Artificial Intelligence · Cross-listed from cs.CY
The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students
Alexis Popovici, Andrei Ionascu and Adrian-Marius Dumitran
As Large
Language Models (LLMs) are increasingly deployed as conversational tutors, they risk institutionalizing systemic inequalities. This study presents a systematic API audit of four LLMs acting as history tutors, evaluating 1,800 responses regarding the 1989 Romanian Revolution across five student personas varying by ethnicity and socio-economic tier. We uncover four interconnected patterns of epistemic paternalism: (1)~Differential Refusal, where safety-aligned models block 76.7% of educational requests from low-tier students; (2)~Epistemic Gatekeeping, evidenced by a 3$\times$ reduction in access to geopolitical complexity (e.g., the contested “coup theory”) for marginalized learners; (3)~Agency Theft, a lexical shift where models like LLaMA produce a 5$\times$ higher victimization-to-politics vocabulary ratio for Roma students compared to elite peers; and (4)~Elite Hermeneutics, where AI tutors disproportionately withhold epistemic confidence and justification scores from low-resource demographic profiles. We argue that current safety
alignment acts as a paternalistic filter, transforming conversational AI into
agents of narrative segregation – a manifestation of hermeneutical injustice in Fricker's~\cite{fricker2007} sense that demands urgent pedagogical
auditing.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Mako: A Self-Evolving Agentic Operating System (SE-AOS) for Autonomous Web Exploitation
Praneeth Narisetty and Shiva Nagendra Babu Kore
We introduce the Self-Evolving Agentic Operating System (SE-AOS): a new class of AI
agent that treats exploit capability as a mutable, versioned kernel it extends at runtime, observing its own failures, synthesising new capabilities, proving them against a live target, and hot-loading them back into itself. Mako is the first SE-AOS instance for security research and the autonomous web exploitation engine developed within LaunchSafe. LaunchSafe builds autonomous security
agents for continuous offensive testing and
agent-driven security research; Mako is the core engine behind that platform. On the public XBOW validation-
benchmarks, 104 containerised, CTF-style web applications spanning 26 vulnerability classes across three difficulty tiers, Mako achieves full-suite coverage: it drives every one of the 104 targets to emit a cryptographically fresh, per-build flag, under a verification regime that makes fabricated or memorised results impossible. Our central result is a law of autonomous exploitation: once a capability exists and is discoverable, difficulty collapses; capability, not
reasoning, is what is scarce, together with an architecture and formalism that turn that law into a self-improving system. Mako further runs a gated self-
evolution loop that proposes, sandboxes, and commits improvements to its own
agents and rules when fitness does not regress. We deliberately withhold the operational results, payloads, exploit chains, and tool source, because a system that reduces full-spectrum web exploitation to a repeatable, machine-speed pipeline is dual-use research of concern. We publish the science; we withhold the weapon.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
A Unified Framework for Comprehensive Cardiac CT Segmentation and Phenotyping: Human-in-the-Loop Data Annotation, Vision Foundation Model Development, Multicenter Evaluation and Clinical Validation
Pooya Mohammadi Kazaj, Leo Fridolin Weber, Wen Xie et al. (+17 more)
Comprehensive quantification of cardiac structures from computed
tomography (CT) remains limited not by data availability but by the scalability of measurements, which makes routine use impractical. Here we present a unified framework for comprehensive cardiac CT
segmentation and phenotyping that combines a human-in-the-loop annotation pipeline, a cardiac CT augmentation technique, and a self-supervised foundation model pre-trained on 60,000 unlabeled cardiac CT scans. Using this approach, we assembled the largest and most comprehensive expert-annotated cardiac CT
segmentation dataset to date, comprising 1598 cases and 14 distinct cardiac structures (1000 for training, 598 for the external test set). Across five external
datasets, the framework segmented all structures more accurately and comprehensively than existing open-source tools. Self-supervised pre-training improved labeling efficiency, with the most significant gains observed during external evaluation in the low-data regime. Benchmarking across convolutional,
transformer, and state-space architectures showed comparable performance, indicating that data quality and pre-training, rather than architecture, drove accuracy. The framework was scaled to population-level phenotyping, with segmented anatomy that carries functionally relevant information about ventricular function and disease severity beyond demographic variables. By openly releasing the largest
dataset with human labels, code, model weights, a CT augmentation library, and software, this work provides a reproducible foundation for opportunistic cardiac phenotyping from routinely acquired CT scans.
