Peer Revenue Equity in science

Papers

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

Computer Science Artificial Intelligence

cs.AI Watch Artificial Intelligence

Friday 21 August

Artificial Intelligence

Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI

Ashita Ashok, Franziska Babel, Patrick Holthaus et al. (+7 more)

Large language models (LLMs) are increasingly used for verbal interaction in social robots, yet prompt design in human-robot interaction (HRI) remains underspecified. As a result, robots may present hallucinated capabilities, unclear behavioural boundaries, and misleading personas. This paper develops a framework for prompt design in LLM-based robots and introduces a structured prompt template comprising eight functional components through which robot behaviour can be specified, bounded, and adapted. The framework is grounded in a review of prior LLM-based HRI work and complemented by survey and discussion data from HRI experts gathered at the Robo-Identity workshop at IEEE RO-MAN 2025 (N=27). The qualitative findings highlight limited legibility of robot personality, the need for user adaptation, and strong ethical concerns about safety, deception, and governance. Based on these findings, we present prompting guidelines accompanied by proof-of-concept template as a structured design and reporting aid for HRI research. We argue that prompt design should be treated as a socio-technical problem rather than a minor implementation detail, requiring explicit capability boundaries, transparent behavioural assumptions, and context-sensitive safeguards to support reliable and interpretable HRI.
Read the full abstract

All authors Ashita Ashok, Franziska Babel, Patrick Holthaus, Rucha Khot, Karla Bransky, Fethiye Irmak Dogan, Karsten Berns, Silvia Rossi, Minha Lee, Guy Laban

Artificial Intelligence · Cross-listed from cs.SE

REFINE: A Multi-Agent LLM Approach for Evidence-Guided Code Refactoring

Muhammad Waseem, Aakash Ahmad and Pekka Abrahamsson

Large Language Models (LLMs) offer new opportunities for automated code refactoring. However, generated changes must reduce targeted quality problems without introducing new issues or altering behaviour-relevant code structures. We introduce REFINE (Refactoring with Evidence-aware Flow for Integrated ageNtic Execution), a tool-agnostic, evidence-aware multi-agent approach for generating Java file-level refactoring candidates. REFINE combines static-analysis-guided smell identification, smell-informed planning, LLM-based transformation, automated re-analysis, preservation checks, and structured reporting. We evaluate REFINE on 450 Java files from 15 open-source systems, producing 1,350 model-pass outputs using OpenAI GPT-5.5, Google Gemini 3.1 Pro Preview, and Anthropic Claude Opus 4.8. REFINE reduces detected code smells by 68.26%, 72.79%, and 68.49% across the three configurations, respectively, with the strongest reductions observed for major smells. A matched 150-file direct-prompt baseline shows that REFINE achieves a higher median code-smell reduction with smaller edits and fewer public-method removals. However, broader quality improvements are inconsistent, and preservation checks reveal residual risks, including assert/fail-call changes and public-method removal. Therefore, REFINE outputs should be treated as refactoring candidates requiring compilation, testing, dependency analysis, and human review before adoption in repository- or system-level settings.
Read the full abstract

Artificial Intelligence

Context as an Environment: Programmatic Context Management for Long-Horizon Agents

Yin Lin, Elaine Ang, Erkang Zhu et al. (+2 more)

LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory representations, committing to what to preserve before future needs are known. We present Scroll, a context manager that treats each agent session as an executable Session Environment. The environment is backed by an append-only Event Log and a sandboxed, persistent Python kernel. The kernel maintains a typed namespace across model calls, allowing tool outputs, retrieved history, and derived state to be bound to variables rather than serialized into the prompt at each call. Model-written code searches, materializes, and transforms session state through exec; only explicitly printed projections enter the model's working view for the next call. Context management thus becomes a programming task that inherits the improving coding abilities of LLMs, while the Event Log preserves lossless historical ground truth. As the working view approaches its budget, stale spans are evicted but remain recoverable: an eviction index keeps compact landmarks tied to exact Event Log addresses, so that the agent navigates directly to evicted regions instead of searching the full log. With Qwen3.8-Max as the backbone, Scroll achieves 94.8% on LongMemEval_S; 73.1% on BEAM_10M, surpassing the best published memory system by 5.1 points; and 86.7% on LOCA_256K, exceeding the best published long-horizon agent by 37.4 points.
Read the full abstract

All authors Yin Lin, Elaine Ang, Erkang Zhu, Bolin Ding, Jingren Zhou

Artificial Intelligence · Cross-listed from cs.LG

Read, Write, Relax: Why Neural PDE Surrogates Need Both Global and Local Processing

Anuj Kumar, Heiko Zimmermann, Josiah Bjorgaard et al. (+4 more)

