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)

Tuesday 11 August

Computation and Language

ODE-Based Transformer Decoders for Iterative Sign Language Translation

Sign language translation has achieved strong results with Transformer architectures, yet recent improvements largely rely on scaling model capacity at the cost of increased computation. We propose a parameter-efficient alternative that improves expressiveness without increasing model size. Rather than scaling capacity, we focus on enhancing the update dynamics of iterative refinement decoders, where each refinement step corresponds to one internal decoder iteration that progressively improves the latent representation before translation generation. We reinterpret residual refinement updates from an Ordinary Differential Equation (ODE) perspective and replace them with higher-order numerical integration schemes, namely Runge–Kutta methods (RK-2 and RK-4). These methods perform multiple function evaluations within each refinement step to produce more accurate and stable representation updates without adding decoder parameters. To the best of our knowledge, this is the first application of ODE-inspired update dynamics to sign language translation. RK-2 achieves 22.96 BLEU-4 on the PHOENIX-2014-T test set and 19.34 BLEU-4 on the CSL-Daily test set, outperforming the IPSLT baseline on both benchmarks, with fewer decoder layers and refinement iterations on CSL-Daily. These results suggest that stronger refinement dynamics can improve translation performance under parameter-efficient decoder designs, providing a complementary alternative to conventional model scaling.
Read the full abstract

Game Theory

Welfare Approximation in Multilateral Trade

We introduce the study of multilateral trade: a mechanism-design problem in which a single potential trade involves $k$ agents and can be executed only if all $k$ agents agree to participate. The classical case $k=2$ is the well-studied bilateral trade problem, where a seller and a buyer with private values must decide whether to trade an item initially held by the seller. Existing extensions of bilateral trade have largely focused on markets with many buyers and many sellers, but where each realized transaction is still bilateral, requiring agreement only between the matched buyer and seller. Our formulation captures settings in which the trade itself requires joint participation, coupling the agents' incentives and creating new challenges. We study welfare approximation in this setting under incentive compatibility, individual rationality, and budget balance. We give a DSIC mechanism with approximation ratio $O(k^2)$, and a BIC mechanism with approximation ratio $\widetilde O(k^{3/2})$. We prove matching lower bounds up to polylogarithmic factors. Finally, we extend the model to an $\ell$-out-of-$k$ partial-agreement setting, where the trade may occur once at least $\ell$ agents participate. In this relaxed model, the welfare guarantees improve smoothly as $k-\ell$, the number of agents whose participation is not required, grows, and we obtain matching upper and lower bounds up to polylogarithmic factors.
Read the full abstract

Computation and Language

Self-Evolving Embodied Agents via Skill-Harness Evolution

Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the model. While supervised fine-tuning and reinforcement learning can adapt agents to new environments, they require additional data, rewards, and training runs; meanwhile, many train-free code-centric approaches rely on programmable robot APIs that may be unavailable in fixed-interface settings. We propose SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen and improves the non-parametric agent system by evolving reusable skills and a context-code harness through target-environment rollouts. In SHAPER, the same frozen model can serve as both planner and optimizer, refining its external skills and context-code harness without parameter updates. We evaluate SHAPER on VLABench and ESI-Bench, covering embodied agents with different low-level action interfaces, and compare against pure execution, supervised fine-tuning, and test-time-scaling baselines such as verifier-free selection and voting. Our results suggest that skill-and-harness optimization is a practical route to self-evolving embodied agents when model training is expensive, unavailable, or undesirable.
Read the full abstract

All authors Peidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Yiqun Zhang, Zihan Wang, Xiaocui Yang, Shi Feng, Yuqing Yang, Dongsheng Li

Machine Learning

Dynamics Models for Offline Hyperparameter Selection in Real-World RL

A key obstacle to deploying reinforcement learning in real-world systems is hyperparameter selection, particularly when simulators are unavailable and online experimentation is costly. Prior work has proposed calibration models trained on offline data to approximate environment dynamics and enable offline hyperparameter selection, but these methods have so far been evaluated only in simple simulated settings. In this paper, we present the first application of calibration models in a real-world industrial setting: a municipal water treatment plant. We evaluate several calibration model approaches, including a k-nearest neighbors model with a Laplacian distance metric, on high-dimensional, non-stationary sensor data for nexting prediction tasks. Our results show that these models can generate realistic long-horizon rollouts and recover meaningful hyperparameter sensitivity trends. We further examine how calibration models scale to year-long datasets, how they support the selection of fine-tuning learning rates for pre-trained agents, and how robust they are under distribution shift. Overall, our findings provide a proof of concept for using offline dynamics models to support RL deployment in real-world environments, while highlighting important practical challenges for future work.
Read the full abstract