Read the full abstract ▾
All authors Pooya Mohammadi Kazaj, Leo Fridolin Weber, Wen Xie, Seyed Amir Ahmad Safavi-Naini, Anselm Stark, Giovanni Baj, Ali Mokhtari, Toshiya Yoshida, Christoph Ryffel, Taishi Okuno, Yoshihiro Akashi, Ronny R. Buechel, Thomas Pilgrim, Waldo Valenzuela, George C. M. Siontis, Xiaowei Xu, Moritz Hundertmark, Stephan Windecker, Christoph Grani, Isaac Shiri
Artificial Intelligence · Cross-listed from cs.CL
Automated Textbook Auditing with Multi-Agent LLM Systems
Ciprian Cristescu, Adrian-Marius Dumitran, Angela-Liliana Dumitran et al. (+1 more)
Ensuring the quality of educational materials requires more than standard proofreading: textbooks must be audited for factual accuracy, domain-specific technical correctness, and linguistic quality simultaneously – a task that general-purpose grammar checkers cannot address. We present AI Textbook Auditor, a modular multi-
agent pipeline for automated quality assurance of educational materials across subject domains. The system accepts a textbook PDF and produces a structured, human-reviewable report via two analysis tracks: a Factual and Technical Track in which an ensemble of specialized LLM
agents detects factual inaccuracies, code errors, incorrect definitions, and conceptual inconsistencies, augmented with web search for humanities domains; and a Grammar Track operating PDF-natively to preserve diacritical encoding. A Judge
Agent filters false positives using domain-specific rules before presenting findings to a human reviewer. The pipeline supports two ingestion modes –
vision-native page rendering and PyMuPDF text extraction – and is domain-adaptable via custom
prompts encoding subject-specific error taxonomies. We demonstrate the system on two Romanian upper-secondary textbooks: a CS textbook (56 technical findings across seven categories, with an expert-validated precision of 62.5%) and a history and social sciences textbook (72 findings spanning factual errors, ideological bias, and grammar). The system is designed as a triage tool that reduces the manual effort of locating candidate issues, with human expert validation required before any editorial action.
Read the full abstract ▾
All authors Ciprian Cristescu, Adrian-Marius Dumitran, Angela-Liliana Dumitran, Gabriel Stefan
Artificial Intelligence · Cross-listed from cs.RO
Towards Predictive, Aligned, and Scalable Robot Learning
Peijun Tang, Shangjin Xie, Baifu Huang et al. (+6 more)
Learning, at its core, extends beyond memorization to the ability to reason and solve novel problems by navigating a space of possibilities. We introduce Lumo-2, a latent world-action model that generates actions by
reasoning over world dynamics in latent space. The learned latent world dynamics capture physically grounded visual transitions, naturally encoding future possibilities and providing a unified substrate for cross-modal
alignment. This formulation enables predictive
reasoning akin to world modelling while remaining lightweight and focused on physical dynamics relevant to control. Central to our approach is the hypothesis that action generation quality is governed by the geometry of the latent space. We observe that standard reconstruction-based action tokenization objectives induce representations biased toward low-level signal fidelity, leading to misalignment between reconstruction quality and downstream control performance. To address this limitation, we propose a multi-stage modality pre-
alignment strategy in which action representations are progressively aligned with latent world dynamics,
vision, and
language. This process enforces cross-modal consistency, promotes abstraction, and induces a structured latent space for predictive
reasoning. We provide a systematic empirical study of latent world modelling and modality
alignment, analyzing their roles in scaling laws and out-of-distribution generalization. Results show that Lumo-2 consistently outperforms strong
vision-
language-action (VLA) and world-action model (WAM) baselines, with gains on challenging real-world tasks requiring temporal
reasoning, physical understanding, or high control complexity, including long-horizon and dexterous manipulation. These findings suggest that structured
multimodal alignment and predictive
reasoning are fundamental principles for advancing
embodied intelligence.
