkouss
Information Theory
Non-Uniform Activation Aided Distributed Generalized Spatial Modulation for DMIMO Systems
Haojin Li, Chen Sun, Rang Su et al. (+3 more)
This letter investigates a non-uniform activation aided distributed generalized spatial modulation (DGSM) scheme in a downlink distributed multiple-input multiple-output (DMIMO) system formed by geographically separated transmission reception points (TRPs). Unlike conventional uniform-activation DGSM, the proposed scheme assigns adaptive activation probabilities to different TRP subsets, thereby jointly exploiting the data-domain transmission capability and the index-domain information carried by cooperative subset selection. We derive a mutual-information upper bound under non-uniform activation and formulate a joint activation-probability and power allocation problem subject to a long-term average power constraint. To solve this problem, we develop a semi-closed-form joint probability and power optimization (SC-JPPO)
algorithm, where the optimal activation probabilities are shown to follow a Softmax function of the effective utilities. Simulation results demonstrate that the proposed scheme improves spectral efficiency under the same activation scale and power budget compared with existing
benchmarks.
Read the full abstract ▾
All authors Haojin Li, Chen Sun, Rang Su, Zhaojian Liu, Wenqi Zhang, Haijun Zhang
Robotics
High-Voltage Optocoupler Amplifier for Electrostatic Actuators
George C. Jurgiel, Alex S. Miller and Jeffrey H. Lang
Many electrostatic actuators require multi-kilovolt drive voltages at sub-milliamp currents, a task poorly suited for conventional switching devices. As an alternative, we demonstrate a high-voltage amplifier using optocouplers as active elements. The amplifier produces a 20-kV peak-to-peak output with up to 500 Hz bandwidth while maintaining a minimal component count. By using optocouplers as linear devices in feedback, lower harmonic distortion and higher bandwidth are achieved than offered by equivalent PWM amplifiers. This design improves the viability of electrostatic actuators by providing a simpler method to achieve useful drive waveforms.
Read the full abstract ▾
Computation and Language
MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression
Youpeng Zhao, Tian Tan, Liqian Peng et al. (+2 more)
Many-shot in-context learning (ICL) enables large
language models (LLMs) to adapt to complex tasks by conditioning on thousands of demonstration examples, but this paradigm shifts the inference efficiency bottleneck to the key-value (KV) cache
memory. Due to the linear scaling behavior of the KV cache, storing these intermediate tensors has become a paramount challenge for both online serving and on-device deployment. To address this issue, we propose a novel compression framework, termed MILO, that exploits the low-rank redundancy inherent in many-shot contexts. Specifically, MILO features a block-wise low-rank compression strategy that compresses the KV cache at the block granularity, where each block contains multiple many-shot examples. Furthermore, to handle the heterogeneous context density across different blocks, MILO dynamically allocates rank budgets based on the information
entropy, preserving the fidelity of critical blocks while aggressively compressing redundant ones. Experimental results on Qwen2.5 models demonstrate that our method achieves up to 50% reduction in KV cache
memory and 1.8x throughput improvement, with negligible performance degradation on classification and
reasoning benchmarks, significantly outperforming prior baselines.
Read the full abstract ▾
All authors Youpeng Zhao, Tian Tan, Liqian Peng, Jun Wang, Alec Go
Artificial Intelligence · Cross-listed from eess.SP
Structured Pose-Conditioned Flow Matching for Generative 5G CSI Augmentation
Haojin Li, Anbang Zhang, Wai Ho Mow et al. (+3 more)
With the growing demand for
privacy-preserving and occlusion-resilient human pose recognition (HPR), 5G channel state information (CSI) offers a promising contactless sensing modality by integrating communication and sensing capabilities. However, collecting large-scale synchronized CSI-pose pairs remains costly in practical 5G systems. To address this limitation, we propose StructFlow-HPR, a structured pose-conditioned flow matching framework for generative CSI augmentation. StructFlow-HPR learns a continuous latent transport process from Gaussian noise to real CSI representations under pose guidance, while preserving the receiver-frequency
topology of CSI through a reconstruction-preserving autoencoder. A pose-conditioned
Transformer is further designed to model the latent velocity field and generate pose-aligned CSI samples via ordinary differential equation sampling. Experiments on real-world 5G sensing data show that StructFlow-HPR can produce realistic CSI-pose pairs and improve downstream HPR performance under limited-data conditions.