Recent mesh-based simulation advances have, in no small part, relied on neural surrogates of two distinct families: global models that route information through a small set of latent tokens, and local models that perform message passing across mesh edges. Consistent with both classes is the inability to perform beyond low-dimensional problems and small-scale or oversimplified meshes, the simulation regimes where industrial problems reside. Our work shows this explicitly and presents a unified formulation. In global approaches, latent-token attention acts as a spatial low-pass filter, while local message passing lacks the global reach necessary to propagate information across large mesh spaces. Viewed through the error, the two operators are the halves of a multigrid cycle: one corrects errors at the lower end of the spectrum, the other at the higher end, and neither can do the other's job. We introduce Read-Write-Relax (RWR), which interleaves latent attention with message-passing relaxation under a unified formulation. The interleaved processor lowers error across the entire spectrum, making RWR the most accurate model in nearly every comparison across our industrial and public benchmarks. It is also markedly data-efficient in the scarce-data regimes, accurate on the engineering quantities of interest, and scales full-field predictions to challenging, large-scale problems.
Read the full abstract

All authors Anuj Kumar, Heiko Zimmermann, Josiah Bjorgaard, Jacan Chaplais, Nikolaos Bouklas, Matteo Salvador, Alexander Lavin

Artificial Intelligence · Cross-listed from cs.LG

SynEHR: Joint Modeling Inter-visit Temporal Evolution and Intra-visit Clinical Structure for Longitudinal EHR Synthesis

Ximiao Li, Lin Jiang, Rongchao Xu et al. (+3 more)

Longitudinal electronic health records (EHRs) document patients' sequences of clinical visits over time, preserving the temporal evolution of disease progression and care delivery. However, real longitudinal EHRs are difficult to access because they contain large amounts of fine-grained, patient-specific information. Synthetic EHR generation therefore provides a valuable approach for preserving the statistical patterns and clinical structure of patient visit trajectories, enabling broader modeling and analysis when real records are limited. Although recent generative models have made progress in producing future visit sequences, they remain limited in explicitly integrating inter-visit irregular temporal evolution and intra-visit clinical event structures in EHRs, leading to clinically inconsistent and temporally unrealistic visit sequences. In this work, we propose SynEHR, a lightweight adaptive LLM-based framework for longitudinal EHR synthesis. There are two novel designs in SynEHR, i.e., a Temporal State Conditioning Module captures irregular temporal states across visits and a Temporal-Relational Adaptation Module combines these states with patient history to dynamically construct patient-specific relational representations. SynEHR then builds on a parameter-efficient LoRA-adapted language-model generator with next-visit generation capability to train the two modules for temporally and clinically informed generation. Extensive experiments on real-world EHR datasets across fidelity, privacy, and downstream utility evaluations demonstrate that SynEHR outperforms state-of-the-art models by generating more clinically coherent and temporally faithful longitudinal EHR data.
Read the full abstract

All authors Ximiao Li, Lin Jiang, Rongchao Xu, Dahai Yu, Zhe He, Guang Wang

Artificial Intelligence

From Mastery Profile to Simulated Response: Stochastic Student Knowledge Graphs (SSKG) for Faithful LLM Student Simulation

Yuan An, Emily Wang, Benjamin Wang et al. (+1 more)

Large language models (LLMs) are increasingly used to simulate students at different mastery levels to generate synthetic training data and stress-test tutoring systems. Existing approaches primarily leverage an LLM to answer questions or perform tests while instructing it to simulate various skill levels. However, LLMs tend to execute at their full built-in capability regardless of target skill levels. We demonstrate this limitation on SAT questions across five mastery levels, where three LLMs consistently achieve 96.8-100% accuracy. To faithfully simulate student behavior, we propose a Stochastic Student Knowledge Graph (SSKG)-based approach that leverages the strengths of LLM in different ways. Using human-in-the-loop workflows, LLMs extract a Curriculum Knowledge Graph (CKG) from course materials, decompose solution paths into CKG triples, and map incorrect distractors. A student's mastery profile is represented as an SSKG, assigning mastery probabilities to CKG triples. When solving a problem, the SSKG is sampled to determine the outcome, after which an LLM generates a rationale consistent with the sampled result. Compared to seven baselines which fail to separate profiles and maintain 86.5-100% accuracy, our SSKG-based approach achieves 44.1-85.2% accuracy from low to high-mastery profiles, creating a clear monotonic gradient. An ablation study demonstrates that taxonomy awareness contributes most significantly to these fidelity gains, particularly for lower-mastery profiles.
Read the full abstract

All authors Yuan An, Emily Wang, Benjamin Wang, Ruhma Hashmi

Artificial Intelligence

Measuring Activation Control in Large Language Models

Marek Mateusz Kowalski, Joshua Fonseca Rivera, Uzay Macar et al. (+1 more)

Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especially when evaluation-aware models exhibit scheming or deception. However, if models can also control their own activations, deception could extend into the latent space itself. With this in mind, we introduce the Activation Controllability Benchmark to quantify the extent to which models can modulate their residual stream via natural-language instruction. Across model families and capability levels, we find that most LLMs can control the direction and magnitude of their residual stream activations with some degree of temporal resolution, though performance varies considerably across models. In simple tasks, this level of control can evade activation-based monitoring methods (including linear probes, natural language autoencoders, activation oracles, and the Jacobian lens), albeit imperfectly. These results suggest that control over the activation space itself could become a confound for monitoring as introspective capabilities increase; therefore, we recommend that frontier labs and evaluators track activation controllability in future models.
Read the full abstract

All authors Marek Mateusz Kowalski, Joshua Fonseca Rivera, Uzay Macar, David Demitri Africa