All authors Jordan Coblin, Han Wang, Martha White, Adam White

Cryptography and Security

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs

Anyone can upload a fine-tuned large language model (LLM) to a public repository and claim it is safe. A backdoored model behaves normally on ordinary inputs until a hidden trigger fires, and a user with no training data, clean reference weights, or the trigger phrase has no clear way to check the model before using it. We introduce and empirically evaluate self-feeding, a black-box test method that feeds a model's own output back as its next input, so the text drifts away from the starting prompt and toward the data the model was fine-tuned on. We test self-feeding against a repeated same-prompt baseline on six open-weight LLMs (3B-15B parameters), each fine-tuned with backdoors spanning eleven attack categories, using twenty ordinary starting prompts and chains of up to ten steps. Self-feeding finds backdoors in five of six models at 92.0% pooled precision, while the same-prompt baseline succeeds on only one of 120 prompt-model pairs; chains that begin with a joke request, an arithmetic question, or a coffee recipe all reach a trigger within a few steps. Recall per prompt is low (19.2%), and we show why it still adds up to much higher detection at the model level once several starting prompts are used. We also report where the method falls short: one model was never triggered, and self-feeding produced two false positives that the same-prompt baseline cannot produce. Cutting the chains to four steps keeps every model-level detection at 100% precision while using 60% fewer queries. Needing only text-level query access and a way to recognize malicious output, self-feeding offers a cheap first check on a downloaded model.
Read the full abstract

Data Structures and Algorithms

Distribution-Free Halfspace Testing with Samples

We prove a tight $\Theta(n/\epsilon)$ lower bound on the number of samples required for testing halfspaces over $\mathbb{R}^n$, in the distribution-free sample-based model where the underlying probability distribution is unknown to the algorithm, and the algorithm only receives random samples (i.e., it cannot make queries). This shows that testing is no more efficient than learning for halfspaces. We also show a matching upper bound for one-sided testers, improving on the standard (two-sided) testing-by-learning reduction, establishing that two-sided halfspace testers in this model have no advantage over one-sided testers.
Read the full abstract

All authors Xi Chen, Renato Ferreira Pinto Jr., Nathaniel Harms, Shyamal Patel, Rocco A. Servedio

Software Engineering

MergirafSemi: A Language-Agnostic Semistructured Merge Tool

Developers frequently face merge conflicts when integrating concurrent changes. Most merge tools rely on unstructured, line-based comparisons, often producing spurious conflicts and missing actual conflicts. To address these limitations, structure-aware merge tools have been proposed, which leverage syntactic representations to improve merge accuracy. However, fully structured tools may incur higher computational cost, and language-specific tools require significant development and maintenance effort. To balance these trade-offs, we propose MergirafSemi, a language-agnostic semistructured merge tool that captures structural information without requiring full structural modeling or language-specific implementations, and applies line-based merging within specific program regions, such as method bodies in Java. Our tool leverages lightweight Concrete Syntax Trees to guide merging decisions while preserving flexibility and efficiency across languages. We evaluate our tool through an empirical study on real-world merge scenarios across multiple programming languages, comparing it with unstructured, semistructured, and structured tools. Our results show that increasing structural granularity improves automatic conflict resolution but can also lead to more aggressive merge decisions, increasing the number of missed actual conflicts. In contrast, MergirafSemi achieves a more balanced trade-off, reducing spurious conflicts while maintaining competitive accuracy and better runtime performance in most common scenarios. Compared to an unstructured tool, it substantially reduces spurious conflicts, and when compared to a semistructured language-specific tool, it achieves comparable effectiveness while exhibiting more robust execution behavior and significantly lower runtime overhead.
Read the full abstract

All authors Pedro Lopes, Paulo Borba, Paola Accioly, Guilherme Cavalcanti

Computers and Society

Governing Agentic AI in FinTech

Financial institutions are delegating consequential decisions to agentic AI systems that decompose goals, coordinate models and tools, and act with little oversight. Yet agentic AI governance in FinTech is under-investigated. We argue the binding governance constraint is not capability but verifiability. We define the Verifiability Gap as the shortfall between the verification delegated authority demands and the explainability and reproducibility retained after a decision. It is indexed to a verifier, evidentiary standard, and audit lag. We develop a multilevel governance theory for agentic AI and test its mechanisms in three studies over nine model versions, from a three-billion-parameter local model to a commercial frontier system. Study 1 shows that provider releases alter historical financial actions, and that the controls replay needs belong to the provider: the frontier model rejects temperature, top_p and top_k outright and exposes no random seed. Under the tightest controls each endpoint allows, a local model reproduced 320 of 320 executions, hosted models 319 of 320 and 959 of 960. Study 2 shows that orchestration is a latent policy layer. Architecture changes final actions, and no execution record repeated in any configuration at any scale. The frontier model reproduces its own actions more often than the local ones, its record no better, and loses a comparable share of its differentiation. Capability buys a higher starting point, not auditability. Study 3 shows two deterministic credit-model versions each reproduce their current action perfectly, yet the current cannot recover a historical one. We conceptualize reproducibility as a governance profile, not a scalar, yielding evidence-contingent delegation: authority is defensible only while retained evidence substantiates its exercise. Beyond finance, the framework extends to other high-stakes domains requiring auditability.
Read the full abstract