Read the full abstract ▾
All authors Haojin Li, Anbang Zhang, Wai Ho Mow, Chenyuan Feng, Chen Sun, Haijun Zhang
Robotics
MorphIK: Morphology-Conditioned Neural Inverse Kinematics for Unknown Robots
Lennart Clasmeier, Jan Gerrit Habekost, Cornelius Weber et al. (+1 more)
Neural models can learn to generate various solutions to the inverse kinematics problem from data, but are usually limited to a single
robot. We present MorphIK, a flow-matching model that solves inverse kinematics for revolute-joint-based kinematic chains it has never seen during training. The model uses a
transformer architecture to encode the
robot's morphology along with the target pose. This encoding then conditions a flow-matching head that generates poses from noise. Trained on purely synthetic data from procedurally generated
robots, the model reaches a precision of about 5 cm on unseen real-world
robots with 6 to 9 Degrees of Freedom. For higher precision, the model serves as an excellent Prior for further optimization
algorithms, reducing error to less than 1 cm after a single step of Damped Least Squares optimization and to sub-1 mm error after 3 steps in most cases. Building on flow matching's generative capabilities to produce highly diverse outputs, our model can efficiently sample the
robot's null space, providing a wide variety of configurations for the same pose. Thus, overall, MorphIK allows learning and generalizing neural inverse kinematics for a multitude of known and unknown
robots.
Read the full abstract ▾
All authors Lennart Clasmeier, Jan Gerrit Habekost, Cornelius Weber, Stefan Wermter
Machine Learning
Spatio-temporally complementary feature propagation on graphs for longitudinal AADT estimation
Linghang Sun, Qishen Zhou, Michail A. Makridis et al. (+1 more)
The estimation of Annual Average Daily Traffic (AADT) is vital for transportation planning and infrastructure maintenance, yet obtaining accurate values for an entire urban network across multiple years remains challenging due to the high cost and spatial sparsity of physical sensors. This research proposes a novel spatio-temporally complementary feature propagation framework that leverages the strengths of two distinct data sources: spatially sparse but temporally dense loop detector data, and a spatially complete but temporally sparse macroscopic transportation model. The methodology highlights a feature propagation
algorithm on directed graphs, formulated as a Poisson energy minimization considering residues. The standard binary adjacency
matrix is replaced with flow ratio
matrices to capture real-world vehicle turn ratios at intersections. Validated in the city of Zurich, the
algorithm demonstrates high computational efficiency, achieving convergence within minutes. Results indicate that the framework effectively reconciles theoretical models with empirical ground truths, yielding a normalized mean absolute error below $10\%$. This scalable approach provides a feasible solution for spatio-temporal network-wide AADT estimation through combining real-world limited sensor coverage and traffic models.
Read the full abstract ▾
All authors Linghang Sun, Qishen Zhou, Michail A. Makridis, Anastasios Kouvelas
Machine Learning · Cross-listed from hep-lat
Accurate Sampling from Diffusion Models
Dénes Sexty
A new proposal called DM-SMC (
Diffusion Model - Sequential Monte Carlo) is investigated, which samples ensembles defined in terms of an action, using
diffusion models trained on samples from the ensemble. The SMC setup allows for accurate sampling in spite of an approximate
diffusion model and the finite stepsize used in the numerical solution of the
stochastic process. Improved update strategies are also investigated. Results are presented for a $Z_2$ symmetric scalar field theory in 2 dimensions near its 2nd order phase transition.
Read the full abstract ▾
Human-Computer Interaction
Working with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work
Rida Qadri, Remi Denton, Michael Madaio et al. (+13 more)
Enterprise AI is transitioning from single-user, reactive tools toward proactive, multi-user 'teammates,' but our empirical understanding of this transition is limited. In this paper, we present an in-situ qualitative study of a persistent, proactive AI
agent 'teammate' deployed across multiple teams in a large technology company. Our findings reveal the boundaries of the human-
agent workplace are actively in flux, triggering breakdowns and negotiations across: 1) tacit rules of collaborative human workflows, 2) the relational boundaries of this new non-human actor, and 3) the redistribution of trust and human agency. We use these early micro-negotiations as signals to chart a new research, design, and organizational agenda that intentionally preserves human agency in a workplace shared with non-human organizational actors.