Artificial Intelligence · Cross-listed from cs.IR

Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals

Meysam Varasteh, Veronika Bogina, Noam Koenigstein et al. (+1 more)

The topic of explanation in recommender systems has seen steady research attention since the earliest days of the field. With some exceptions, this work has focused on the explanation of single items in a recommendation list and, especially recently, has emphasized approaches that are decoupled from the logic of the recommendation algorithm itself. Based on findings in the psychology of interpersonal communication, we propose a new task, pairwise interpretation of item rankings, asking the comparative question “Why is item A ranked higher than item B?”. An effective solution to this task, we argue, is inherently grounded in the operation of the recommendation algorithm. We propose a class of techniques based on counterfactual learning to uncover the items in a user's profile that have contributed to the relative ranking of items. Using multiple datasets, we show that it is possible to identify such items as potential basis for comparative explanation.
Read the full abstract

All authors Meysam Varasteh, Veronika Bogina, Noam Koenigstein, Robin Burke

Artificial Intelligence · Cross-listed from cs.LG

Power-Performance Characterization of TinyML Systems

Yujie Zhang, Dhananjaya Wijerathne, Zhaoying Li et al. (+1 more)

TinyML systems are enabling machine learning (ML) inference at the edge. However, there is little quantitative analysis of such systems. This paper presents a systematic performance and power characterization of diverse TinyML applications on microcontrollers (MCUs), spanning neural network models, software libraries, operating systems, and hardware architectures. We focus on the impact of the multiple layers of abstraction that provide higher programmability at the expense of performance and energy efficiency. We propose a model to estimate the costs of different abstraction layers and make recommendations for minimizing those costs. Our findings can help designers with Neural Architecture Search (NAS) and CNN inference optimization on edge devices.
Read the full abstract

All authors Yujie Zhang, Dhananjaya Wijerathne, Zhaoying Li, Tulika Mitra

Artificial Intelligence

SAEM: Stage-Aware Expert Management for Memory-Efficient MoE Inference in Chain-of-Thought Reasoning

Yujie Zhang, Bin Gao and Tulika Mitra

Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases decoding latency and memory usage. Mixture-of-Experts (MoE) models scale capacity through sparse expert activation, yet their full expert weights often exceed GPU memory and require costly GPU-CPU transfers. Existing runtimes treat all tokens uniformly, overlooking a key structural property of CoT traces: consecutive reasoning stages exhibit coherent and predictable expert activation patterns. Ignoring this stage-level regularity leads to inefficient caching and unnecessary data movement. We propose SAEM, a stage-aware MoE inference runtime that detects reasoning stage boundaries and exploits stage-level activation coherence to guide expert placement. SAEM combines stage-aware caching, expert-aligned token repacking, and in-situ CPU execution to reduce data transfer and kernel fragmentation. On mathematical and scientific reasoning workloads, SAEM achieves an average 1.33x throughput improvement over the strongest state-of-the-art caching and offloading baselines under constrained GPU memory, rising to 1.54x when calibration data matches the workload, demonstrating the effectiveness of stage-aware, locality-driven MoE inference for CoT reasoning.
Read the full abstract

Artificial Intelligence

Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals

Junaid Farooq

Retrieval-augmented generation relies mostly on flat, fixed-granularity indexes: documents are cut into uniform chunks and retrieved by similarity, discarding the hierarchical structure of the source. We introduce Semantic Compression Trees (SCT), a hierarchical index in which each node stores only its semantic residual – the information it adds beyond its parent – and retrieval proceeds by progressive descent from the root, so that per-query cost is governed by tree depth rather than collection size. We evaluate on QASPER (50 papers, 173 questions) under two protocols differing only in whether the benchmark supplies the relevant document, with bootstrap confidence intervals and paired significance tests throughout. The results are mixed and we report them as such. When the document is given, SCT with a zero-LLM extractive compressor matches dense retrieval on answer quality (0.274 vs. 0.277 F1, $p = 0.37$) using 30% fewer context tokens and no LLM calls to build the index, and residual storage beats storing full summaries at each node (0.274 vs. 0.205, $p < 0.001$). Increasing the collection fifty-fold multiplies flat retrieval's per-query scoring work by 48.9x and SCT's by 6.4x. Progressive descent itself is not supported. Retrieving the same residuals without the tree performs identically when the document is given ($p = 0.27$), and descent is substantially worse when the system must select the document (0.122 vs. 0.165, $p < 0.001$). Routing accuracy localises the cause: descent selects the correct paper 20.2% of the time against 39.3% for flat retrieval, because that choice is made from the root residual, the most compressed node in the tree. We conclude that the residual representation is worth keeping and top-down routing is not.
Read the full abstract

Artificial Intelligence

Generate in the Chart, Not on the Boundary: Function-Symbol Grounding for Hard Constraints in LTN-GANs