Read the full abstract ▾
All authors Peijun Tang, Shangjin Xie, Baifu Huang, Binyan Sun, Haotian Yang, Kuncheng Luo, Weiqi Jin, Shilin Fang, Jianan Wang
Artificial Intelligence · Cross-listed from cs.IR
Enhancing LLMs through human feedback: a journey towards self-improvement
Tatiana Pelc, Gila Kamhi, Asaf Avrahamy et al. (+1 more)
In the rapidly evolving landscape of information
retrieval systems, the ability to adapt and improve through user feedback is paramount. This study introduces a novel methodology for refining the performance of a primary
Retrieval Augmented Generation (RAG) system by strategically integrating an auxiliary feedback RAG system. By systematically harnessing human-generated feedback, the approach aims to enhance the accuracy, relevance, and overall quality of responses, driving the system towards self-improvement. Central to this methodology is a human-in-the-loop implementation, where user feedback is continuously collected, classified, and integrated into the inference workflow, enabling the system to learn and evolve iteratively. To validate the effectiveness of this approach, the study employs rigorous testing against three diverse
benchmark datasets focused on general and custom domain knowledge, utilizing a LLM-as-a-Judge evaluation strategy. This comprehensive framework not only underscores the transformative potential of feedback-driven enhancements in RAG systems but also sets a precedent for future research in adaptive information
retrieval technologies, marking a significant step in the journey towards autonomous refinement and optimization through user engagement.
Read the full abstract ▾
All authors Tatiana Pelc, Gila Kamhi, Asaf Avrahamy, Adi Fledel-Alon
Artificial Intelligence
Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought
Daeyeop Lee and Hwanjo Yu
Chain-of-Thought (CoT) prompting has significantly advanced the
reasoning capabilities of Large
Language Models (LLMs), yet it often incurs substantial computational costs due to over-
reasoning: the generation of redundant, verbose, or irrelevant steps. While existing
reasoning step evaluators effectively detect logical fallacies and factual errors, our analysis reveals a critical blind spot: they fail to penalize valid but inefficient
reasoning steps that inflate
token usage without contributing to the solution. To systematically diagnose this limitation, we introduce RIV-GSM8K, a diagnostic
benchmark injected with five distinct types of inefficiencies, including circular
reasoning and excessive decomposition. Diagnostic experiments reveal that state-of-the-art evaluators struggle to distinguish these inefficiencies from necessary
reasoning. To address this gap, we propose CAID (Context-Aware Information Density), a training-free metric grounded in information theory that identifies low-utility steps. To validate the metric's practical utility, we apply it within PACE, a post-hoc compression strategy. Additional control experiments show that the gains of PACE are not explained by trivial
pruning: compared with random step removal and PRM-based compression baselines, it preserves accuracy at substantially higher compression rates. Empirical results on GSM8K, StrategyQA, and ARC-Challenge demonstrate that PACE reduces
token consumption by 31-53% while maintaining accuracy, confirming that CAID successfully distills informational froth from
reasoning chains without compromising deductive validity.
Read the full abstract ▾
Artificial Intelligence
Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans
Jasmin Thelen and Oliver Wilhelm
Two competing perspectives on fluid intelligence (gf) measures propose that performance is primarily constrained either by working
memory capacity or by the ability to induce novel relations. The first perspective is currently dominant in measurement, as evident from the use of a limited set of recurring rules, whereas the second perspective is reflected in many definitions but rarely present in measurement. The ARC-AGI
benchmark predominantly requires rule induction and was proposed as a measure of gf for both humans and artificial systems. However, its psychometric properties have not yet been examined in human samples. We therefore investigated the psychometric characteristics and nomological network of ARC-AGI in a first study with 100 participants. A compilation of ARC-AGI items showed good psychometric properties and correlated substantially with figural fluid intelligence as measured by a figural
reasoning test ($\rho$ = .63). Associations with figural originality were weak. These findings provide initial support for the validity of ARC-AGI as a measure of human fluid intelligence. Future research should include more rule induction tasks as well as additional multivariate
covariates. This study is unusual by studying a task in humans that was initially designed for machines. We suggest systematically
embedding AI
benchmarks into the nomological network of human cognitive abilities to enable more systematic evaluation and interdisciplinary cooperation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
Do Multi-Agent LLMs Explore Each Other?