Read the full abstract ▾
All authors Rida Qadri, Remi Denton, Michael Madaio, Mahima Pushkarna, Leslie Lai, Sherry Moore, Michelle Chen Huebscher, Andrew Butcher, Ritom Sen, Hsiao-Yu Tung, Shaan Mathur, Yimeng Liu, Shibl Mourad, Noah Fiedel, Edward Grefenstette, Michael Terry
Artificial Intelligence
Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
Tingyu Qu, Weigao Sun, Yuecheng Liu et al. (+23 more)
The rapid progression of large
language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift raises a compelling question: can AI be both the object of development and an active participant in building next-generation AI systems? We explore this question by building Qwen-Planner-
Agent within a closed-loop AI-for-AI framework for scalable development and iterative improvement. Mobile planning offers a demanding test of this approach: complex, long-horizon tasks challenge
agent reliability, while costly real-device interaction limits development scalability. The framework connects data production, model training, and deployment through a shared action-feedback-verification contract. (i) AI for Data builds a human-gated agentic data flywheel in which specialized
agents construct tasks, collect interaction trajectories, curate and balance training data, and use training feedback to guide subsequent data generation. (ii) AI for Training combines a supervised planning cold start with hybrid-environment online agentic reinforcement learning, where we introduce Competence-Aware Reward-and-Advantage Engineering (CARE) to reduce
reasoning and tool-use costs while preserving task performance. (iii) AI drives model–harness co-
evolution through an execution-evidence-driven loop that orchestrates
memory, skills, and tools at runtime and feeds structured action feedback and preserved failure traces back into coordinated model and harness adaptation. Qwen-Planner-
Agent achieves the best overall performance among all evaluated models and systems on MobilePA-Bench, improving over its base model across tool use,
memory, skills, and sub-
agent coordination. Further evaluations of our model show improvements across non-mobile agentic
benchmarks while largely preserving general capabilities.
Read the full abstract ▾
All authors Tingyu Qu, Weigao Sun, Yuecheng Liu, Yucheng Zhao, Yi Zhu, Yifeng Ding, Qiyi Wang, Sihan Cao, Pengkun Jiao, Hanlei Xie, Xiongwei Wu, Qichao Wang, Haodong Zhang, Jiajun Liu, Yuhao Wang, Yuqing Xie, Junpeng Zhao, Long Chen, Ming Ma, Sihan Yang, Ziwang Zhao, Yanhao Jia, Liangquan Gong, Feida Zhu, Yiran Zhong, Steven Hoi
Sound
EditVoice: Variable-Length Non-Autoregressive Zero-Shot TTS and Speech Editing with Edit Flows
Hongyao Deng, Wenhao Guan, Xuetao Lin et al. (+4 more)
Recent non-autoregressive (NAR) zero-shot text-to-
speech (TTS) models generate in parallel but typically require the target sequence length to be specified before generation. We introduce EditVoice, to our knowledge the first variable-length NAR zero-shot TTS model, which uses Edit Flows to jointly update
speech content and sequence length through insertions, deletions, and substitutions. EditVoice adopts
speech-infilling training, which unifies zero-shot TTS and text-based
speech editing and allows both prefix and suffix
speech prompt placements at inference. We introduce Complementary
Prompt Sampling (CPS) to leverage the complementary Edit Flow predictions induced by the two
prompt placements. We further find that EditVoice can edit source and model-generated
speech beyond its training sources. We use this generalization for end-to-end editing and training-free post-generation refinement. With the Edit Flow model trained on 10K h of GigaSpeech, EditVoice demonstrates competitive zero-shot TTS performance on Seed-TTS Eval EN and LibriSpeech-PC and
speech editing performance on RealEdit.
Read the full abstract ▾
All authors Hongyao Deng, Wenhao Guan, Xuetao Lin, Peijie Chen, Weijie Wu, Lin Li, Qingyang Hong
Machine Learning · Cross-listed from math.OC
Cost-Sensitive Online Window Size Selection for Portfolio Management
Yi-Chen Liu and Chung-Han Hsieh
This paper investigates cost-sensitive online window size selection for portfolio management under changing
market conditions. Specifically, we propose a two-level framework that constructs portfolios using candidate window sizes and dynamically aggregates them through online learning. By treating candidate window sizes as “experts,” we dynamically update their aggregation weights using turnover-inclusive losses. Moreover, we derive finite-horizon cost-sensitive tracking-regret bounds that account for turnover of the aggregated portfolio, with static regret as a special case. Under bounded losses and cost rates, suitably tuned Fixed Share achieves asymptotically no tracking regret for sublinear switching budgets, with Hedge covering the static case.