Nijesh Upreti and Vaishak Belle

Logic Tensor Network-Enhanced Generative Adversarial Networks (LTN-GANs) inject background knowledge by grounding each logical axiom as a predicate and training the generator to raise its satisfaction, a fuzzy truth value in $[0,1]$. Previous LTN-GAN work grounded every constraint this way, at the predicate level, and improved constraint satisfaction. A predicate, however, only scores a sample, so it cannot embed hard structural constraints, rules such as orderings, positivity, and definitional identities that must hold in every generated sample. In this work, we investigate grounding each axiom as a function symbol inside the LTN framework. We compare against the state-of-the-art alternative, a constraint layer that clamps each violating sample onto the feasible boundary and so produces outputs that are always valid. Our investigation shows that a valid sample is not always a realistic one. An inequality is not merely satisfied or violated. It holds by a margin, and a faithful generator should also reproduce the margin's real distribution. We find that the resolution ratio $R$, the data's scale over the margin's spread, is a diagnostic, computable before training, of which constraints a chosen grounding can learn. When $R$ is large, the predicate receives no learning signal, the clamp pushes every sample onto the boundary, and the margin distribution is lost while every standard metric still looks fine. A function symbol avoids both failures, computing the constrained variable rather than scoring it. Together the function symbols form a chart, a coordinate system inside the feasible region, where every sample is valid by construction and the margin is learned like any other quantity.
Read the full abstract

Artificial Intelligence

K-Bench: measuring model performance on real scientific agent requests

Aubrey M. Brueckner, Darshil Patel, Yuhuan He et al. (+1 more)

Benchmarks for scientific artificial intelligence are mostly written to be scored: multiple-choice questions, curated agent tasks with reference solutions, or simulators with a known generative structure. Real scientific requests arrive differently. They are underspecified, they carry attachments, and they lack ground truth. We report K-Bench 01, an evaluation built from first-turn requests sampled from live user traffic on K-Dense Web and run end to end by nine frontier models in identical sandboxes, yielding 1,602 completed agent runs. Three blinded language-model judges scored every run against an eight-dimension rubric. On a rubric whose 8-anchor is defined as work a domain scientist would accept with minor edits, no model clears the line under all three judges. gpt-5.6-sol has the highest pooled mean, 8.04, but its 95% interval [7.80, 8.23] spans the threshold, and two of the three judges rank claude-opus-5 first instead. We therefore report the ordering of systems as the reproducible quantity, the absolute level as an attribute of the instrument, and the top of the table as unresolved. Across all 39,934 scored judgments – the eight dimension scores plus a holistic overall for each assessment, excluding not-applicable cells – 47.6% fall below the 8-point threshold. Difficulty is not uniform across the rubric: scientific accuracy averages 6.22 against 7.33 for communication, on identical denominators and in the same direction within every one of the nine models. The single leading failure tag is overclaiming, on 31.4% of assessments. We argue that the informative quantity for scientific agents is not a leaderboard position but the joint distribution of what was delivered, what was claimed, and what artifacts were produced.
Read the full abstract

All authors Aubrey M. Brueckner, Darshil Patel, Yuhuan He, Timothy Kassis

Artificial Intelligence

Data-Driven Dynamic Algorithm Dispatch with Large Language Models

Rushil Shah, Emmanuel Lujan, Rabab Alomairy et al. (+1 more)

We introduce a large language model (LLM)-driven approach for generating dynamic algorithmic dispatch heuristics in high-performance linear algebra. By combining prompt engineering with LLaMA 3 and a curated performance database, the model learns to synthesize selection heuristics that exploit structural patterns to identify fast algorithmic choices. A case study on LU factorization demonstrates the model's ability to replicate expert-designed strategies. This work, developed as part of the DARPA-MIT SmartSolve project, highlights the promise of LLMs for algorithmic discovery and the development of more adaptive, fast linear algebra software.
Read the full abstract

All authors Rushil Shah, Emmanuel Lujan, Rabab Alomairy, Alan Edelman

Artificial Intelligence

Robust Lightweight Deep Learning Models for Oral Cancer Screening

Siddhant Bharadwaj, Aakash Shedsale, Tejashree Subramanya et al. (+6 more)

Oral cancer is a leading cause of mortality in low-to-middle-income countries, where a shortage of specialists delays diagnosis. While point-of-care screening via smartphones offers a scalable solution, developing robust AI for resource-constrained settings poses significant challenges, including class imbalance in training data, variable data quality, and computational constraints on edge devices. In this paper, we present the optimisation of lightweight deep learning models for smartphone-based oral cancer screening. Using a diverse, multi-centre retrospective dataset of approximately 30,000 images acquired over a decade, we systematically evaluate state-of-the-art convolutional, transformer, and hybrid architectures. Through rigorous pipeline ablation, we demonstrate that directly optimising hybrid architectures for the edge strictly outperforms computationally heavy paradigms, such as large models or knowledge distillation. Furthermore, interpretability analysis and simulated noise-stress tests revealed that the system anchors on clinical features and remains robust to unstructured sensor noise, despite vulnerabilities to impulse bit errors. In the held-out test set, our optimised MobileViTv2 models achieved an average sensitivity of 83.2 $\pm$ 1.5% and an average specificity of 86.0 $\pm$ 0.8%, with the best model exhibiting 87.4% sensitivity, 86.5% specificity, and a critical negative predictive value of 97.2% with reference to specialist labels. These results confirm that with targeted architectural selection and streamlined optimisation, interpretable and robust lightweight AI models exhibit high potential for edge deployment to enable automated triage in primary care settings.
Read the full abstract