Artificial Intelligence

Can Frontier LLMs Match Natively Multimodal Embeddings? A Comparison on Hard-Negative Text-to-Image Retrieval

Multimodal retrieval and classification across different types of media, spanning text, images,video and audio, has traditionally relied on dual-encoder models that align visual and textual representations through contrastive learning. The March 2026 release of Gemini Embedding 2, Google's first natively multimodal embedding model to map text, images, video, audio, and documents into a single shared space, raises competition among multimodal retrieval systems. Simultaneously, frontier Large language models (LLMs) have also demonstrated strong visual understanding, raising the question of whether they can serve as effective zero-shot rankers. Our study provides the first direct comparison of native multimodal embeddings against LLM-based visual ranking on Flickr30k. We observe that GPT-4.1 and Claude Sonnet 4.6 perform on par with Gemini Embedding 2. Additionally, once embeddings are precomputed, multimodal embeddings are better suited for low-latency applications.
Read the full abstract

Machine Learning

Weightless Fine-Tuning: Personalizing LLMs via Logit-Space Transport

Supervised fine-tuning (SFT) is a standard approach for adapting LLMs to a target distribution, but in settings such as personalization, where each author requires separate weight access, optimization, storage, and retraining, its costs become prohibitive. We propose Weightless Fine-Tuning (WFT), a training-free decoding-time method that approximates the distributional effect of SFT without weight updates. WFT computes supervised residuals on an author's training sequence and transports them to the current prompt through a cross-prefix transport operator estimated from dropout-induced cross-covariance. The operator captures how a perturbation at one context propagates to predictions at another, replacing gradient-based parameter updates with logit-space corrections. On three LaMP personalization benchmarks, WFT achieves the best average performance across datasets, matches or exceeds SFT on individual tasks, and outperforms other lightweight baselines on average. In a budget-controlled comparison, WFT approaches SFT performance using less than 7% of the effective computation. Logit-level analysis shows a cosine similarity of 0.875 between the logit shifts induced by WFT and SFT over 95% of the next-token probability mass, suggesting that WFT captures the distributional effect of supervised adaptation without modifying model weights.
Read the full abstract

All authors Bohan Zhang, Anqi Ni, Yixin Wang, Paramveer S. Dhillon

Artificial Intelligence

Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence

Apollo did not reach the Moon merely because its engineers could solve difficult equations. It succeeded by turning a distant ambition into a mission architecture of explicit objectives, simulation, verification, and repeated correction. AI now faces a similar transition: frontier models can solve difficult tasks once the problem, tools, and success criteria are specified, yet consequential real-world challenges rarely arrive in an executable or verifiable form. We introduce Apodex Discovery, a framework for building and evaluating discoverative AI through the heavy-duty solver, a system comprising a foundation model, harness, tools, and control policies that pursues extended, stateful, verifiable investigations. It has three core components. First, a problem-scouting process surveyed 561 industries across 16 sectors, assembled 423 high-value real-world problems, and selected 20 for the initial release. Second, a common environment-task-episode abstraction provides data, tools, constraints, feedback, trajectory recording, and verification of intermediate artifacts and final submissions. Third, HDS6 evaluates Tools, Repair, Alternatives, Coherence, Evidence, and Scope independently of final-task success. In AAV capsid design, Apodex surpassed the published state of the art by 7% across viability, tropism, structure prediction, and generative design. In drug repurposing and reformulation, a task-specific biomedical environment improved the mean normalized prediction score of GPT-5.5 and GPT-5.6-sol by 2.5 and 7.6 points over the same closed-book backbone. Controlled ablations show that the fixed TRACES episode interface enables attribution of performance differences to specific solver components. Apodex Discovery moves AI evaluation beyond predefined benchmarks toward verifiable investigations aimed at genuine discovery.
Read the full abstract

All authors Brian Wang, Bin Feng, Xiaoman Pan, Chenyang An, Felix Liu, Tangqi Fang, Gongbo Sun, Lingfeng Shen, Ning Wang, Handuo Zhang, Feng Chen, Fuchao Yang, Xiang Wang, Jiacheng Lin, Siting Li, Zixuan Liu, Chi Han, Zhenhailong Wang, Kunlun Zhu, Lawrence Zhao, Yueqi Guo, Kailong Wen, Feng Xing, Yiling Guo, Lidong Bing, David Tan, Bo An, Heng Ji, Sheng Wang