Read the full abstract ▾
Computational Complexity
A New Gap Sequence for Shellsort: RL-Driven Algorithm Discovery Beyond $N^{4/3}$
Bo Liu
Choosing Shellsort gaps is a well-known open problem. For over sixty years, successful sequences have relied on human-designed formulas, numerical searches, or number-theoretic constructions. Although stronger general bounds exist for dense or mainly theoretical families, the worst-case upper bound for a short, sparse, and practically competitive construction has not advanced beyond $N^{4/3}$ for decades. We ask whether the sequence itself can instead be learned from execution. We present an RL-driven, self-supervised system that searches over executable gap generators. Every proposal is valid by construction, and executed candidates return exact comparison and move counts; no classical sequence is used as a target. Across five independent searches, the system discovers a common rational-
geometric family. A second self-supervised stage tunes only a finite prefix, producing the practical sequence $1,3,8,20,47,116,300,585,1416,3303,\ldots$. Once frozen, it obtains the lowest equal-task average operation count among seven classical baselines on 25 large tasks with $10^7<N\leq 10^8$. We complete the learned tail without changing its practical behavior: only beyond $10^{1000}$, a zero-density set of unit companions $h_s+1$ removes the remaining congruence barriers. The resulting sparse sequence has matching
polynomial upper and lower exponents, up to polylogarithmic factors: $\Omega(N^{1.024296451657\ldots}) \leq T(N) \leq O(N^{1.024296451657\ldots}\operatorname{polylog} N)$. The lower bound follows from Zang's recent
theorem for rational-
geometric sequences; our contribution is the matching upper bound. Thus one exact sequence connects self-supervised discovery, large-scale practical performance, and a substantial step below the classical $N^{4/3}$ bound for sparse practical Shellsort sequences.
Read the full abstract ▾
Networking
Energy-Aware Two-Sided Learning for Dynamic Matching Games in Mobile Crowdsensing
Sumedh J. Dongare, Anja Klein and Andrea Ortiz
Mobile crowdsensing (MCS) is a promising enabler of Sensing-as-a-Service (SaaS) for next generation networks (NGNs), where sensing, communication, and computing are jointly considered as on-demand services. In MCS, mobile units (MUs) collect and deliver sensing data to data requesters (DRs) via a mobile crowdsensing platform (MCSP) in exchange for monetary incentives. After sensing tasks are announced, MUs strategically select tasks to maximize their long-term utility while accounting for energy and time costs, whereas the MCSP assigns tasks to maximize its own service revenue and data quality. A fundamental challenge arises from the lack of prior knowledge of MUs' sensing qualities and task efforts, as well as the energy limitations of battery-powered devices, which directly impacts service availability and reliability in SaaS for NGNs. To address these challenges, we formulate the interaction between MUs and the MCSP as a dynamic two-sided matching game under incomplete information, explicitly incorporating energy constraints. We propose Energy-aware Two-Sided Learning (ETSL), a fully decentralized and lightweight learning framework in which MUs locally learn task proposal strategies, while the MCSP learns the data quality of participating MUs to devise task assignment strategy. ETSL jointly enables MUs' energy-aware task proposals and MCSP's adaptive task assignment, considering their individual preferences to maximize their net revenues. Simulation results demonstrate that ETSL significantly improves MU and MCSP profits and overall energy efficiency, highlighting its effectiveness as a scalable and sustainable SaaS solution for NGN.
Read the full abstract ▾
Machine Learning
From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation
Yu Qin, Andrew Glaws, Aadil Latif et al. (+1 more)
Generative modeling approaches often focus on recovering broad statistical characteristics from the training data. In the context of graph generation, this may refer to degree distributions, clustering coefficients, or spectral properties. However, generating usable distribution feeders when detailed feeder models are unavailable requires more than matching generic graph statistics: the sampled
topology must also obey electrical compatibility and radiality rules. We therefore formulate feeder synthesis as a constraint-guided graph generation problem and propose the Power-Grid-constrained Discrete Denoising
Diffusion model, PG-DiGress, which learns categorical node and edge patterns from feeder data, while respecting domain-specific rules. Specifically, it injects feeder constraints into the reverse
diffusion process through soft masks that suppress incompatible edge classes during denoising, followed by a final projection step that rebuilds a connected, rule-compliant feeder graph. We evaluate PG-DiGress using graph-distribution similarity, feeder-rule satisfaction, structural validity, and downstream model construction. Compared with the unconstrained baseline, PG-DiGress increases the strict feeder pass rate from 13.7% to 96.8%. We also successfully convert the generated graphs into executable feeder models for downstream analysis.
