Peer Revenue Past citations are no guarantee of future returns

Papers

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

Computer Science Artificial Intelligence

cs.AI Watch Artificial Intelligence

Monday 15 June

Artificial Intelligence · Cross-listed from cs.CL

AuAu: A Benchmark for Auditing Authoritarian Alignment in Large Language Models

Andreas Einwiller, Max Klabunde and Florian Lemmerich

The worldwide rise of authoritarianism and the growing role of Large Language Models (LLMs) in users' everyday lives raise the question of whether specific models exhibit or promote authoritarian attitudes. We introduce AuAu, a comprehensive benchmark for assessing the risk of authoritarian tendencies in LLM responses. AuAu combines three evaluation approaches: (i) psychometric questions from 15 human-validated instruments, (ii) vignettes probing intended behavior in concrete situations, and (iii) responses to realistic user prompts. Unlike prior work, AuAu measures not only overall authoritarian alignment but also its established sub-concepts: Authoritarian Aggression, Authoritarian Submission, and Conventionalism. Evaluating 17 models from China, the EU, Russia, and the USA, we find substantial authoritarian response rates on psychometric instruments across all models, though rates drop significantly on more realistic downstream tasks. Moreover, a simple authoritarian system prompt manipulates 15 of 17 models into promoting increased authoritarianism. Our results underscore the need for continued, systematic auditing of LLM-based AI systems to detect and mitigate authoritarian tendencies in their outputs.
Read the full abstract

Artificial Intelligence

Thinking with Visual Grounding

Junkai Zhang, Yihe Deng, Kai-Wei Chang et al. (+1 more)

Visual thinking should not only sound right; it should show its evidence. While recent vision-language models (VLMs) can produce natural-language reasoning traces, these traces often leave the supporting image regions implicit, making them hard to verify and difficult to supervise. We introduce visually grounded thinking, a reasoning process in which models interleave natural-language thoughts with explicit point or box groundings of the visual evidence used at each step. This lets the model express intermediate reasoning in language while grounding key objects in the image regions they refer to. To train this behavior, we construct a scalable synthesis pipeline that distills correct visual reasoning traces, extracts the visual objects required by the traces, grounds them with a SAM3-based agent, and derives aligned point and box supervision from the resulting masks. We further propose grounding-aware reinforcement learning, which combines answer correctness rewards with dense grounding rewards that score whether generated object references match the correct image evidence. Across two counting benchmarks and four spatial reasoning benchmarks, adding visually grounded thinking to Gemma3-4B-IT consistently improves performance over the original model and the non-grounded thinking baseline. On spatial reasoning, the visually grounded thinking 4B models match, and in some cases surpass, Gemma3-27B-IT from the same model family. Our analysis shows that point grounding is well suited to counting, while box grounding benefits most from explicit grounding rewards on spatial tasks. Overall, our results show that VLMs think better when their intermediate thoughts are tied to the image regions that make them true.
Read the full abstract

All authors Junkai Zhang, Yihe Deng, Kai-Wei Chang, Wei Wang

Artificial Intelligence

Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning

Olivia Peiyu Wang, Sanna Wong-Toropainen, Daneshvar Amrollahi et al. (+4 more)

Large Language Models (LLMs) achieve strong performance on reasoning tasks, but whether this reflects faithful logical inference or heuristic approximation remains unclear. We study this question in legal entailment by comparing three paradigms, including pure LLM classification, LLM-based Formal Reasoning, and solver-based Formal Reasoning using the Z3 SMT solver, on a re-annotated subset of ContractNLI across five LLMs. Our re-annotation reveals a systematic and measurable gap between pragmatic legal interpretation and strict formal entailment, where a substantial proportion of legally sound inferences are not formally grounded without additional unstated assumptions. While introducing formal structure improves accuracy, with LLM-based Formal Reasoning achieving the highest benchmark performance, we show that this gain does not imply faithful reasoning. We identify three recurring failure modes: scope laundering, where LLMs report solver-inconsistent classifications without executing the underlying formal reasoning, producing conclusions that appear logically grounded but are not; implicit constraint blindness, where LLMs overlook logical constraints present in formal representations; and program synthesis failures, where LLMs generate incorrect Z3 code despite structured prompting. Critically, scope laundering persists across all models, raising serious concerns about the faithfulness of LLM-based formal reasoning as a proxy for symbolic execution. These results reveal a fundamental gap between benchmark accuracy and logical faithfulness.
Read the full abstract

All authors Olivia Peiyu Wang, Sanna Wong-Toropainen, Daneshvar Amrollahi, Ryan Bai, Tashvi Bansal, Arush Garg, Leilani H. Gilpin

Artificial Intelligence

RecourseBench: A Modular Framework for Reproducible Algorithmic Recourse Evaluation

Hashir Ahmed, Zahra Khotanlou, Chenghao Tan et al. (+2 more)

Algorithmic recourse methods provide counterfactual explanations that inform individuals of the actions required to overturn an unfavorable model decision. Despite rapid methodological progress, principled comparison remains elusive; existing frameworks are often difficult to extend and lack both interoperability and systematic verification that integrated methods faithfully reproduce their originally reported claims. We introduce RecourseBench, a unified evaluation framework built around three commitments: modularity, reproducibility, and interactivity. The framework decomposes the pipeline into five fully decoupled layers—Data, Preprocessing, Model, Recourse Method, and Evaluation—governed by abstract interfaces and a dynamic registry. Every integrated method is classified into a four-tier reproducibility taxonomy based on artifact availability, followed by a systematic verification of its core empirical claims. We further provide an interactive web interface for flexible, configuration-driven exploration across datasets, model architectures, methods, and evaluations. To our knowledge, RecourseBench is the first benchmark to explicitly ground recourse evaluation in structured claim verification and mathematically rigorous reproducibility standards, all while featuring the largest collection of state-of-the-art recourse algorithms (27 in total).
Read the full abstract