Networking

Self-evolving network verifiers

Symbolic network verifiers can reason about correctness across vast spaces of routing inputs and failures, but only for the protocols and features an expert has encoded by hand. Creating and maintaining a faithful model of the control plane is both difficult and never-ending, since no written source specifies perfectly what a network does: vendor implementations deviate from the RFCs, and behaviour shifts with releases. The burden of constant upkeep ultimately keeps verification out of many networks that need it. We argue that the model should instead evolve automatically to faithfully capture the actual network behaviour. To achieve that, we leverage the only source that specifies it unambiguously: the router software itself. In a counterexample-guided loop, a coding agent proposes extensions to the verifier's symbolic encoding, while a trusted oracle (e.g., emulated routers) supplies the ground-truth routing state. The agent iteratively refines the network model using each disagreement with the oracle. As early evidence, a prototype of this system taught a 3,000-line SMT-based verifier three features it did not support: OSPF areas, BGP route reflection, and L3VPN over EVPN, converging autonomously on models that match the oracle, even noticing vendor-specific behaviour. Automating model growth shifts the hard problem from writing verification systems to systematically testing them; we propose a research agenda for trusting and harnessing automatically evolved verifiers.
Read the full abstract

Computation and Language

Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost

Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents to novel domains by means of learning skills. Existing works focus on performance gain over cost effectiveness. As a result, little is known about what skill learning strategies save cost. We argue that among all the different skill learning methods, those that view skills as programs can achieve the best cost reduction. By executing sequences of actions deterministically, a program-augmented agent can reliably and cheaply achieve goals that would otherwise require trial and error and risk degenerate behavior over long horizons. An agent can learn at inference time by incrementally discovering these programs and equipping them for future tasks. We hypothesize that past trajectories contain enough signal to guide skill learning, even without replay or validation, provided the agent can learn to analyze them. To test our claims, we propose SpeedRunner, a coding agent that analyzes trajectories and refactors skills for better performance on future tasks. Across three different embodied environments, we show that SpeedRunner consistently achieves the frontier in learning and cost reduction while remaining robust against distribution shifts and environmental randomness.
Read the full abstract

All authors Zixi Huang, Xiheng Wang, Andrew Wang, William Jurayj, Bernal Jiménez Gutiérrez, Daniel Khashabi, Nicholas Andrews

Cryptography and Security

Association-based Privacy Attacks in Wireless Protocols: Formal Modeling and Mitigation

With the surge in privacy-sensitive data from sources such as social media and IoT devices, there is a pressing need for formal, automated methods to assess privacy risks within these intricate systems. This paper formally investigates root sources of pairing-based privacy threats exploited using replay/relay techniques in wireless communication. Our research harnesses condition-oblivious responses, replay-resistance, and distance bounding measures vital for protocols utilizing shared keys in allowlists for authenticated reconnections. Particularly, the paper uses formal modeling of notable wireless networks, like the Wi-Fi P2P persistent group formation and the Bluetooth Low Energy reconnection procedure, to illustrate the root causes and countermeasures. Our model rigorously validates the proposed solution against association inference attacks, along with existing formalizations of well-authentication, frame opacity, and no-desynchronization. The ensuing analysis reveals not only uncharted privacy realms in wireless communication but also identifies old and new vulnerabilities. Our proposed design changes are acknowledged by Wi-Fi Alliance and Bluetooth SIG, paving the way for future advancements in resilient, privacy-preserving wireless protocols.
Read the full abstract

Computer Vision

Dual-Domain Cross-Modal Decoding for Clinical Text-Guided Medical Image Segmentation

Clinical text can narrow down what to segment, but recent text-guided designs emphasize spatial alignment while overlooking frequency content that governs texture and boundaries. We propose Dual-Domain Cross-Modal Decoding (DD-CMD) for clinical text-guided pulmonary infection segmentation, integrating two complementary forms of language guidance during decoding. In the spatial domain, Text-Guided Spatial Cross-Attention (TGSA) aligns multi-scale visual tokens with text semantics and updates features through gated residual fusion. In the frequency domain, Spectral-Text Adaptive Modulation (STAM) applies a 2D DCT to compute learnable band-energy statistics and predicts text-conditioned FiLM parameters to recalibrate decoder channels for frequency-aware decoding. DD-CMD embeds TGSA and STAM into a coarse-to-fine decoder (7x7 to 56x56) and restores full-resolution masks using a lightweight two-stage refinement module. Experiments on QaTa-COV19 and MosMedData+ show that DD-CMD achieves 91.46% Dice / 84.26% mIoU and 81.95% Dice / 69.42% mIoU, respectively, with average gains of +1.96 Dice and +2.67 mIoU over the strongest prior baselines. Code: https://github.com/maklachur/DD-CMD.
Read the full abstract