Hyeong Kyu Choi, Jiatong Li, Wendi Li et al. (+2 more)
Exploration is essential for reliable autonomy in multi-
agent systems, yet it remains unclear whether large
language model (LLM)
agents can explore effectively when interacting with one another. We show that modern LLM
agents often fail to do so, exhibiting myopic and polarized interaction patterns that lead to suboptimal coordination and increased regret. We formalize this challenge as the Multi-
Agent Exploration problem, modeling it as a partially observable
stochastic game (POSG), in which
agents must probe peers to infer their capabilities and identify effective interaction strategies. To address this, we introduce Multi-
Agent Contextual Exploration (MACE), a lightweight framework that explicitly promotes exploration through structured peer selection. Across both contextual and parametric diversity settings, exploration behavior and downstream task performance substantially improve when MACE is applied. We further provide theoretical insight that MACE achieves a sublinear expected-regret bound. Overall, our results highlight a fundamental limitation of current LLM
agents and underscore the importance of explicitly guided exploration for reliable multi-
agent autonomy.
Read the full abstract ▾
All authors Hyeong Kyu Choi, Jiatong Li, Wendi Li, Xin Eric Wang, Sharon Li
Artificial Intelligence · Cross-listed from cs.SE
An Empirical Study for Android-to-OpenHarmony GUI Test Migration
Yakun Zhang, Xinjia Chen, Yiyun Chen et al. (+6 more)
To reduce the substantial engineering effort required to test the corresponding applications from Android to OpenHarmony, migrating existing GUI test cases has become a critical problem. However, current research neither proposes solutions tailored for OpenHarmony nor provides a systematic evaluation of migration approaches on this system, leaving developers with limited empirical guidance in practice. In this paper, we present the first systematic empirical study of test migration from Android to OpenHarmony. Specifically, we first construct a
dataset referred to as the ATH
Benchmark, comprising 36 commercial applications with an average of over 9 billion downloads, along with 108 manually designed test cases. Second, we select two state-of-the-art test migration approaches (i.e., ReSPlay and ITeM) and adapt these two approaches to enable their execution on OpenHarmony. Third, we use the preceding infrastructure to evaluate these two approaches from three perspectives, including testing performance, root causes of failures, and the impact of OpenHarmony characteristics. Our results reveal that existing test migration approaches are less effective (15% success-rate on ReSPlay and 26% success-rate on ITeM) in Android-to-OpenHarmony scenarios. Through an in-depth analysis of failed cases, we identify that test performance is primarily hindered by OpenHarmony-specific characteristics, including technical architecture differences and unique ecosystem traits. Utilizing these findings, we propose an enhanced approach based on ITeM, referred as ITeM-HM, which incorporates specific OpenHarmony system features. As a result, ITeM-HM successfully achieves a 214% success-rate relative improvement over the original ITeM (from 26% to 81%).
Read the full abstract ▾
All authors Yakun Zhang, Xinjia Chen, Yiyun Chen, Yuxia Zhang, Mingyi Zhou, Xiang Gao, Shaokun Zhang, Li Li, Yunming Ye
Artificial Intelligence · Cross-listed from cs.CY
DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs
Anqi Li, Jie Zhang, Zhongqi Wang et al. (+4 more)
While Large
Vision-
Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predominantly rely on static
datasets, which provide only a superficial assessment, as their fixed test cases cannot adaptively evolve to measure the true depth and limits of model vulnerabilities. We introduce DeepBias, an adaptive framework for the in-depth probing of social biases in LVLMs with carefully designed
agents. Our approach operates through a dynamic ”generation-
evolution-probing” loop. First, a generative ProposerAgent synthesizes test data and is iteratively updated via Direct Preference Optimization (DPO) based on the target LVLM's responses, exploring model-specific failure modes. Second, an autonomous skill-driven DiggerAgent rewrites each test data across multiple probing turns, adaptively selecting from a curated skill library of deepening and rewriting strategies. At each turn, this process is conditioned on the model's previous response, enabling progressively deeper biases to be exposed. Furthermore, we build a
benchmark named DeepBiasBench using our framework. By employing an ensemble of five diverse state-of-the-art LVLMs as anchors, the
benchmark captures vulnerabilities shared across architectures. Comprehensive experiments demonstrate the effectiveness of our framework and show that DeepBias provides a challenging
benchmark for in-depth bias evaluation, establishing an evolutionary paradigm for LVLM safety assessment.