All authors Hashir Ahmed, Zahra Khotanlou, Chenghao Tan, Ahmed Abdelaal, Amir-Hossein Karimi

Artificial Intelligence · Cross-listed from cs.LG

Scaling Adaptive Depth with Norm-Agnostic Residual Networks

Tomás Figliolia and Beren Millidge

Residual architectures are ubiquitous in deep learning, but they suffer from a subtle structural limitation: the norm of the residual stream can grow rapidly with depth. As a result, updates from later layers become small relative to the accumulated residual state. This reduces their impact on the representation and limits the benefits of scaling models in depth. To address this, we introduce NAG, a norm-agnostic residual architecture that separates magnitude from directional information in the residual stream, preserving meaningful layer contributions throughout depth and preventing later updates from being systematically suppressed by residual-norm growth. Importantly, NAG introduces only a negligible number of additional parameters and relies on simple operations that are easily kernel-fusible, preserving training efficiency in practice. We show that this architecture outperforms baseline Transformers, with gains that increase substantially as depth grows, enabling effective training of much deeper models. The norm-agnostic formulation also leads to an interpretable Mixture-of-Depths (MoD) mechanism that adaptively skips both attention and MLP layers. Beyond serving as a post-training accuracy-compute tradeoff, this mechanism can be used as a pretraining-time scaling strategy: under iso-FLOP training, compute saved by reducing per-token forward-pass cost can be reinvested into training on more tokens while keeping the total parameter count and KV-cache budget fixed. In our experiments, moderate Mixture-of-Depths rates of approximately 20%-25% match full-depth baseline performance under equal training compute while substantially reducing the number of executed layer parameters and forward-pass FLOPs. These results identify sparsity in depth as a new scaling axis for fixed-compute training, enabling very deep yet FLOP-efficient models.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

Long-Context Modeling via GSS-Transformer Hybrid Architecture with Learnable Mixing

Kuzey Torlak, Hüseyin Arda Arslan, An{\i}l Dervişoğlu et al. (+2 more)

Modeling long-range dependencies remains a central challenge in natural language processing. Transformer architectures achieve strong performance via self-attention but scale quadratically ($O(N^2)$) with sequence length, while State Space Models (SSMs) scale linearly ($O(N)$) but suffer from a selective recall bottleneck, struggling to retrieve precise information from compressed states. This creates a fundamental tradeoff between efficiency and perplexity. To tackle these challenges, we propose the Parallel Hybrid Architecture (PHA), which runs Gated State Spaces (GSS), Grouped Query Attention (GQA), and Feed-Forward Networks (FFNs) as independent parallel branches fused by a learnable mixing mechanism. Instead of forcing SSMs to approximate attention or serializing the two paradigms, PHA allows each branch to specialize: GSS captures global context, while attention performs selective retrieval, with FFN providing complementary processing. On WikiText-103, PHA achieves 16.51 PPL at 125M parameters, outperforming Hedgehog (16.70) and H3-125M (23.70). Scaling to 180M parameters yields 16.42 PPL, which gives comparable results with the pure attention baseline while delivering 24% higher throughput and up to 40% lower memory usage at long contexts. On OpenWebText, our 125M model achieves 19.72 PPL, outperforming standard Transformers (20.60) and GSS hybrid baselines (19.80). These results demonstrate that separating sequence modeling paradigms into parallel specialists enables Transformer-level perplexity with substantially improved efficiency for long-context language modeling.
Read the full abstract

All authors Kuzey Torlak, Hüseyin Arda Arslan, An{\i}l Dervişoğlu, Beyza Nur Deniz, Onur Boyar

Artificial Intelligence · Cross-listed from cs.CV

VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA

Young Rok Jang, Hyesoo Kong, Kyunghwan An et al. (+3 more)

Real-world documents combine text with tables, charts, photographs, and diagrams arranged in diverse layouts, yet existing research on multimodal large language models (MLLMs) for document QA predominantly produces text-only responses, underutilizing these visual elements. We introduce VinQA, a dataset for long-form answer generation where cited visual elements are explicitly interleaved with their supporting text and grounded in relevant document pages. To support this task, we study two encoding methods for feeding raw document page images into an MLLM, along with their visual-element citation mechanisms: (1) Page Encoding, which directly encodes full-page images with bounding boxes of visual elements and treats these boxed regions as citable units; and (2) Modality Encoding, which parses each page to extract text and crop visual elements, encodes them separately, and uses these cropped elements as citable units. In our experiments, we propose M-GroSE, a multimodal evaluation framework extending GroUSE to assess answers along four dimensions: completeness, answer relevancy, faithfulness, and unanswerability. We additionally report Visual Source F1 to directly measure visual citation accuracy. Although proprietary frontier models still achieve the best overall scores on the VinQA test split, fine-tuning open Qwen2.5-VL models on the training split substantially improves their performance and narrows this gap. Modality Encoding is initially more robust for complex documents with long text, many visual elements, and diverse citation requirements. After training on VinQA, however, Page Encoding reaches a comparable level, competing effectively even without the explicit parsing used in Modality Encoding. Finally, Visual G-Eval, an MLLM-based judge, confirms that fine-tuned models insert visual elements at semantically appropriate positions with faithful supporting text.
Read the full abstract