Computation and Language

Gloss-Free Representation Learning for Cross-Dataset Sign Spotting

Sign-language research for resource-constrained languages is often limited by the cost of dense linguistic labels such as glosses, temporal boundaries, and sign order. Broadcast news offers a practical alternative by pairing continuous signing with spoken-language transcripts, but this supervision is weak since text and signing are loosely aligned. Morphologically rich languages such as Turkish add further difficulty, as the same lexical meaning can appear in many inflected forms while some derived forms should remain distinct. We study whether weak transcript-based supervision can pretrain a reusable sign encoder in this setting, where poor text normalization can fragment pseudo-gloss targets and weaken representation learning. Unlike prior pseudo-gloss pipelines designed mainly to improve translation, we test whether the pretrained encoder transfers as a reusable representation for cross-dataset sign spotting. We pretrain on TSL-News, a new Turkish broadcast corpus, using pseudo-gloss labels derived from transcripts rather than manual annotation, comparing rule-based morphological lemmatization with constrained LLM-assisted normalization over a fixed vocabulary. We evaluate the learned representations via cross-dataset sign spotting on a new TSL Spotting Benchmark built from the TSL Dictionary corpus. The LLM-assisted encoder raises top-5 temporal localization mean IoU from 0.235 to 0.465, with 56.2% of examples reaching an IoU of at least 0.50; a frequency analysis suggests this gain is not mainly driven by memorizing frequent pseudo-gloss labels. In a downstream translation check, the same pretraining improves BLEU-4 from 9.60 to 11.04 and ROUGE from 23.48 to 27.43. These results show that loosely aligned broadcast data can provide effective weak supervision for learning sign representations that capture both lexical content and temporal structure.
Read the full abstract

All authors Oğuz Akif Tüfekcioğlu, Ezgi Ekin, Mustafa Kaan Çevik, Hacer Yalim Keles

Sound

Qwen-MusicAVQA-7B: A Multimodal Model for Music Audio-Visual QA

A common approach to adding audio to a vision-language model is to train or adapt a large omni-modal system. We show that a lightweight alternative can be highly effective for music audio-visual question answering (AVQA). Qwen-MusicAVQA-7B connects a frozen Whisper encoder to Qwen2-VL-7B-Instruct through learned linear projections. The same frozen encoder processes both the video's music track and a TTS-spoken question through separate projectors, while the language model fuses visual frames, music, and question audio through pretrained self-attention, with no task-specific fusion network. On MUSIC-AVQA, our system reaches 96.0% +/- 3.9% accuracy across three independent training seeds on the 7,402-question available-video test subset. Our central finding is that downstream accuracy tracks how much fine-grained local temporal information the audio representation preserves. In a matched 32-token comparison, a stride-pooled Whisper frame sequence outperforms a globally pooled PANNs representation expanded to the same budget by 26 percentage points, even though PANNs sees at least as much audio and uses a far larger projector. The effect is not simply sequence versus vector: within Whisper alone, reducing temporal resolution at a fixed token budget costs a comparable amount. Under matched data and inputs, fine-tuned Qwen2.5-Omni-7B reaches 80.9%, against 95.9% for our 30 s variant; because the systems differ in backbone and adaptation, this is a system-level comparison. Accuracy remains high on sampled head and tail splits of the rephrased MUSIC-AVQA-R benchmark (96.5% and 95.6%). Because both encoders stay frozen and the music features are cached, the entire adaptation is cheap to train: the complete two-stage AVQA run takes approximately 5 hours on a single A100 80GB, and every run reported here fits on that one GPU.
Read the full abstract

Machine Learning

Long-Horizon Forecasting of Complete Financial Statements with Forma

Specialist training beats generalist scale when forecasting financial statements. To our knowledge, no prior work jointly forecasts complete financial statements beyond one year, yet in a discounted-cash-flow valuation most firm value sits past that window. We release ProForma-20Q, a reproducible benchmark for forecasting 78 statement line items 1-20 quarters ahead, for anonymized firms, from past statements and an industry code, scored by change-space $R^2$. On it, Forma, a transformer that reads statements as sets of (account, quarter, value) tuples and maximizes a masked-tuple Gaussian likelihood, beats every competitor we field: classical machine learning, chained gradient boosting, a zero-shot time-series foundation model, and frontier large language models. Its lead widens with horizon, where valuation needs accuracy most, and its Gaussian predictive intervals never under-cover. Forma's forecasts nearly satisfy accounting identities; exact coherence is recoverable at no statistically significant accuracy cost. Its tuple interface supports scenario analysis without retraining, and we show that pinning future revenue paths sharpens the rest of the statement.
Read the full abstract

All authors Travis L. Johnson, Jiannan Jiang, Soumyabrata Chaudhuri, Yihao Chen, Lauren Falvey, Donal O'Cofaigh

Machine Learning

Contextual Quality-Diversity Evolutionary Reinforcement Learning for HVAC Control in Tropical Commercial Buildings