Read the full abstract ▾
All authors Anqi Li, Jie Zhang, Zhongqi Wang, Songkai Xue, Jiahao Wang, Shiguang Shan, Xilin Chen
Artificial Intelligence
Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory
Tengjiao Liu
LLM
agents today are caught in an awkward bind. Lock them down with static safety instructions and they rarely venture beyond the obvious; give them free reign with tools and multi-
agent debate, and safety violations quickly follow. Rather than forcing a single model to juggle both creativity and caution, we separate the concerns across specialized roles. A Disrupter generates unconventional proposals, a Validator enforces hard runtime checks at the tool gateway, and a Broker pulls in distant but relevant analogies. Failures are not discarded – they are compiled, via MCTS, into compact, signed constraint patches we call Scars. These patches are cached locally and inherited by future cohorts, turning repeated failures into reusable, low-cost runtime constraints. In a spatial-semantic sandbox (N=20 runs, p<0.01), our cohort reaches remote targets where debate fails, the Validator prevents all executed breaches, and Scars reduce
token consumption by 15.1% by avoiding redundant validator checks. Furthermore, credit-based Communication Allocation Scores (CAS) restrict outbound bandwidth, reducing overall
token costs by 55.9% under resource constraints.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
HandFlow: Fully Generative 4D Hand Recovery with Flow Matching
Mingxi Xu, Bowen Duan, Yi Gu et al. (+3 more)
Accurate
monocular 4D hand reconstruction remains challenging. Per-frame discriminative regressors lack temporal context and often produce jittery predictions. Temporal models improve consistency by aggregating information across frames, but they are typically deterministic regressors, making them vulnerable to ambiguous observations caused by occlusion and motion blur. Generative modeling offers a natural alternative by learning a prior over plausible hand motion sequences, enabling coherent hand-state recovery when visual evidence is incomplete or unreliable. Motivated by this observation, we present HandFlow, a fully generative flow-matching framework for temporally coherent 3D hand pose and shape estimation from
monocular video. Given visual and skeletal observations, HandFlow denoises an entire temporal window of MANO parameters through a single ODE integration. To support this, we use a Flux-style dual-stream
transformer that attends across the full sequence to capture long-range dependencies without autoregressive decoding, and a confidence-aware continuous masking mechanism that blends observed features with learnable mask
tokens to handle noisy or missing observations. Experiments on DexYCB and HOT3D show that HandFlow achieves state-of-the-art performance, with particularly large gains in world-space accuracy and temporal smoothness. It reduces world-space pose error by over 30% compared with the strongest baseline and achieves the lowest acceleration error among all evaluated methods, while remaining competitive in per-frame pose accuracy. Moreover, on a single GPU HandFlow reconstructs a 150-frame sequence at 47 fps, about 12x faster than the fastest prior
video-based method, with reconstruction itself accounting for only a small fraction of the end-to-end latency.
Read the full abstract ▾
All authors Mingxi Xu, Bowen Duan, Yi Gu, Zhengyang Shen, Renjing Xu, Yutao Yue
Artificial Intelligence
PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection
Liming Liu, Chao Hu, Mingfei Lu et al. (+3 more)
Relational fraud detection can exploit both label-free graph context and label-derived neighborhood evidence, but these two information sources obey different validity conditions. In particular, neighborhood risk becomes invalid when a queried node's own label, or any validation or test label, enters its construction. We formulate this issue as provenance-constrained relational evidence use and present PREF-Gate, an auditable decision framework with two fixed experts and a finite validation gate. The context expert uses attributes, one-hop means, feature residuals, and degree descriptors without labels. The evidence expert adds self-excluded, training-label-only neighborhood risk and empirical-Bayes summaries that expose support, uncertainty, availability, and shrinkage. Before test inference, the gate selects either expert or one of three pre-specified probability mixtures and fixes the decision threshold. On Amazon, YelpChi, and TFinance, using five identical stratified splits and 14 same-protocol methods, PREF-Gate obtains mean AUPRC values of 0.9085, 0.8104, and 0.8913. It selects the label-free expert on all Amazon and YelpChi splits and an evidence mixture on all TFinance splits. Thus, the main result is conditional rather than universal: label-derived relational evidence is useful only where held-out validation supports it. The framework couples competitive ranking performance with an explicit label-provenance contract, finite selection policy, failure accounting, and review-budget evaluation, providing an auditable knowledge-based decision pipeline for graph fraud detection.