All authors Young Rok Jang, Hyesoo Kong, Kyunghwan An, Jae Sub Huh, Gyeonghun Kim, Stanley Jungkyu Choi

Artificial Intelligence

Rhythm of the Deep: Two-tier acoustic organization of sperm-whale codas from click waveforms to coda sequences

Mudit Sinha and Sanika Chavan

Sperm-whale codas are usually described by the number and timing of their clicks. These measures have revealed patterns in whale communication, but leave open how click sound contributes beyond timing and whether the order of whole codas carries additional structure. We investigate these questions through two tiers of acoustic organization, first within codas and then across coda sequences. Frozen pretrained audio encoders provide a framework for measuring acoustic variation beyond timing. We use them to identify recurring forms independently for clicks and whole codas in 1,483 codas, then validate their differences through direct waveform measurements. Within codas, click sound provides information beyond timing alone, while timing remains informative when click composition is held fixed. At the level of complete codas, we also find recurring acoustic forms whose differences are not fully captured by conventional timing-based types. With these forms identified, we examine how ordering contributes at each tier. Within codas, click-form order adds little predictive information beyond composition. Across codas, knowing the last two codas improves prediction over knowing only the last one. Together, these findings support two tiers with different organizing rules: acoustic composition and rhythmic timing within codas, and predictive relationships among whole codas across recorded sequences.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

Tool-IQA: Augmenting Image Quality Assessment with Simple Tools

Guanyi Qin, Junjie Zhang, Chunming He et al. (+4 more)

Vision-Language Models (VLMs) have been increasingly adopted for Image Quality Assessment (IQA). However, current methods typically employ a static one-shot scoring paradigm, despite the fact that humans assess image quality through dynamic visual inspection, e.g., selectively adjusting views to verify details and subtle artifacts. Specifically, relying solely on a single-pass observation introduces two primary limitations: first, perceiving the image only at a global scale restricts the assessment of finer local details; second, the original intensity distribution of the image may overwhelm the visibility, leading to insufficient inspection of image quality. To address these issues, we propose Tool-IQA, shifting the assessment mechanism from passive scoring to a tool-augmented workflow. In particular, we equip VLMs with simple yet effective view tools: a Magnifier to inspect local details, and a Gamma Corrector to uncover visibility and hidden artifacts. The assessment follows a structured pipeline that consists of an initial observation with rubric notes, a tool-augmented in-depth inspection, and a final quantification for calibrated quality score. Furthermore, to ensure efficient and purposeful tool callings, we introduce a batch-aware training strategy to reward tool interactions that can yield positive contributions rather than simply encouraging usage. Experiments on a variety of IQA benchmarks demonstrate that, with effective tool calling and calibrated assessment, our proposed Tool-IQA significantly outperforms existing state-of-the-art models, e.g., it achieves a PLCC of 0.854 on the challenging CLIVE dataset.
Read the full abstract

All authors Guanyi Qin, Junjie Zhang, Chunming He, Yibing Fu, Jie Liang, Tianhe Wu, Lei Zhang

Artificial Intelligence · Cross-listed from cs.LG

Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting

Weizhi Nie, Weichao Liu, Honglin Guo et al. (+1 more)

Multivariate forecasting in physical systems requires models that predict coupled temporal variables while preserving meaningful state evolution. Deep forecasters can fit temporal correlations, and physics-informed models can regularize predictions with scientific constraints, but these directions are often connected only at the decoded-output level. As a result, the hidden predictive state that generates future trajectories may remain statistically useful but physically unstructured. We introduce Phys-JEPA, a physics-informed joint-embedding predictive architecture for multivariate time-series forecasting. Phys-JEPA learns a latent world model in which predictive states are decomposed into physical and residual components, and physical consistency is imposed directly on latent states and latent transitions rather than only on decoded forecasts. This formulation uses known physical variables to organize the representation space while retaining residual capacity for unresolved dynamics. On Jena Climate 2009–2016, Phys-JEPA reduces aggregate MSE from 0.12482 to 0.12273 and temperature MSE from 0.01892 to 0.01831 at H=24. On Traffic, full Phys-JEPA improves aggregate MSE over the supervised baseline across all tested horizons, reducing H=192 MSE from 0.800784 to 0.773873. On Electricity, the best variant depends on horizon: static latent consistency is strongest at H=24 and H=48, while full Phys-JEPA gives the best aggregate and target-variable MSE at H=192. These initial results suggest that moving physics-informed learning from output space to latent predictive state space is a promising direction for interpretable temporal world models.
Read the full abstract

All authors Weizhi Nie, Weichao Liu, Honglin Guo, Yuting Su

Artificial Intelligence · Cross-listed from cs.CL

PVminerLLM2: Improving Structured Extraction of Patient Voice via Preference Optimization

Samah Fodeh, Linhai Ma, Ganesh Puthiaraju et al. (+7 more)