This paper proposes a contextual quality-diversity evolutionary reinforcement-learning controller, CQD-ERL, for the supervisory control of a tropical, water-cooled chiller plant and its associated air side. Rather than converging to a single scalarised policy, the controller maintains a product archive of specialised policies indexed jointly by a data- driven operating context, a cluster of daily weather and load regime, and a context-invariant behaviour descriptor, filled by a gradient-free evolutionary operator and a soft-actor-critic policy-gradient operator that share one replay buffer. Every action is filtered through a deterministic safety shield before execution. The controller is trained on a two-tier reduced-order environment representing the latent load, cooling-tower approach and humidity constraints of a Singapore commercial building, and is evaluated over a full annual backtest against an ASHRAE Guideline 36 baseline.
Read the full abstract

Artificial Intelligence

Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations

Enterprise practitioners read agent leaderboards as if they ranked agent capability. We show, across three open agent-trace benchmarks (TheAgentCompany, $\tau^2$-bench, and AppWorld), that the agent main effect accounts for less than 3% of total variance in every dataset and check type, while the agent-by-task interaction accounts for 7-23%. Leaderboards rank specialization, not capability. We arrive at this through a four-facet Generalizability Theory variance decomposition, fit with three estimators (Henderson Method-I, REML via lme4, and a Bayesian binomial GLMM) that agree to three decimal places. Four further findings sharpen what the leaderboard is hiding. First, aggregate reliability collapses on the hardest task quartile: $E\rho^2$ on $\tau^2$ action_checks falls from 0.752 to 0.000. Second, training-cell reliability negatively correlates with held-out reliability ($r = -0.90$ on $\tau^2$), meaning the designs that look most reliable replicate worst. Third, population-level diagnostics transfer across enterprise benchmarks (capability-gap ratio stable at 0.35-0.40) but per-family agent rankings invert. Fourth, on the MAST failure taxonomy, trace-level mode profiles are idiosyncratic (MAE = 0.261) while cell-level profiles generalise (MAE = 0.056, $r = 0.83$). We package these into Deployment Decision Reliability (DDR), a one-page reporting discipline that turns the variance-component table into five decisions an enterprise buyer can defend. All code, data loaders, and fit artifacts are released under an open-source license.
Read the full abstract

Human-Computer Interaction

Socioduality: A Relational Process Framework for Human-AI Interaction

Human-AI research often evaluates individual capabilities, joint performance, or final outputs, but these approaches can lose the interaction process that produced the result. This article introduces socioduality: a sequential, reciprocal, and history-carrying process in which one party's response becomes part of the observable conditions shaping the other party's next contribution, judgement, decision, or action. For human-AI dyads, the framework identifies moves, candidate episodes, confirmed episodes, and maximal pathways. A minimum episode A1 -> B1 -> A2 requires evidence that B1 responds to A1 and that B1 then enters the formation of A2; candidates are classified as confirmed, non-sociodual, or indeterminate. A frozen coding protocol was calibrated on three natural human-AI records using two separate model-based evaluator series. A supplementary exploratory analysis then compared frozen Sociodual pathways with blind developmental/task-process segmentations. Across six examined interactions, the two representations were empirically non-equivalent: task-stage changes could occur within a continuing Sociodual pathway, while formal pathway breaks could occur within a continuing task context. This distinction persisted under fine-grained re-segmentation and record-format checks and was reproduced in all three prospectively selected unseen records using a fresh model-based Sociodual coding line. Socioduality therefore offers a bounded process-level framework for studying how human and AI contributions become relationally linked across time, preserving information that task-stage and endpoint-centred analyses do not uniquely recover.
Read the full abstract

2608.11322 · 11 Aug · 50 pages, 4 figures, 12 tables. Revised version adds a Supplementary Exploratory Analysis comparing Sociodual pathways with blind developmental/task-process segmentation, with granularity and record-format checks and an unseen-case extension. Main construct specification unchanged; minor editorial and terminology refinements

Social and Information Networks

Spectral graph clustering with inhomogeneous latent geometry

We study spectral clustering in the presence of a confounding latent geometry. The leading eigenvectors may then be dominated by the latent geometry rather than by the communities. Nevertheless, we show in a block latent-space model that communities can be recovered from eigenvectors deeper in the spectrum. We analyze the spectral properties of the adjacency matrix through a limiting integral operator and use its structure to develop DBSPEC, a density-based spectral clustering algorithm that requires only approximate localization of the informative eigenvalue and is robust to poor eigenvalue separation. Crucially, this approach handles general latent geometries, overcoming restrictions to homogeneous toroidal models in prior works. Our theoretical predictions for the location of the informative eigenvalue notably align with observations in real-world experiments.
Read the full abstract