All authors Siddhant Bharadwaj, Aakash Shedsale, Tejashree Subramanya, Mohd. Azfar, Praveen Birur, Debnath Pal, Shankararama Sharma, Anupama Shetty, Rajesh Sundaresan

Artificial Intelligence · Cross-listed from cs.LG

Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning

Yuyang Luo and Kai Shu

Multimodal Large Language Models (MLLMs) are increasingly deployed in high-stakes domains where fairness is a critical safety requirement. In practice, these models are continually updated through continual learning (CL) to adapt to evolving tasks and data distributions. Prior work has shown that backdoor attacks can manipulate MLLM responses through hidden triggers, but naively implanted backdoors degrade as models undergo subsequent updates of CL. Although fairness has emerged as a central concern for MLLM deployment, whether backdoor-induced fairness violations can survive CL remains unexplored, leaving two critical questions unanswered: (1) whether a backdoor can reliably induce fairness violations in MLLMs, and (2) whether such fairness-targeted backdoors can persist through continual learning. We bridge this gap by proposing Persistent Fairness Backdoor Attack (PFBA) to inject persistent and group-specific discrimination into MLLMs. Specifically, PFBA achieves this through two novel mechanisms. The Latent Space Fairness Reinforcement reshapes the model's deep feature geometry by anchoring privileged-group representations to preserve utility while repelling and clustering targeted-group representations to sustain discrimination, and the Continual Learning Simulation iteratively optimizes the trigger against simulated parameter drift to ensure backdoor persistence across future updates. Extensive experiments demonstrate that PFBA induces severe fairness disparities that persist across continual learning rounds, evading standard backdoor defenses. The data and code are publicly available at https://github.com/lyygua/PFBA.
Read the full abstract

Artificial Intelligence

A Reproducible, License-Aware Distillation Recipe for CPUDeployable Safety Classification

Edson Rodrigues da Cruz Filho, Paulo Ricardo Ferreira Neves, Paulo Henrique Eleuterio Falsetti et al. (+7 more)

Deploying a safety layer for large language models on commodity hardware is constrained by the guards available to do it: current open guard models hold between 1 and 9 billion parameters, are oriented toward the graphics processing unit, and answer in seconds per request on a central processing unit. This paper presents a reproducible, license-aware knowledge-distillation recipe addressing that constraint. A strong open guard labels a corpus of roughly 97,000 prompts, drawn from 24 public datasets, into seven safety categories aligned to a public hazard taxonomy, and a fleet of small students spanning lexical, shallow, encoder and generative architectures is trained to reproduce that signal. The corpus is partitioned at the license boundary, so that a deployable and a research model differ only in their training data and the cost of that restriction becomes measurable. Every model is scored against an independent gold benchmark of 6,361 rows over four slices, labeled apart from the teacher and including a slice of harmless prompts that makes over-defense measurable. The distilled students match the teachers on adversarial text within overlapping confidence intervals and reduce false alarms on harmless prompts, the smallest generative student reaching 3.8% against 4.8% for the 8-billion-parameter teacher, while the encoder classifies in roughly 24 ms per request on CPU. Per-class rebalancing is the only decisive ingredient of the recipe. No superiority over the distilled guards is claimed; on the clean reference slice they remain ahead.
Read the full abstract

All authors Edson Rodrigues da Cruz Filho, Paulo Ricardo Ferreira Neves, Paulo Henrique Eleuterio Falsetti, João Vitor Pavan, Ian Degaspari, Henrique Vieira Laturrague, Patrick Vieira Laturrague, Guilherme Nielsen Dias, Marccello Wilson Perez Berto, Gustavo Voltani Von Atzingen

Artificial Intelligence

Quantifying geographic domain shift to decouple the geospatial transferability of human mobility flow generation models

Zhiyong Zhou, Song Gao, Qianheng Zhang et al. (+2 more)

Human mobility serves as an essential proxy for understanding social, economic, and environmental dynamics in urban systems. Geospatial transferability, which measures a model's capability in a new location or unseen region, is a critical dimension for comparing different human mobility generation models. However, few studies have studied the intrinsic characteristics of geospatial transferability. To this end, this study systematically investigates the geospatial transferability of four representative human mobility generation models using a large-scale benchmark dataset of census tract level commuting flows across 2265 counties in the United States. Inspired by the domain adaptation theory in machine learning, we introduce geographic domain shift to describe the intrinsic differences in geographic feature distributions and spatial structures between source and target regions, which may jointly affect model transferability. Moreover, we propose two metrics, mutual information and spatial shift, to quantify the geographic domain shift. To examine their associations with model transferability, we employ linear mixed-effects regression to analyze the associations between geographic domain shifts and transferability. Our results reveal substantial spatial heterogeneity and asymmetry in transfer performance across regions. Both information shift and spatial shift exhibit statistically significant and complementary explanatory power. This indicates that geospatial transferability depends not only on model design but also on intrinsic geographic differences. These findings provide a novel methodological framework for evaluating and improving the geospatial transferability of human mobility generation models and support more robust and fair human mobility data synthesis across diverse regions. It also offers insights on spatial transferability for GeoAI model development.
Read the full abstract

All authors Zhiyong Zhou, Song Gao, Qianheng Zhang, Feng Zhang, Zhenhong Du

Artificial Intelligence · Cross-listed from cs.CL

Automating Multi-Hop RAG Evaluation via TRIAD: From Context Extraction to Validated Dataset Generation