Motivation: Patient-generated text contains critical information on patients' lived experiences, social context, and care engagement, but remains largely unstructured, limiting its use in patient-centered outcomes research. Prior work introduced the PV-Miner benchmark and PVMinerLLM models for structured extraction. However, supervised fine-tuning (SFT) alone struggles with rare, fine-grained, and unevenly distributed errors, particularly in token-critical structured outputs. Results: We present PVminerLLM2, an improved set of LLMs for structured patient voice extraction that applies preference optimization to address token-critical errors beyond the reach of supervised fine-tuning. Our method introduces (i) a preference objective with token-level gated stabilization term that prevents degradation of absolute token likelihood under preference optimization, and (ii) confusion-aware preference pair construction to better capture low-separation distinctions. We further incorporate token-importance weighting and inverse-frequency reweighing to address token imbalance and class skew. Across multiple model sizes, PVMinerLLM2 consistently outperforms strong baselines, achieving gains of up to 4.43% (Code), 3.50% (Sub-code), and 1.55% (Span), and outperforms baseline LLM trained with existing preference optimization methods. Availability and Implementation: The supplementary material, code, evaluation scripts, and trained models for PVminerLLM2 are publicly available at: https://github.com/Data-Mining-Lab-Yale/PVminerLLM2
Read the full abstract

All authors Samah Fodeh, Linhai Ma, Ganesh Puthiaraju, Srivani Talakokkul, Afshan Khan, Elyas Irankhah, Sreeraj Ramachandran, Ashley Hagaman, Sarah Lowe, Aimee Roundtree

Artificial Intelligence · Cross-listed from cs.CR

MASCOT-Android: A Curated Dataset and Automated Collection Pipeline for Android Malware Source Code Specimens

Bojing Li, Duo Zhong, Prajna Bhandary et al. (+4 more)

Compared with binaries and decompiled code, malware source code more directly reflects the attackers' original intent. However, the scarcity of source code and the high cost of manual review make such datasets difficult to build and maintain. We propose MASCOT-Android, a curated dataset of Android malware source code and an automated collection framework for scalable malware source code discovery on GitHub. A key finding of our work is that repository-level documentation alone provides a strong signal for malware source code collection. Our model extracts character-level TF-IDF features from 8,772 malware and 25,747 benign README documents and trains a LinearSVC classifier to distinguish malware repositories. This README-only model achieves an accuracy of 96.28% and an FPR of 1.06% in local evaluation. In addition, the model outputs confidence scores, allowing users to adjust the decision threshold to balance FPR and coverage, which is practical in real-world malware source code collection.
Read the full abstract

All authors Bojing Li, Duo Zhong, Prajna Bhandary, Raguvir S, Charles Maxa, Robert J Joyce, Charles Nicholas

Sunday 14 June

Artificial Intelligence · Cross-listed from cs.CL

When Vocabulary Comprehension Fails Clinical Reasoning: Evaluating Therapy Bots' Safety Risks for Generation Alpha

Manisha Mehta and Virendra Mehta

Conversational AI systems have become informal mental health support resources for Generation Alpha (Gen Alpha, born 2010-2024), with 13.1% of U.S. adolescents (5.4 million) using generative AI for mental health advice. While these systems, from therapy apps to general chatbots, rely on large language models trained on extensive psychological literature, their safety for youth communication patterns characterized by hyperbolic language, ironic positivity, rapid semantic drift, and contextual polysemy remains unvalidated. Following multiple adolescent deaths linked to AI chatbot interactions, systematic evaluation is critical. We present two benchmarks: (1) 64 Gen Alpha mental health expressions validated by native speakers (ICC=0.72) and clinicians (kappa=0.78); (2) 75 multi-turn conversations (780 turns) with paired Standard/Gen Alpha versions. Across evaluations of LLM architectures underlying therapy apps and general chatbots - Claude, GPT-4o, Llama-3.1 - models understand 76-82% of vocabulary but correctly calibrate only 64-72% of clinical risk, creating a 10-14 percentage point (pp) vocabulary-comprehension gap (p<.001, d>0.48) absent in human therapists (3pp, p=.22). The gap is architecturally consistent and widens with ambiguity (7pp -> 18pp). We identify six failure patterns: sarcasm masking (29pp), minimization acceptance (43pp), informal style bias (24pp), risk-stratified ambiguity (19pp), semantic drift (19pp), context-dependent violence (7pp). Patterns compound; three or more yield 94% miss rates. Lightweight mitigations fail; only heavy scaffolding achieves human performance (6.4x cost). With 34% baseline miss rate yielding 146,880 estimated annual missed crises, we recommend mandatory human-in-the-loop architectures, quarterly youth-specific validation, transparent performance disclosure, and regulatory frameworks for youth-facing mental health AI.
Read the full abstract

Artificial Intelligence

Decentralized Granular Access Control for Agentic AI Systems in Critical Infrastructure

Arun Malik, Deepal Jayasinghe, Bradley Klemick et al. (+3 more)

The deployment of autonomous AI agents in production infrastructure introduces fundamental security challenges that traditional role-based access control (RBAC) models cannot address. Unlike deterministic automation, AI agents exhibit stochastic behavior, making conventional trust models insufficient for governing their access to critical systems. This paper presents a decentralized, multi-layered access control architecture designed specifically for agentic AI systems operating in critical cloud infrastructure. Our framework introduces four key innovations: (1) a compound identity model that binds agent actions to delegated human authority, (2) a hierarchical permission system spanning five granularity levels from global platform access to per-parameter constraints, (3) a decentralized policy ownership model where tool teams independently govern their authorization boundaries, and (4) progressive trust escalation with safety interlocks that prevent autonomous agents from executing high-risk operations. We ground our design in the OWASP Top 10 for LLM Applications (2025) threat taxonomy and demonstrate how each architectural decision mitigates specific attack vectors. Deployed in production at a major cloud provider managing network infrastructure across hundreds of datacenters, the system enforces granular access control for 20+ specialized AI agents and 60+ deterministic playbooks processing thousands of operations daily while maintaining zero unauthorized write operations over eight months of production deployment. We present empirical data on access pattern distributions, denial rates, and the effectiveness of layered authorization in preventing privilege escalation by non-deterministic actors.
Read the full abstract