Read the full abstract ▾
All authors Liming Liu, Chao Hu, Mingfei Lu, Yiwei Ge, Xingle Li, Heyuan Shi
Artificial Intelligence · Cross-listed from cs.CL
ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm
Pei Guo, Enjie Liu, Yunzhi Tan et al. (+6 more)
Table-based
reasoning with large
language models (LLMs), which requires
reasoning based on natural
language questions and structured tabular data, has gained widespread
attention. However, a series of issues still constrain the application of this task. The previous approaches suffered from significant performance degradation when faced with large tables due to the difficulty of long text modeling and the limitation of input length for LLMs. The text-to-SQL approach is used to efficiently extract key information from tables and generate smaller sub-tables. However, tabular data, especially web tables, often lack the necessary structure and consistency, making them unsuitable for performing mathematical logic operations using SQL queries. We propose the ProgramTab framework, which guides LLMs employing in-context learning to perform tabular data preprocessing with Python code, as well as the momentous contents extraction with row and column extraction and SQL generation. The experiment results on table
reasoning datasets demonstrate that the ProgramTab framework effectively deals with table-based
reasoning tasks and outperforms all LLM-based baselines.
Read the full abstract ▾
All authors Pei Guo, Enjie Liu, Yunzhi Tan, Mochi Gao, Jianxin Zhang, Ruichao Zhong, Juntao Li, Bo Hu, Zang Li
Artificial Intelligence
What We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities
Sukai Huang, Chenyuan Zhang, Fucai Ke et al. (+4 more)
When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-level variation may reflect distinct latent planning competencies rather than differences along a single ability spectrum. We study this question on ACPBench-Hard by evaluating multiple LLM families under varying test-time
reasoning budgets and applying a multidimensional item response theory model to uncover the latent competency structure underlying LLM planning. The analysis reveals two principal dimensions that shape planning performance: operational
reasoning, the ability to evaluate local action applicability and immediate state transitions, and structural enumeration, the ability to reason about goal reachability and landmark structure. Operational
reasoning improving under model scaling and longer
reasoning traces, while structural enumeration remains comparatively insensitive. Our findings motivate competency-level evaluation of LLM planning, shifting the focus from whether models improve overall to which planning competencies improve, under what conditions, and why.
Read the full abstract ▾
All authors Sukai Huang, Chenyuan Zhang, Fucai Ke, Zhixi Cai, Naim Rastgoo, Gholamreza Haffari, Hamid Rezatofighi
Artificial Intelligence · Cross-listed from cs.SE
RepTran: Search-Based Repair of Transformer Models
Yuta Ishimoto, Paolo Arcaini, Fuyuki Ishikawa et al. (+3 more)
To ensure the overall quality of AI-enabled software, not only traditional software components but also AI components need to be tested and repaired. Among AI components,
Transformer models are increasingly integrated into software systems, which makes their misbehaviors critical. Although prior work in the software engineering community has proposed deep neural network (DNN) repair methods, most overlook
Transformer-specific structures. We propose RepTran, a search-based repair method for
Transformer models. It targets their feed-forward networks (FFNs), which play a central role in the architecture. RepTran identifies suspicious weights by combining two types of scores: a variance-based
neuron score and an existing bidirectional score. It then iteratively optimizes these weights using differential
evolution. Our evaluation includes 18 fault
benchmarks constructed from CIFAR-100 and Tiny-ImageNet. We compare RepTran against three baselines: random weight selection, Arachne (a state-of-the-art DNN repair method), and ArachneW, which enables Arachne to control the number of selected weights. RepTran achieved an average repair rate of 74.7%, statistically outperforming random selection and Arachne across all
benchmarks. Effect size analysis revealed that RepTran achieved higher repair rates than ArachneW regardless of the number of selected weights. These results suggest that RepTran is effective for enhancing the reliability of AI-enabled software.