Read the full abstract ▾
All authors Yu Qin, Andrew Glaws, Aadil Latif, Ryan King
Artificial Intelligence
Ontology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholders
Stefan Bischof, Juliana Kainz and Danilo Valerio
Neurosymbolic research typically assumes a pre-existing symbolic specification, leaving the upstream challenge of acquiring and formalizing requirements and constraints largely unaddressed. We present an architecture that fills this gap by using an OWL configuration ontology to mediate between neural constraint sources and downstream consumers. In this framework, LLM assistants elicit soft stakeholder preferences, while hardware specifications define hard physical and engineering limits. The ontology unifies these heterogeneous inputs, leverages description logic to identify unsatisfiability, and generates symbolic explanations that enable LLMs to interactively renegotiate terms with users. Any remaining conflicts are resolved downstream via priority-based relaxation. We illustrate our approach on a microgrid use case from the FLEXI project and argue its generalizability to multi-stakeholder domains where constraint acquisition is distributed across human and automated sources of unequal authority.
Read the full abstract ▾
Artificial Intelligence
When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression
Mingxuan Wang, Fei Luo, Bo Wang et al. (+6 more)
Long horizon
language model
agents continually accumulate
reasoning history, increasing context length and inference cost even after earlier decisions have been executed and observed. Unlike static Chain of Thought compression, removing historical
reasoning can change future actions and the resulting interaction trajectory. We study when such
reasoning can be safely forgotten. We propose Interaction Aware Compression for Long Horizon
Reasoning (ICLR), a training free online method that ranks
reasoning blocks using frozen proxy
entropy while preserving actions, tool calls, and observations. On 260 WorkBuddyBench tasks, ICLR improves average reward from 0.699 to 0.718, while reducing input, output, and cache read
tokens by 25.5%, 14.4%, and 33.3%, respectively. Ablations reveal trajectory amplification, where local
reasoning deletion produces nonlinear changes in total computation by altering subsequent interaction. Representation probing, activation patching, and controlled trajectory analyses further suggest that historical
reasoning becomes more replaceable once task relevant derived state has been reliably externalized into code, files, tool outputs, or environmental feedback. These results characterize
agent reasoning as dynamic working state rather than permanent interaction history.
Read the full abstract ▾
All authors Mingxuan Wang, Fei Luo, Bo Wang, Guorun Yao, Yinglong Guo, Chao Ning, Hongyue Chen, Yanbiao Ma, Jungong Han
Artificial Intelligence
A Risk-Adaptive and Evidence-Constrained Framework for Generative AI Feedback in Programming Education
Shihao Wang
Generative artificial intelligence can turn learning analytics into personalized support, but feedback systems must decide when to intervene, which evidence to use, and how much assistance to provide. We developed a risk-adaptive, evidence-constrained framework for introductory programming using 2993 failed-submission states from 215 students. Student-disjoint models predicted persistent failure and related outcomes; four matched feedback conditions were generated for 136 cases; and calibrated risk informed capacity-limited intervention policies. The validation-selected logistic regression model achieved a test precision-recall area under the curve of 0.550 and a receiver operating characteristic area under the curve of 0.681. Broader student histories improved prediction of unmodified resubmission. After standardized repair and evidence gating, 519 of 544 newly generated messages contained all required components. A fixed-threshold sequential policy selected 17.8% of eligible test states and captured 25.2% of observed persistent failures. These findings support an evidence-gated progressive assistance strategy: calibrated risk guides intervention timing, recorded evidence constrains feedback content, and assistance progresses from self-checks to localized hints when warranted. The framework connects prediction, decision-making, and grounded generation while keeping their evaluation outcomes distinct.