All authors Arun Malik, Deepal Jayasinghe, Bradley Klemick, Prachi Shah, Nitish Talasu, Vineet Tushar Trivedi

Artificial Intelligence

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

Jessica Tang, Shraddha Barke and Sharad Agarwal

When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies propagate across prior turns? Existing context attribution methods process the full context in a single pass, recovering surface-level dependencies but missing the layered, non-linear structure of real-world dialogues and multi-step reasoning tasks. We introduce multi-turn context attribution (MTCA): given a target span in a model response, the task of tracing attribution backward across turns to identify not only which prior turns were directly relevant, but also how those turns themselves depended on earlier context. We propose Tokengeist, an attribution-method-agnostic and scalable framework that recovers full dependency paths by casting attribution as a recursive traversal of a directed acyclic graph (DAG) over conversation turns. We will release MTCABench, a benchmark of 3,845 target spans across 665 multi-turn conversations, annotated with gold provenance graphs reaching depths of up to 14, across four dependency types. Across four open-weight models, flat attribution methods fail to recover multi-hop dependencies, achieving under 20% source recall, while Tokengeist reaches 90%. Our results reveal systematic failure modes of single-pass attribution – which we term provenance collapse – and motivate attribution methods that reason recursively across turns.
Read the full abstract

Artificial Intelligence

Evaluating LLMs as Interpretable Controllers for Dynamical Systems

Aleksander Østensen, Alberto Mino Calero, Anastasios M. Lekkas et al. (+1 more)

Large Language Models (LLMs) are increasingly used for decision-making and reasoning tasks, yet their potential as controllers for physical systems remains largely unexplored. This work investigates whether LLMs can function as interpretable controllers for a dynamic thermal environment, examining their ability to follow setpoints, interpret natural-language commands, reason about actuator effects, and incorporate prior model-based knowledge. Five LLMs of varying scales are evaluated under multiple scenarios, including settings with penalties on heater or fan usage and cases where the models have access to a physics-based prediction tool. The results show that control performance depends on model complexity: while low- and mid-scale models frequently misinterpret actuator dynamics or generate inconsistent reasoning, high-complexity models such as Qwen-3~14B and GPT-4o achieve accurate temperature tracking, stable actuator usage, and coherent explanations aligned with physical principles. Incorporating a physics-based model significantly improves control smoothness and energy efficiency by enabling anticipatory decision-making. A detailed reasoning taxonomy further reveals a clear progression from causal misinterpretation in smaller models to cohesive and temporally aware reasoning in larger ones. The findings demonstrate that LLMs can act as interpretable controllers when sufficiently capable and appropriately grounded in domain knowledge, highlighting promising opportunities for hybrid model-based and language-driven control strategies that can provide plausible explanations.
Read the full abstract

All authors Aleksander Østensen, Alberto Mino Calero, Anastasios M. Lekkas, Adil Rasheed

Artificial Intelligence

Workload-Aware Caching for Multi-Agent Systems

Anas Mohamed, Kaizan Haque, Azal Ahmad Khan et al. (+3 more)

Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries. However, existing cache eviction policies treat all cached entries uniformly based on access history, ignoring structural and workload signals uniquely available in agentic execution environments. We present a workload-aware eviction policy that combines three signals, namely recomputation cost, DAG dependency count, and agent invocation frequency, into a unified scoring function that retains the most valuable entries under memory constraints. Evaluated across three multi-agent benchmarks spanning diverse reuse regimes, our policy reduces latency by up to 64.7% relative to the uncached baseline and achieves on average a 31.1% latency reduction over the next best finite-capacity baseline, while approaching the performance of an unbounded cache and maintaining accuracy on par with or exceeding all competing finite-capacity methods. We further show that workload-aware content caching is complementary to other agentic system optimization methods, including plan-level caching and parallel agent execution, with each technique targeting a distinct efficiency bottleneck in multi-agent pipelines.
Read the full abstract

All authors Anas Mohamed, Kaizan Haque, Azal Ahmad Khan, Chetan Sharma, Shuwen Ge, Ali Anwar

Artificial Intelligence · Cross-listed from cs.LG

Ablation, Statistical Inference, and Validation for KV-Cache Compression

Paolo D'Alberto, Ashish Siarasao, Elliott Delaye et al. (+1 more)

This study systematically compares Turbo-Quant and SpectralQuant KV-cache compression, evaluating non-dominated schemes, including WHT rotation with Beta Lloyd-Max and QJL, through a statistical validation methodology that separates systematic codec differences from implementation variance. Key findings reveal that while eigenbasis-based methods fail on heavy-tailed data due to covariance instability, they excel in structured regimes, with the effective semantic dimension ($d_{eff}$) adapting to calibration budgets rather than true data rank. (this is an abstract of the abstract thank you )
Read the full abstract

All authors Paolo D'Alberto, Ashish Siarasao, Elliott Delaye, Rajeev Patwari

Artificial Intelligence · Cross-listed from cs.IR

Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?