Computational Complexity

An FKN Theorem for the Binary Grassmann Scheme

A classical theorem due to Friedgut, Kalai and Naor asserts that if a function $f\colon \{0,1\}^n\to\{-1,1\}$ close to a degree $1$ function, then either $f$ or $-f$ is close to either the all $1$ function, or to $(-1)^{x_i}$ for some $i\in [n]$. We prove a version of their theorem for the Grassmann scheme over $\mathbb{F}_2$. More precisely, we prove if a function $f\colon \genfrac{[}{]}{0pt}{}{\mathbb{F}_2^n}{\ell}\to\{0,1\}$ is close to a degree $1$ function, then either $f$ or $1-f$ must be close to a function of the form $g(L) = \sum_{x\in\mathcal{X}}1_{x\in L}+\sum_{W\in\mathcal{W}}1_{L\subseteq W}$, where $\mathcal{X}\subseteq\mathbb{F}_2^n$ is a set of points and $\mathcal{W}$ is a set of hyperplanes in $\mathbb{F}_2^n$.
Read the full abstract

Machine Learning

Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction

Many sequential construction tasks have exact terminal symmetries even though execution is directed and depends on history. Process evidence supplies order. Terminal correspondence transports it between equivalent outcomes; the realized state updates relevance. These roles define a carrier framework: transport what the outcome preserves; refine what history changes. SymBuild combines transported process and state residual ranks by ordinal rank meet. Its rank threshold sets equal the corresponding unions, yielding a tight worst-case verifier query bound under prefix information. We evaluate SymBuild in three construction domains: computer-aided design (CAD) assembly, Mini-Programs, and exact-fill packing, and its ordinal adaptation in target removal. SymBuild improves the area under the anytime verified success curve by up to 6.77, 21.75, and 8.68 points over Static in the three construction domains. Refresh gains recur beyond SymBuild under alternative aggregation, planning, and learned scoring methods; on Geometric Reasoning Network (GRN) target removal, direct Combined refresh has the lowest mean verifier query score at all three scales and reduces distinct scored states by factors of 6.48-12.22 relative to refreshed population-based search. Together, these results support the carrier framework and demonstrate that SymBuild is an effective, analyzable method for anytime verified construction.
Read the full abstract

Computer Vision

Clinical Feasibility of Low-Magnification Fluorescence Imaging for Breast Cancer Margin Detection Using Texture Analysis and Deep Learning

High-resolution images of unprocessed surgical breast tissue can be obtained using microscopy with ultraviolet surface excitation (MUSE). This technique is considered a promising method for checking surgical margins during breast cancer surgery. In this study, MUSE images at 4x and 10x magnifications were compared using patch-level classification methods. Texture analysis (TA) based on local binary patterns (LBP) and deep learning (DL) with a base Vision Transformer (ViT) model were used. Both methods achieved similar performance at both magnifications. Using DL method, both 4x and 10x magnifications achieved 96.30% sensitivity, 100% specificity and 98.18% accuracy. Using TA method, 4x achieved better specificity (100% vs 93.33%) and 10x yielded higher sensitivity (100% vs 93.33%), but both had the same accuracy (96.67%). No clear improvement in performance was observed with 10x magnification. These results show that 4x imaging achieves the same diagnostic accuracy as 10x imaging. At the same time, 4x offers a larger field of view and faster image capture. Therefore, lower magnification can be effectively used in MUSE systems for accurate and efficient intraoperative margin assessment.
Read the full abstract

All authors Pouya Afshin, Tianling Niu, Tongtong Lu, David Helminiak, Julie Jorns, Mollie Patton, Tina Yen, Donghye Ye, Bing Yu

Cryptography and Security

Backdoor Decontamination Dynamics in LLM Agents

Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defenders do not know the existing trigger, they cannot unlearn it directly. One decontamination strategy is to install a known backdoor (defensive poisoning) then to unlearn it, hoping that the original unknown backdoor is removed as a side effect. However, this procedure has uncertain outcomes: the original backdoor may persist or be erased or rerouted, among other possibilities. We introduce a framework for studying these dynamics in tool-calling agents, decoupling trigger, response, teacher, and fine-tuning method across systematic experiments on AgentDyn. Across 115 experiments, defensive poisoning alone erases around 56% of original backdoors; subsequent decontamination then drives almost all survivors to erasure, confirming that trigger recognition and malicious execution are behaviorally dissociable. Interestingly, our experiments find that malicious backdoors never persist when using different triggers of the same general type as the defensive backdoor when followed by decontamination via unlearning. Co-installing up to four backdoors increases resistance (around 36% erased), yet decontaminating a single known co-resident backdoor collaterally clears 52/60 co-residents (87%). Upon visualizing postdecontamination model internals using J-lens, we confirm that although the decontamination restores benign LLM responses, traces of original trigger awareness persist at intermediate layers.
Read the full abstract

All authors Gabriel Huang, Abhay Puri, Léo Boisvert, Alexandre Drouin, Perouz Taslakian, Spandana Gella, Christopher Pal

Cryptography and Security

Battlefield 5G: Dual-PKI and TPM-Based UE Attestation for Tactical 5G Standalone Networks