Read the full abstract ▾
Software Engineering
Formal Model Construction Guided by Model-Based Proof Sketches
Hongshu Wang, Xinyue Zuo, Yufan Cai et al. (+3 more)
Formal modeling provides strong guarantees about system correctness, but developing and repairing formal models remains labor-intensive and requires substantial expertise in logic and formal
reasoning. Recent LLM-based autoformalization
agents seek to reduce this burden by generating candidate formal models and revising them using feedback from formal tools. However, the existing approaches follow a generate-and-repair paradigm, in which repairs are driven by verification failures of the generated model and therefore depend heavily on both the granularity of the feedback and the LLM's repair capability. As a consequence, a repair targeting one level of verification may invalidate properties at another level, which requires
reasoning over the complete set of event guards. To address these limitations, we propose Proof-Sketch-Guided Formal Model Synthesis (ProGS), an autoformalization method centered on model-based proof sketches. A model-based proof sketch represents the proof structure of the target formal system as a tree. Internal nodes capture case splits and inductive
reasoning steps, while leaf nodes correspond to concrete state-transition events that realize individual subgoals. ProGS uses LLMs to generate and repair these sketches, with verification failures mapped back to specific nodes and subtrees to provide structured guidance for iterative repair. Our evaluation on a
benchmark of 27 formal systems shows that ProGS improves over state-of-the-art agentic formal modeling approaches in syntactic validity, deductive verifiability, and behavioral correctness, demonstrating the benefit of organizing formal model construction around hierarchical proof sketches.
Read the full abstract ▾
All authors Hongshu Wang, Xinyue Zuo, Yufan Cai, Neeraj Kumar Singh, Yamine Ait Ameur, Jin Song Dong
Game Theory
Costly Voting in the Hotelling-Downs Model
Guy Wolf and Reshef Meir
We study a partial-participation variation of the Hotelling-Downs model. Voters each have a cost to vote, and only vote when the comparative gain from their preferred candidate exceeds the cost. Under this model the median voter
theorem breaks, and we study the extent of polarization under
equilibria in different voters and cost distributions. We find that the main predictor of polarization is the reverse-hazard-rate of the cost distribution, indicating that the driver of polarization under our model is the willingness of voters to respond to changes in positions of candidates. We then extend the model by adding parameters governing alienation and candidate competitiveness, showing that our results are robust even when taking into account other realistic factors.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.AS
Does per-frame early exit pay? A compute-matched study of dynamic depth for on-device speech enhancement
Clément Laroche and Riccardo Miccini
Deep learning-based
speech enhancement is increasingly deployed on-device in hearing aids, headsets, and earbuds. Most of these devices, however, can only accelerate static int8 graphs, so a depth-varying network must be implemented as several graphs, orchestrated by a policy. In this paper, we supervise every intermediate depth of one causal model, then we fine-tune its output heads to guarantee that deeper outputs are never worse than shallower ones. Using this training protocol, we can derive a family of static models that are more Pareto-efficient than their equivalently-sized counterparts trained from scratch on the same budget. Specifically, we achieve up to 0.11 higher PESQ for equivalent compute, and match the best PESQ at 30% less compute. We then quantize the models to int8 and measure the latency-quality frontier on an STM32N6 microcontroller. On VoiceBank-DEMAND, the dynamic enhancer lies on the same frontier as the static models, rather than trading quality for dynamic execution. Running the policy on the companion Cortex-M55 takes only 26 $\mu$s per frame, while splitting the enhancer into separate NPU graphs adds 2.2% latency overhead. The cost of dynamic execution is therefore small.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.AS
Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement
Clément Laroche and Rasmus Kongsgaard Olsson
Deploying real-time
speech enhancement on resource-constrained devices requires meeting strict latency,
memory, and energy constraints. Microcontroller NPUs can accelerate neural inference under these constraints, but only through a restricted set of operators in static, integer-quantized graphs. Recent
speech-enhancement networks have reduced parameter counts and MACs to levels nominally suitable for microcontrollers, but their operators and execution patterns often remain incompatible with restricted NPUs. We address this gap by redesigning LiSenNet, a 37k parameter sub-band dual-path model, for the STM32N6570-DK Neural-ART accelerator. We replace its recurrent bottleneck with convolutional frequency and temporal mixers, reformulate unsupported operations as static int8-compatible primitives, and use bounded decoder activations to preserve quality after quantization. On VoiceBank-DEMAND, the final NPU-compatible model matches or exceeds the recurrent LiSenNet baseline, reaching PESQ 3.08 versus 3.01 in FP32 and 3.01 versus 2.93 in int8. Deployed on a microcontroller, it processes each 16 ms input hop in 4.83 ms, corresponding to a real-time factor of 0.30. Stateless receptive-field recomputation is an order of magnitude slower at the same frame rate despite higher accelerator utilization. These results show that parameter count and operator compatibility, quantization range, and persistent streaming state must be co-designed to achieve efficient real-time
speech enhancement on restricted NPUs.