Lorenz Brehme and Adam Jatowt

Recent advances in LLMs and the adoption of RAG systems in industry have created a need for domain-specific question-answer datasets that can assess RAG performance on proprietary data. Existing datasets, such as HotpotQA, challenge current RAG systems on Wikipedia-based knowledge, but they cannot be transferred directly to domain-specific settings. A comprehensive evaluation of RAG system quality requires both multi-hop queries and unanswerable questions. This paper introduces TRIAD, a three-stage automated dataset generation approach. First, it generates question–answer (QA) pairs for the domain-specific knowledge base of a RAG system. Second, a validator checks each QA-pair in a feedback loop. Third, the QA pairs are extended with relevance-labeled context documents for downstream evaluation. We evaluate this approach against the established MuSiQue and HotpotQA datasets. The results show that the generated dataset exhibits similar performance trends across different RAG setups, while human validation indicates that the questions are suitable for evaluating a domain-specific RAG system. The code used to generate the dataset and all validation results are available in our GitHub repository(https://github.com/lorenzbrehme/triad).
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents

Baicheng Chen, Zheyuan Liu, Jingyu Zhang et al. (+4 more)

Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations rather than model parameters alone. This creates an evaluation mismatch for LLM unlearning: previous unlearning methods may suppress direct parametric recall, but an agent can still recover the same forget target through tools such as web search, retrieval, or database lookup. We identify this failure mode as tool-mediated recovery and study agentic tool unlearning, which aims to reduce both parametric recall and tool-mediated recovery while preserving normal tool use for retained knowledge. To address this challenge, we propose Agentic Tool Unlearning (ATU), a two-stage framework. The first stage applies parametric knowledge unlearning to suppress direct recall, while the second stage performs trajectory-level reinforcement learning in simulated tool-augmented environments to penalize target-seeking tool behavior and final-answer leakage. Experiments on RWKU and MUSE across different LLM architectures show that ATU achieves a better balance between target forgetting and retained utility, making unlearning more robust under tool-augmented agent deployment.
Read the full abstract

All authors Baicheng Chen, Zheyuan Liu, Jingyu Zhang, Kaize Ding, Ningshan Ma, Yue Huang, Meng Jiang

Artificial Intelligence · Cross-listed from cs.CV

presto: Efficient, Training-free, and Open-world Object Placement via Imaginary Search

Weixuan Ding, Shang Liu, Hanyu Pei et al. (+1 more)

Object placement is critical in image composition, requiring spatially and semantically coherent positioning of objects within diverse scenes. Existing approaches typically rely on hand-crafted rules or supervised learning on limited datasets, which restricts their generalization and interpretability, especially in open-world scenarios involving novel objects and scenes. In this work, we reformulate open-world object placement as a heuristic search task guided by reasoning from a Multimodal Large Language Model (MLLM). We introduce presto, a zero-shot, training-free framework that operates within an imaginary action space to iteratively refine object position and scale. Our coarse-to-fine search strategy ensures fast convergence, and we evaluate two decision-making variants: Metric-guided Selection and MLLM-as-a-judge. Experiments across multiple benchmarks show that presto~achieves state-of-the-art performance, particularly in previously unseen, open-world settings. Human studies further reveal that the MLLM-as-a-judge variant produces more perceptually coherent placements than metric-driven approaches, highlighting a gap between standard evaluation metrics and human visual judgment.
Read the full abstract

All authors Weixuan Ding, Shang Liu, Hanyu Pei, Zeyan Liu

Artificial Intelligence

Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning

Qifan Shi, Zhaolu Kang and Chenghua Zhu

Credit assignment in large-language-model reinforcement learning (LLM RL) can be separated into three objects: evidence about success, a transport operator that converts this evidence into token-level advantages, and an update geometry that turns advantages into policy changes. Recent work has greatly improved evidence, sampling, and update geometry, but the transport operator is usually architecture-agnostic. Fixed-discount GAE applies a stationary geometric kernel along token time; group-relative methods broadcast an outcome statistic across an entire response. Neither operator represents the trajectory-specific computation used by the Transformer policy itself. We introduce computation-conditioned credit transport (CCT), a general framework in which a detached statistic of the behavior policy's internal computation parameterizes the causal kernel that transports downstream value through a rollout. Our concrete algorithm, CompPO, maps native attention concentration to a bounded per-token retention gate, uses the gate in both the one-step bootstrap and a path-dependent generalized-advantage trace (Comp-GAE), and co-designs a transport-aligned critic (TAC) that reuses the actor's hidden states and routing information without a second same-scale Transformer. The task reward and clipped PPO policy objective remain unchanged; a constant gate recovers fixed-coefficient GAE. Across five Qwen3-4B seeds, CompPO reaches 61.4% final held-out accuracy (95% CI [60.8,62.0]) versus 53.8% [52.9,54.7] for tuned GRPO. Neither Comp-GAE with a standard critic (55.2%) nor TAC with a fixed gate (56.4%) matches the full model (interaction +2.4 [1.9,2.9]). Shuffle and position controls confirm trajectory-specific alignment; CompPO is stable in 10/12 PPO-grid runs versus 3/12. Frozen evaluation improves over GRPO by 4.3 and 3.9 greedy pass@1 macro points on Qwen3-4B and Llama-3.1-8B-Instruct.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CR