The standardized 5G Authentication and Key Agreement (5G-AKA) authenticates a subscriber credential stored on a Universal Subscriber Identity Model (USIM) but does not authenticate the physical device that holds that credential or verify its boot state. This gap is significant in tactical 5G deployments, where user equipment may be captured, modified, returned to service, or used with transplanted subscriber credentials. We present Battlefield 5G, a pre-authentication framework for 5G Standalone networks that combines dual X.509 device-certificate checks with Trusted Platform Module (TPM) -based boot attestation before standard registration is accepted. The design places an outer certificate challenge on the 5G base-station called gNB, an independent inner certificate challenge on the Access and Mobility Management Function (AMF) in the 5G core network, and a TPM PCR (Platform Configuration Register) quote verified by an attestation proxy on the 5G core network side. A gNodeB (gNB) side Radio Resource Control (RRC) forwarding gate and an AMF-side save-and-replay mechanism enable multi-round certificate and attestation challenge-response exchanges to be inserted into the registration path without modifying any 3GPP Non-Access Stratum (NAS) message structures or adding new NAS message types. We implement these capabilities by extending the Radio Access Network of the Software Radio System (srsRAN), gNB, User Equipment of the Software Radio System (srsUE) and Open5GS in a B210-based Universal Radio Peripheral (USRP) testbed with a hardware TPM 2.0 in the UE. The prototype blocks SIM-transplant, rogue-certificate, firmware-tampering, and replay attacks. Across six trials, Battlefield 5G increases average onboarding latency from 1886 ms to 2260 ms, adding 373.4 ms of pre-authentication overhead while preserving standard 5G-AKA, security mode, and packet data unit (PDU) session procedures.
Read the full abstract

All authors Al Nahian Bin Emran, Rajendra Paudyal, Rajendra Upadhyay, Lisa Donnan, Arupjyoti Bhuyan, Duminda Wijesekera

Computer Vision

Self-Evolving Code-with-Image Reasoning

Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The central challenge is one of perception: tools mostly serve to expose visual evidence, reasoning over that evidence stays in language, and most targets are ones a human could in principle determine by inspection. Some visual questions, however, are not bottlenecked by perception: recovering their answers requires executing a multi-step visual algorithm over the pixels. On such questions a model often names the correct algorithm at once yet still answers wrong, because language can describe an algorithm without being able to run one. Code-with-Image crosses that line: given nothing but a Python interpreter, the model must implement a genuine visual algorithm in code to solve the task; the program itself becomes the reasoning. The bottleneck then shifts from executing code to deciding which algorithm to implement. So we let the model teach itself: a training-free reflection loop studies its own failed programs, tests repairs against constructive ground truth, and keeps what survives as portable skills. On our Code-with-Image Bench (CwI-Bench), thirty task families induced by hidden visual computations with disjoint learning and evaluation splits, even GPT-5.6-luna stays below 30% with tool-free chain of thought; given a bare interpreter it reaches 43%, and with skills evolved through its own executable reflection, 67%. The open 27B model climbs the same ladder (9% $\rightarrow$ 33% $\rightarrow$ 56%), and the skills are plain text, transferable across scales and families. When code carries the reasoning, debugging code becomes debugging reasoning.
Read the full abstract

All authors Tianze Yang, Liang Wu, Ruitong Sun, Yucheng Shi, Yanqiao Wang, Mayank Darbari, Ninghao Liu, Jin Sun, Liangjie Hong

Cryptography and Security

Dueling Deep Q-Learning for Intrusion Detection

Intrusion detection systems (IDS) and automated systems for detecting and reporting cyber threats, are commonly handled via supervised machine learning methods. Though effective, these models struggle to effectively adapt to new attack types. This study proposes a novel approach by employing a reward-based, dueling Q-learning model for IDS, achieving an average accuracy of 99.68% across multiple attack classes. The proposed model has a dueling network architecture which separates its predictions into value and advantage streams. This has the benefit of improving learning efficiency and stability. The model was trained on the CIC-IDS2018, a benchmark dataset based on real-world intrusion detection scenarios, having multiple attack classes such as DDoS, botnets, and brute-force attacks. Furthermore, Explainable AI (XAI), specifically SHAP (SHapley Additive exPlanations), was also integrated into the training and evaluation process to provide interpretability into the model's predictions.
Read the full abstract

All authors Logan Luna, Matthew P. Berkowitz, Laxima Niure Kandel, Sirio Jansen-S'anchez

Discrete Mathematics

How Difficult Is It to Recognize CIS Graphs?

A graph $G$ is called $CIS$ if each maximal clique intersects each maximal stable set of $G$, with maximality taken with respect to set inclusion. CIS graphs resemble perfect graphs in several respects and have interesting applications in game theory. The complexity of recognizing CIS graphs was posed as an open problem by Chvátal in the 1990s and has since led to conflicting conjectures. We settle the problem by showing that recognizing CIS graphs is $\mathsf{coNP}\text{-complete}$.
Read the full abstract