Read the full abstract ▾
Computational Geometry
A Collapse Process for Farthest Voronoi Diagrams of Lines in Three Dimensions
Evanthia Papadopoulou, Martin Suderland and Zeyu Wang
We study a collapse process to construct the farthest Voronoi diagram of lines in three dimensions, given a spherical map of the diagram's unbounded features. The collapse process sweeps through the diagram in order of decreasing distance from the farthest lines. It follows the shrinking map, a
cell complex on a topological sphere that encodes the locus of points with a fixed farthest distance. We show that, in three dimensions, the collapse process has exactly four non-terminal local event types that change the structure of the shrinking map: deletion, swap, local minimum, and local maximum events; plus one terminal event. This list is complete. We give intrinsic three-dimensional
geometric descriptions of the four non-terminal events. First, we classify the two vertex-related events, deletion and swap events, by the spherical convex hull of the four tangent points from a vertex to its four defining lines. Then, we analyze the events related to the local extrema of the distance function along the trisector of three lines. We show that the distance function along a trisector has at most $4$ local maxima and $8$ local minima, and that both bounds are tight. The extrema can be found via a
polynomial of degree $12$. As a byproduct, this gives a direct method for finding the smallest sphere tangent to three given lines. At each local extremum, the tangent sphere touches the three lines at points lying on a great circle. The collapse process and the completeness of the event list also apply, under similar general position assumptions, to the farthest Voronoi diagram of convex sites under strictly convex distance functions.
Read the full abstract ▾
Computer Vision
Efficient Continuous DEM Reconstruction under Limited Target-Resolution Supervision
Zekai Shi, Meng Zhang, Haokun Zhang et al. (+1 more)
High-resolution digital elevation models (DEMs) support Earth observation applications, but paired training references are often available only at coarser output resolutions. Reconstructing finer terrain grids therefore requires both effective transfer beyond the supervised scale and control of dense-query computation. To address this problem, SCOPE learns a continuous terrain representation from coarser-resolution pairs. It predicts a latent coefficient field on the low-resolution grid and reuses local
Fourier residual functions through basis evaluation and geometry-guided ensemble fusion. This separates high-dimensional coefficient prediction from output-grid construction. Experiments on geographically distributed land–ocean samples assess supervised reconstruction, unseen-scale inference, cross-domain generalization, and theoretical computation. SCOPE leads the compared methods across six metrics in the main supervised-scale evaluation. At an unseen factor three times the training factor, land reconstruction reduces RMSE and MAE by approximately 12% relative to bicubic interpolation, with errors close to target-scale fine-tuning. Ninefold output density increases counted multiply–accumulate operations by only about 2%. Frozen-model validation on held-out external marine regions reduces RMSE relative to the DEM-specific implicit baseline EBCF-CDEM by approximately 19% under self-downsampling and 2% with cross-product inputs, while also yielding lower RMSE than LIIF-MS in both settings. These results demonstrate the value of reusable coefficient fields for accurate reconstruction beyond the supervised resolution with low incremental arithmetic cost.
Read the full abstract ▾
All authors Zekai Shi, Meng Zhang, Haokun Zhang, Bo Zhang
Computer Vision
Modelling dynamic systems transfer functions from events in computational neuromorphic imaging
Nimrod Kruger and Gregory Cohen
Event
Vision Sensing (EVS) report threshold crossings of log-irradiance, so a static optical system imaging a static scene produces no output at all. The classical procedure for measuring a Point Spread Function (PSF), illuminating the system with a constant point source, therefore has no event-based equivalent: the probe must carry a temporal profile, and that profile becomes part of the measurement. A growing body of Computational Neuromorphic Imaging (CNI) work already exploits this, pairing engineered or modulated optics with event sensing, but each system adopts a particular excitation together with a particular reading of the event stream without the correspondence between the two being stated. We examine that correspondence directly within a analytical framework of an Linear Shift-Invariant (LSI) optical system with a specified Modulation Transfer Function (MTF), a first-order filter EVS pixel model, and three different temporal probes: a step function, a linear ramp and an exponential ramp. By analysing the inverse of the entire chain for different event-statistic, and comparing the results to the specified MTF, we identify the context where each probe is most relevant. We consider how
photon-noise and cross-array threshold mismatch effects the analytical accuracy of the probe-inverse. Results show that the widely used step probe is highly susceptible to mismatch while resilient to
photon shot-noise, while a linear rise probe and exponential rise probe retain their ability to infer signal levels even with high mismatch. We discuss the potential of dynamic-PSFs as components of a full forward operator from scene to events. In this, we use this analytical description to define dynamic-PSFs around EVS, and discuss the gaps toward a unified pixel model and a scene-composition framework required for CNI.