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

Yibo Peng, Long Lian, David Wagner et al. (+1 more)

Prompt injection is listed as the \#1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may inject a prompt into the data, saying, "Ignore all prior instructions and perform <an attacker's task>." To prevent arbitrary manipulation of agents, defenders try to train secure LLMs, which, however, still suffer from near 100% attack success rates (ASRs) against adaptive prompt injections. We note that this is because existing defensive finetuning recipes rely on sequence-level feedback signals (in DPO or GRPO). Treating an entire output equally prevents the model from learning precisely which output tokens are insecure. In this paper, we propose Secure On-Policy Distillation (SecOPD) that provides token-level feedback to guide defensive fine-tuning. The LLM receives an injected sample and produces a rollout, whose tokens are scored by the initialization model given the corresponding clean input. With more fine-grained training signals, our defended Qwen3.6-27B achieves a 9.0% ASR against the SoTA PISmith adaptive prompt injections, compared to 94.0% for the prior SoTA, Meta-SecAlign. The obtained security generalizes to domains completely unseen in training: in agentic tool calling, SecOPD achieves a 4.7% ASR compared to 5.5% for Meta-SecAlign. Code and the model are available at https://github.com/pppyb/SecOPD and https://huggingface.co/pybbb/Qwen3.6-27B-SecOPD.
Read the full abstract

All authors Yibo Peng, Long Lian, David Wagner, Sizhe Chen

Artificial Intelligence · Cross-listed from cs.LG

Selection of Heart Sound Segments for Synchronous Classification of Multi-channel Heart Sounds

Marcelo Nogueira, Jorge H. Oliveira, Carlos F. Ferreira et al. (+2 more)

Cardiac auscultation remains the most cost-effective screening procedure for cardiovascular diseases, and requires listening at the four main auscultation spots. Despite this, automatic heart sound analysis algorithms mostly classify patients using a single heart sound (single-channel), or, when using more than one (multi-channel), analyze each channel individually. To our knowledge, no prior work classifies patients through the synchronous analysis of multi-channel heart sounds, following the procedure used by physicians. This motivates us to study whether synchronous multi-channel analysis outperforms single-channel approaches, and whether it holds an advantage over asynchronous multi-channel methods that analyze channels one by one, potentially by capturing inter-channel interference phenomena. To answer these questions, we introduce a selection algorithm that identifies optimal heart sound segments from each of the four auscultation spots, which are then fed into a multi-input CNN that classifies patients by analyzing the four selected sounds simultaneously. Our synchronous approach, combining the proposed selection algorithm with a multi-input CNN, achieves a superior overall accuracy of 96.5%, a 9.1% gain over the best-performing single-channel and asynchronous multi-channel methods. The benefit of the proposed segment selection strategy over random selection is confirmed by a paired statistical significance test ($p = 0.003$). These results were obtained on 735 patients from the CirCor DigiScope dataset with complete recordings from all four spots, and their scope and generalizability are discussed in light of this and other methodological considerations.
Read the full abstract

All authors Marcelo Nogueira, Jorge H. Oliveira, Carlos F. Ferreira, Miguel T. Coimbra, Alípio M. Jorge

Artificial Intelligence · Cross-listed from cs.LG

KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks

Mohammad Meymani and Roozbeh Razavi-Far

While machine learning models have demonstrated strong performance in many domains, these models have shown profound vulnerabilities when they are exposed to adversarial threats. While adversarial attacks fall into various categories, the most prominent category in research studies is evasion. In evasion attacks, the adversary generates perturbed versions of samples, which might not be observable by human eyes. These samples generally fool the machine learning models with high confidence. This phenomenon poses a significant security violation against machine learning models. In this paper, we investigate the certified and empirical robustness of various Kolmogorov-Arnold network architectures against strong evasion attacks. At first, we provide the mathematical foundations for randomized smoothing and interval bound propagation, and report the $\ell_2$-certified robustness of the models under randomized smoothing. After that, we systematically evaluate the robustness of various defended and undefended KAN models under FGSM, PGD, and C&W attacks in order to find out the optimal defense strategies and architectures.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

TASSO: TAsk-Specific Subspace Optimization for Continual Learning of Vision-Language Models

Chang Sun, Francesco Barbato, Matteo Caligiuri et al. (+1 more)

Vision-Language Models (VLMs) exhibit strong zero-shot capabilities, making them an attractive solution for continual learning across diverse tasks. However, during continual adaptation, both catastrophic forgetting and zero-shot degradation occur, severely degrading performance. In this paper, we introduce TASSO, a new paradigm that efficiently preserves the latent space geometry while ensuring network plasticity. We achieve this with two complementary techniques: subspace learning and geometry-aware knowledge distillation. Specifically, we first learn a sequence of task-specific low-rank projectors, which we use to project the latent representations before optimizing cross-entropy. Secondly, we employ a geodesic-distance-based loss that distills knowledge from the previous-task model while effectively preserving the latent space geometry. These design choices not only avoid unnecessary parameter updates along the full embedding dimensions but also improve learning by focusing on task-specific manifolds. Moreover, the geometry-aware distillation provides strong regularization and significantly reduces both catastrophic forgetting and zero-shot degradation throughout the continual learning sequence. Experimental results with the CLIP vision language model in the multi-domain task incremental and class incremental learning benchmarks demonstrate clear improvements over state-of-the-art methods in mitigating forgetting and preserving zero-shot capabilities.
Read the full abstract