Sadanand Singh, Allam Reddy and Manan Chopra

Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval. The benefits reported for these methods come almost exclusively from homogeneous corpora, predominantly Wikipedia prose. Whether they hold on the mixed-format collections common in practice, where code, markdown, tables, scientific PDFs, and prose are interleaved within one corpus, has not been measured. To study this directly, we build HetDocQA, a heterogeneous benchmark with chunker-agnostic span-overlap relevance labels and collection-disjoint splits, and pair it with MuSiQue and QASPER as homogeneous controls. We evaluate eight methods on a shared backbone, with bootstrap confidence intervals and multiple-comparison correction. A strong cross-encoder reranker accounts for most of the pipeline's quality; beyond it, only two methods yield reliable gains: query expansion and SSCC. SSCC, a per-source calibrated corrector introduced here, sets a separate acceptance threshold for each score source and helps only on heterogeneous data. The remaining reranking and pool-expansion methods in common use, among them hierarchical summarization, graph expansion, routing, and rank fusion, give no reliable gain once that reranker is present.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.IR

CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval

Adnan Qidwai, Anand Eswaran, Sonam Mishra et al. (+2 more)

RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.g., synthetic queries or summaries generated from corpus chunks) that are subsequently queried alongside the base index to improve retrieval via better alignment between document representations and user intent. While these supplementary representations substantially improve retrieval quality, they introduce a computational bottleneck: the configuration space of enrichment types and generator models is combinatorial, and the cost of exhaustive index-time evaluation scales linearly with corpus size. We introduce CAMI (Cost-Aware Multi-Indexing), a framework that formalizes multi-index construction as a budgeted, multi-objective portfolio selection problem. CAMI targets the upstream decision of which enrichment views to generate and materialize before the retrieval backend is applied. CAMI incorporates three primary mechanisms: (i) an agentic discovery phase that proposes corpus-specific representation templates; (ii) an atomic-unit search procedure that evaluates individual enrichment-model pairs and recombines them via fidelity-local closure to identify synergistic portfolios; and (iii) a confidence-aware promotion schedule that prunes unpromising configurations early, decoupling optimization spend from total corpus size. We evaluate CAMI across diverse retrieval corpora. Our findings reveal that the framework systematically isolates high-recall portfolios under strict budget constraints, outperforming standard content-only baselines in challenging settings by up to 9.4% recall@10. Further, CAMI is able to systematically identify these high-recall portfolios using up to 5x less budget compared to random search baselines, making our approach practical in real production scenarios.
Read the full abstract

All authors Adnan Qidwai, Anand Eswaran, Sonam Mishra, Jaydeep Sen, Sachindra Joshi

Artificial Intelligence · Cross-listed from cs.CL

Specific Domain Ontology Construction Using Large Language Models

Vivian Magri Alcaldi Soares and Renata Wassermann

Ontologies are useful structures to organize and maintain information that can be understood both by humans and systems. However, since their manual crafting is a laborious task, many specific domains lack reference ontologies. The outstanding ability for understanding natural language demonstrated by the Large Language Models (LLMs) has motivated their application to aid on a variety of fields, including on ontology development. This work presents the experimentation with a technique that uses LLMs in the role of domain experts to build conceptual hierarchies for a given initial concept. Twenty ontologies automatically constructed for the domain of the Brazilian maritime territory (a.k.a the Blue Amazon) using GPT-3.5 and GPT-4 were then evaluated by human experts. The models were able to construct overall coherent conceptualizations of the domain, but none of the outputs was completely satisfactory as a representation of the context without refinement.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.RO

JPPD: Joint Prediction_Planning Diffusion with Differentiable Safety Guidance for Dynamic Obstacle Avoidance in Intelligent Transportation Systems

Jiahao Wu and Shengwen Yu

Shared-space transportation operation requires low-speed autonomous platforms to navigate safely and efficiently among pedestrians, service robots, micromobility users, carts, and other road users. Most existing systems decompose this problem into trajectory prediction followed by motion planning, which creates one-way information flow: predicted participant futures influence the robot plan, but the selected robot plan cannot influence the predicted multi-agent evolution. This paper presents a joint prediction-planning diffusion framework that treats participant prediction and robot planning as a single conditional trajectory generation problem, where the model samples the future robot trajectory and all participant trajectories from one coupled distribution using a causal Transformer with cross-trajectory attention. To replace heuristic repulsive post-processing, the framework introduces differentiable safety potential guidance, a time-varying occupancy-probability potential whose gradient directly guides the joint sampler, and conditional flow matching is used to reduce inference steps while preserving multimodal trajectory diversity. The evaluation emphasizes shared-space operational effects, including near misses, blockage time, induced participant deviation, hard-braking events, and embedded latency, rather than treating average displacement error and final displacement error as the main result. Experiments in scenario-grounded simulation, naturalistic pedestrian replay, Isaac Sim validation, and ROS/Orin deployment show that joint sampling improves tail safety and runtime efficiency over a separated prediction-then-planning baseline.
Read the full abstract

Artificial Intelligence

From Question Answering to Task Completion: A Survey on Agent System and Harness Design

Jianyuan Guo, Zhiwei Hao, Chengcheng Wang et al. (+14 more)

LLM-based agents mark a shift from passive question answering to active task completion: they perceive environments, invoke tools, maintain state, and act over extended horizons. As agent systems have evolved from prompt engineering to workflows and context engineering, harness engineering, and agent-native training with co-evolution, a central question has become increasingly important: where does the bottleneck in agent performance reside, in the foundation model, in the execution harness, or in the coupling between them? This survey examines LLM-based agents through a model-harness lens. We first clarify the functional definition of agents and the implementation view of an LLM-based agent as a foundation model coupled with an execution harness. We then analyze the limits of model-centric scaling, trace four paradigms of agent engineering, and decompose the execution harness into six coupled runtime responsibilities: observation, context, control, action, state, and verification. Using this decomposition, we map task properties and domain pressures to harness configurations, review benchmark and evaluation practices, and synthesize model-harness evidence on how runtime design affects long-horizon task completion, efficiency, and reliability. Finally, we identify open challenges in value-aware evaluation, safety, harness generalization, and model-harness co-evolution. Rather than treating agents as models with auxiliary tools, this survey argues that agent quality – including success, efficiency, safety, and generalization – emerges from the interaction between model capability, runtime infrastructure, task structure, and evaluation design. A collection of papers discussed in this survey is provided in https://github.com/ggjy/Awesome-Agent-Engineering.
Read the full abstract