Read the full abstract ▾
Robotics
Guangzhao Dai, Qianru Sun, Qi Wu et al. (+1 more)
We investigate whether GPT-6-Astra, a general-purpose foundation model, can navigate unfamiliar environments using its own perception,
reasoning, and decision-making capabilities. Our evaluation focuses on zero-shot
vision-and-
language navigation in continuous environments (VLN-CE) through a minimal interface in the Codex harness, aiming to unleash GPT-6-Astra's full potential for
navigation. Using
monocular RGB, GPT-6-Astra decides when to observe, how to move, and when to stop, without
navigation-specific fine-tuning, a trained waypoint predictor, or a pre-built scene map. Our evaluation yields four key findings and implications. First, GPT-6-Astra achieves strong zero-shot
navigation performance using only
monocular RGB observations. On R2R-CE-100, GPT-6-Astra (ultra
reasoning) achieves a success rate of 81.3%, exceeding the strongest reported zero-shot and even train-based success rates by 15.3 and 9.2 percentage points, respectively. Second, GPT-6-Astra exhibits promising capabilities in interpreting multi-stage instructions, understanding the environment, and adjusting routes. Third, execution and goal-verification failures persist even with ultra
reasoning. Fourth, these results motivate combining general-purpose model capabilities with
navigation-specific expertise. Based on these findings, future VLN research should investigate which aspects of instruction interpretation, spatial understanding, and
navigation decision-making general-purpose models can handle directly, and where
navigation-specific learning can extend their capabilities. This includes exploring how spatial representations,
navigation experience, and learned control skills can improve progress tracking, error recovery, and goal verification while preserving the flexibility to adjust routes.
Read the full abstract ▾
All authors Guangzhao Dai, Qianru Sun, Qi Wu, Bin Zhu
Distributed Computing
A Block Decomposed QUBO Workflow for Chromosome-Y Phylogeny Reconstruction
Giuliana Siddi Moreau, Riccardo Berutti, Manuela Profir et al. (+3 more)
This paper sets out a computational workflow that reconstructs the phylogeny of human Y-chromosome populations from a Variant Call Format (VCF) file of biallelic Single Nucleotide Polymorphisms (SNP). The two classical phylogenetic decisions -
topology selection and root placement - are cast as Quadratic Unconstrained Binary Optimisation (QUBO) problems. The workflow combines two QUBO formulations with an Alternating Direction Method of Multipliers (ADMM) decomposition strategy and a plug-in Digitized Counter-Diabatic
Quantum Optimization (DCQO) solver, enabling large phylogenetic optimization problems to be executed across multiple classical or
quantum computing resources. The DCQO gate-based optimizer drives each ADMM-block QUBO with short-depth counter-diabatic
circuits in the impulse regime, without the necessity for an outer variational loop. The combination of ADMM decomposition and the DCQO block solver facilitates problem sizes that surpass the
qubit budget of any individual digital
quantum processing unit call, while maintaining the integrity of the original objective. The workflow extracts genotype information from VCF files, reconstructs
topology and rooting through two QUBO formulations, and annotates the resulting tree using PhyloTree. The resultant data set comprises a Nexus-annotated rooted tree, in addition to diagnostic figures. The workflow demonstrates the potential of modest-scale QUBO formulations combined with ADMM decomposition to serve as a scalable alternative to greedy heuristics in the domain of population genomics.
Read the full abstract ▾
All authors Giuliana Siddi Moreau, Riccardo Berutti, Manuela Profir, Lorenzo Pisani, Maria Laura Clemente, Lidia Leoni