All authors Chang Sun, Francesco Barbato, Matteo Caligiuri, Pietro Zanuttigh

Artificial Intelligence · Cross-listed from eess.IV

Reliability- and Anatomy-Consistency-Aware Multimodal Learning for Robust Fracture Classification from Bangladeshi Radiographs

Musa Tur Farazi and K G Subarno Bithi

Background: Multimodal fracture classifiers may benefit from patient and anatomical metadata, but they can also become brittle when contextual information is missing or mismatched. Methods: We studied 1493 radiographs from the Bangladeshi OrthoFrac-XR dataset using leakage-safe age, sex, bone type, and laterality. A ConvNeXt image encoder was combined with a clinical multilayer perceptron through concatenation, late fusion, reliability-gated residual fusion, and a hierarchical state-location formulation. We additionally introduced an anatomy-consistency gate that attenuates metadata corrections when an image-side anatomical prediction disagrees with the reported bone type. Results: Across five folds and three seeds, hierarchical residual fusion achieved a macro-F1 of 0.6046 +/- 0.0279, compared with 0.5727 +/- 0.0270 for image-only learning, while improving the Brier score from 0.5239 to 0.4948. In a five-fold robustness experiment, anatomy-consistency fusion reduced the macro-F1 loss under shuffled metadata from 0.0567 to 0.0203 relative to ordinary residual fusion, although its clean-data macro-F1 was lower. Without bone type at inference, auxiliary anatomy supervision improved macro-F1 from 0.5620 +/- 0.0330 to 0.5899 +/- 0.0289. Conclusions: Structured context improves fracture classification, and consistency-aware gating limits harm from mismatched metadata. The observed clean-performance-robustness trade-off and the absence of patient-level identifiers motivate external and prospective validation.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

Complexity Induction: Compositional Generalization via Structured Training Distortion

Aleksandr V. Abramov

We demonstrate that structured distortion of training data - which we term complexity induction - can induce compositional generalization in a standard CNN classifier without architectural modification. Using synthetic images of colored geometric shapes, we encode classes as flat string labels (e.g., "red-circle") with no explicit attribute decomposition, and exclude certain color-shape combinations from training entirely. We apply two distortion methods derived from Jaccard string similarity between class names: mixed labels (soft target distributions encoding inter-class overlap) and expanded dataset (false training samples with structurally motivated incorrect labels). Both methods induce the ability to predict unseen class combinations, and act at different levels: mixed labels activate the classifier for unseen combinations by exploiting the CNN's natural embedding structure, while expanded training improves the embedding factorization itself. A control with random (unstructured) false labels confirms that the effect depends on the structure of the distortion, not on noise per se. These results suggest that structured complication of training signals can influence both the internal organization of learned representations and their compositional interpretation - a principle that may underlie the role of natural language in cognitive development.
Read the full abstract

Artificial Intelligence · Cross-listed from math.OC

Primal Acceleration of Newton's Method

Nikita Doikov

We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian. The algorithm uses only primal variables and performs just one linear solve per iteration. With a simple predetermined choice of parameters, it achieves the global convergence rate of $O(1/k^3)$ in terms of the functional residual. To the best of our knowledge, this is the first second-order method for this problem class attaining this rate while relying solely on one linear system solve per iteration (without solving auxiliary nonlinear regularized subproblems, such as cubic regularization, performing nonlinear parameter searches, or using dual extragradient corrections). Our method can be implemented in a Hessian-free way, using an inexact linear system solver, while preserving the fast global rate. We further extend our construction to arbitrary geometry through Bregman divergence, and to composite optimization problems.
Read the full abstract

Artificial Intelligence

VIALS: A Benchmark for Visual Interpretation of Artifacts in the Life Sciences

Elaine Lau, Thanuka Udumulla, Lee Izhaki-Tavor et al. (+3 more)

In professional life sciences workflows, scientists routinely interpret visual artifacts (gel blots, microscopy images, plasmid maps, flow cytometry plots, molecular structures, ...) to inform research decisions. We introduce VIALS, a visual question-answering benchmark with 161 such interpretation tasks, spanning the types of artifacts examined throughout experimental workflows in the biotech industry (rather than polished figures from publications and textbooks). While frontier vision-language models can now fluently describe natural images, we find that they are unable to accurately interpret these scientific images, reflecting limitations in domain knowledge and domain-specific visual reasoning capabilities. In contrast, scientists with relevant domain expertise find these visual interpretation tasks straightforward. AI that cannot similarly interpret such images will have limited utility in professional life sciences workflows, where such artifacts are central to how scientists reason, communicate, and make decisions.
Read the full abstract

All authors Elaine Lau, Thanuka Udumulla, Lee Izhaki-Tavor, Francisco Guzmán, Nicholas Magazine, Jonas Mueller