All authors Jianyuan Guo, Zhiwei Hao, Chengcheng Wang, Cheng Fan, Tingzhang Luo, Hongguang Li, Ying Gao, Hefei Mei, Jiankun Peng, Rongjian Xu, Minjing Dong, Han Wu, Mengyu Zheng, Kai Han, Shiqi Wang, Chang Xu, Yunhe Wang

Artificial Intelligence · Cross-listed from cs.SE

DynAMO:Dynamic Asset Management Orchestration via Topological Multi-Agent Scheduling

Kanishk Kushwaha, Vikrant Vinod Bansode, Harsh Vardhan et al. (+1 more)

While LLM-powered agents offer end-to-end automation for industrial asset lifecycles, real-world Industry 4.0 deployment is hindered by latency, concurrency instability, and safety risks. We present DynAMO (Dynamic Asset Management Orchestration), a deployment-ready engine using a Plan-then-Execute architecture to generate verifiable workflow graphs. DynAMO supports both SequentialWorkflow (topological execution) and ParallelWorkflow (dependency-aware concurrency). By dynamically identifying independent tasks, DynAMO preserves structural correctness and safety while significantly improving efficiency through controlled reasoning overlap. Across six controlled experiments on the AssetOpsBench industrial benchmark, DynAMO demonstrates substantial performance and robustness gains. Parallel execution reduces end-to-end latency by a median of 1.6x over sequential orchestration, rising to 1.8x on highly parallelizable workflows. After instrumenting external tool calls with realistic latencies, a latency decomposition shows that LLM reasoning and orchestration still account for more than 90% of execution time, identifying model inference as the primary system bottleneck. Structured context pruning reduces inference latency by approximately 30%, and DynAMO maintains correct functional behaviour (task completion, agent sequencing, and output quality) while exhibiting graceful degradation under controlled fault injection. Reproducibility analysis further confirms stable execution under repeated runs, with parallel scheduling reducing latency variance. These findings establish DynAMO as a practical blueprint for scalable, safe, and latency-aware agent deployment in Industry 4.0 automation pipelines. Code is available at: https://github.com/kushwaha001/DynAMO
Read the full abstract

All authors Kanishk Kushwaha, Vikrant Vinod Bansode, Harsh Vardhan, Dhaval C. Patel

Artificial Intelligence · Cross-listed from cs.SD

Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech

Yue Heng Yeo, Haoyang Li, Yizhou Peng et al. (+6 more)

Code-switch (CS) Automatic Speech Recognition (ASR) remains challenging due to limited availability of high quality CS text-speech pairs for training. Although synthetic data augmentation via Text-to-speech (TTS) has been explored, existing CS TTS approaches primarily optimise reconstruction fidelity and do not explicitly enforce language-boundary consistency, thereby limiting their effectiveness for CS ASR augmentation. This paper proposes a code-mixing guided preference-learning framework that steers synthetic speech generation toward improved code-switching fidelity using the Code Mixing Index (CMI). Experiments on the SEAME Mandarin-English conversational corpus demonstrate that the proposed method enhances the utility of synthetic data for ASR fine-tuning. Specifically, when fine-tuning Whisper Large, the proposed approach reduces Mixed Error Rate (MER) from 12.1%/17.8% to 8.9%/14.2% on the DevMAN and DevSGE sets, respectively.
Read the full abstract

All authors Yue Heng Yeo, Haoyang Li, Yizhou Peng, Shreyas Gopal, Hexin Liu, Leibny Paola Garcia-Perera, Hardik B. Sailor, Jeremy H. M. Wong, Eng Siong Chng

Artificial Intelligence · Cross-listed from cs.LG

Models Take Notes at Prefill: KV Cache Can Be Editable and Composable

Bojie Li

Prefix caching reuses prefill only across an exactly shared prefix, so one changed field invalidates the entire downstream cache. Yet overwriting the field's own key/value vectors and reusing the rest leaves the model acting on the old value. The reason, established causally across four model families: at prefill the model has already written the field-conditioned conclusion onto downstream notes; the field's own key/value drives under 1% of the decision. Read as a notebook of memoized conclusions, two capabilities follow. (1) It is editable. A salient erratum amends the notes; and with chain-of-thought, editing the field alone recovers the decision (1.00 at 8B, ~1% compute), while without CoT it is ignored. (2) It is composable. The notes are position-portable, so a precompiled skill can be RoPE-repositioned and spliced into any context, indistinguishable from full recompute (logit cosine 0.90-0.999, twelve models) at O(L) rather than O(L^2) time-to-first-token. A unified edit+compose agent stays decision-identical to recompute at up to 14.9x lower latency. The approach applies to any per-token attention KV cache, validated across scale, quantization, Mixture-of-Experts, and multimodal caches, and extends to several attention variants through small adapters. Because the erratum is append-only, it composes with production prefix caching: in an online vLLM benchmark it keeps the prefix cache-aligned (98.5% hit-rate), cutting p90 time-to-first-token by 53-398x.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.AR

Prefill/Decode-Aware Evaluation of LLM Inference on Emerging AI Accelerators

Shun Usami, Venkatram Vishwanath and E. Wes Bethel

As large language models (LLMs) are increasingly deployed in latency- and cost-sensitive settings, inference efficiency has become a central systems challenge. While GPUs dominate current deployments, a growing number of AI accelerators claim advantages for LLM inference, yet it remains unclear under which conditions such accelerators outperform GPUs in practice. Recent inference systems decompose execution into Prefill and Decode phases, which exhibit distinct computational characteristics and latency metrics, commonly captured by time to first token (TTFT) and time per output token (TPOT). This paper presents a phase-aware evaluation of LLM inference performance across GPUs and emerging AI accelerators using a common model, Llama2-7B. By separately measuring Prefill and Decode performance, we reveal that accelerator advantages differ by phase and metric. Our results show that GPUs consistently excel in the compute-intensive Prefill phase, while GroqRack achieves significantly lower TPOT during Decode (batching not currently supported). However, GPUs regain an advantage in Decode throughput as batch size increases. These findings demonstrate that each platform exhibits distinct phase-dependent strengths. We further analyze heterogeneous Prefill/Decode disaggregation across different accelerator platforms, identifying performance gains and the workload and network conditions under which such gains are realized.
Read the full abstract

Artificial Intelligence · Cross-listed from physics.pop-ph

Quantum Cinema: An Interactive Cinematic Exploration of Quantum Computing Hardware via Generative World Models

Aoyu Zhang, Dongping Liu and Luyao Zhang

Quantum computing promises transformative advances across science and industry, yet the physical hardware that enables these computations remains invisible to the public: quantum processors operate inside sealed dilution refrigerators at temperatures near absolute zero, making direct observation impossible. This "imagination gap" between quantum computing's growing societal impact and the public's ability to visualize it represents a significant barrier to quantum literacy and workforce development. We present Quantum Cinema, an open-source, browser-based interactive application that closes this gap by transforming invisible quantum hardware into explorable, cinematic experiences using generative world models. Quantum Cinema guides users through a four-act narrative – from the foundational Nobel Prize-winning science of quantum entanglement, through curated video introductions to three major quantum computing architectures (trapped-ion, neutral-atom, and superconducting systems), into immersive three-dimensional generative worlds that make invisible quantum phenomena observable, and finally to interactive radar-chart comparisons grounded in real quantum device specifications. All three-dimensional environments are generated using WorldLabs' generative world model platform and are scientifically grounded in curated metrics from Amazon Web Services (AWS) Braket quantum hardware. Quantum Cinema requires no installation, no specialized hardware, and no quantum computing background. It is designed to serve two distinct communities: scholars and developers seeking to replicate or extend the platform, and educators, researchers, and science communicators seeking an intuitive tool for explaining quantum hardware to diverse audiences. This paper describes the system architecture, the generative world model pipeline, use cases for both communities, and directions for future work.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.SE

Software Delegation Contracts: Measuring Reviewability in AI Coding-Agent Work

Vincent Schmalbach

AI coding agents increasingly accept assigned software tasks, modify repositories under bounded authority, and return work packages for review. Prior work proposed the software delegation contract, covering the task, authority, returned work package, and acceptance context, as the unit of analysis for delegated coding work, but did not measure its effects. This paper reports a controlled pilot study of explicit delegation contracts for coding agents. We built a dependency-free TypeScript API task environment with seeded defects and documentation gaps, authored ten tasks across five families, and ran 64 agent executions across two model tiers under three conditions: a realistic issue-style prompt, an explicit delegation contract, and a contract with a required evidence bundle. Each run was scored with hidden acceptance tests, mutation checks, and scope analysis, then reviewed by three independent condition-blinded model-based reviewers using a fixed rubric, for 192 reviews. Explicit contracts did not improve objective task outcomes: all 64 runs passed hidden acceptance checks, with zero scope violations. They did improve reviewability. Evidence sufficiency improved in 22 of 30 paired comparisons and worsened in none (+0.83 on a 5-point scale, p < 0.0001, Cliff's delta = 0.66); reviewer ambiguity decreased (p = 0.035); changed-file lists, known-limitations sections, residual-risk sections, and reviewer checklists appeared mostly or only when demanded by the contract. Contracts cost +13% agent tokens and +38% wall-clock time, with larger effects for the weaker model tier. On these small tasks, delegation contracts bought reviewability rather than correctness.
Read the full abstract

Artificial Intelligence

Mind-Studio: Executable World Models with Lookahead Evaluation for Partially Observable Games

Yifei Dong, Mingen Zheng, Linquan Wu et al. (+2 more)

World-model synthesis aims to turn interaction experience into an internal model of environment dynamics. Existing symbolic approaches often fit observed transitions or mixtures of local rules, but they do not produce a complete executable program that can run independently of the real environment. We present Mind-Studio, a framework that synthesizes executable pygame-style world models from state-action-next-state trajectories using large language models. Mind-Studio combines entropy-selected traces with a lightweight game skill file containing object, action, and static scene information extracted from screenshots. We evaluate synthesis quality with a K-step lookahead fidelity protocol that compares generated world-model rollouts against Real-ALE rollouts from the same state. On Montezuma's Revenge, Mind-Studio improves chosen-action next-state prediction from 0.3% for PoE-World to 48.7% while verifying 5 of 8 subgoals; across Alien, Assault, and Skiing, it achieves stronger branch-level fidelity than prior learned lookahead sources.
Read the full abstract

All authors Yifei Dong, Mingen Zheng, Linquan Wu, Jeff Z. Pan, Jiaxin Bai