Read the full abstract ▾
All authors Yuta Ishimoto, Paolo Arcaini, Fuyuki Ishikawa, Masanari Kondo, Naoyasu Ubayashi, Yasutaka Kamei
Artificial Intelligence
SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
Bowen Lv, Xiao Liu, Yanyu Ren et al. (+7 more)
Computer use
agents (CUAs) are emerging as a powerful interface for automating complex digital workflows through visual perception and GUI execution. Online reinforcement learning with verifiable rewards (RLVR) has emerged as a key direction for scaling their capabilities. However, this paradigm is bottlenecked by verifiable data scarcity and online RL inefficiency. To break these barriers, we introduce ScaleCUA, a unified framework that scales online RL for CUAs via verifiable task synthesis and efficient training. At the data level, we design VeriGen, an end-to-end framework for generating verifiable RL tasks through iterative docker interactions and a multi-
agent feedback loop. Scaled to 100+ concurrent
agent workers via a shared docker interaction probe, this pipeline produces 24K+ verifiable tasks and nearly 3K high-quality RL tasks. To maximize sample efficiency, we propose Frontier Sampling, which tracks per-task capability and allocates rollouts to the current learning frontier. On the training side, we further design Visual Context
Segmentation, a sliding window over recent visual context that balances rollout and training-engine pressure, yielding a 2.83x training speedup over step-wise decomposition. Together, ScaleCUA achieves 68.7% on OSWorld and 54.0% on ScienceBoard, establishing new state-of-the-art performance among open-source computer use
agents. Code, models, and
datasets are available at https://github.com/THUDM/SCALE-CUA.
Read the full abstract ▾
All authors Bowen Lv, Xiao Liu, Yanyu Ren, Hanyu Lai, Bohao Jing, Hanchen Zhang, Yanxiao Zhao, Shuntian Yao, Jie Tang, Yuxiao Dong
Artificial Intelligence · Cross-listed from cs.CL
Amplitude-Only FFN Intervention for Tool-Structured LLM Inference: Method, Gated Evaluation Protocol, and Cross-Model Empirical Results
Sheng Xu, Zhen Chen, Junhua Wang et al. (+4 more)
We study amplitude-only rescaling of feed-forward network (FFN) activations to repair tool calls and other structured outputs, using multiplicative coordinate masks rather than additive steering vectors. Amplitude Gating (AG) keeps pretrained weights fixed and applies magnitude/
entropy-based masks at six SwiGLU sites, with a Newton-Schulz windowed ranking variant. Across three Qwen checkpoints and six text/tool endpoints, effects are task dependent. Under frozen local scorers, Qwen3.5-9B non-NS configurations improve two function-call endpoints by +2.61/+2.67 percentage points (pp) and static ToolBench in/out-domain by +1.64/+2.82 pp; JSON gains are small. These gains survive comparing the weaker of two observed AG runs with the stronger baseline, supporting observed-run robustness rather than population significance. Scores measure lexical or answer/action-name agreement, not executed-tool success. Under the current experimental conditions, the six-task random-forest refit improves native score by +0.46 pp with a positive conditional paired interval; transfer to other settings requires further evaluation. The results support task-specific interventions; causal mechanisms, equal-budget advantages, repeated-run uncertainty, and serving cost require further evaluation. Code and experimental data: https://doi.org/10.5281/zenodo.23654706.
Read the full abstract ▾
All authors Sheng Xu, Zhen Chen, Junhua Wang, Boyuan Huang, Ke Jia, Jiadun Zhu, Yiming Xu
Artificial Intelligence
The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy
Chunzheng Zhu, Lei Tian, Bohan Tan et al. (+15 more)
The growing ability of large
language models and
vision-
language models to jointly interpret and reason over images and text is reshaping medical imaging AI, moving it from task-specific predictors toward autonomous
agents that perceive, reason, plan, remember, and act in clinical environments. This survey departs from the capability-first perspective of existing literature and instead begins from clinical deployment, asking what tasks, contamination-resistant
benchmarks, and interactive training environments are required before medical
agents can be trusted in practice. Medical
agents are formalized as sequential decision-making systems under partial observability, together with a three-level autonomy taxonomy spanning assisted, cooperative, and fully autonomous operation. The field is organized along a unified scaling spine consisting of framework scaling, capability scaling, and environment scaling. Within this framework, clinical environment scaling, the integration of tools, data, and clinical gyms, is identified as the most actionable yet underexplored direction for
agents operating in PACS, EHR, and FHIR ecosystems. Clinical self-
evolution, where
agents improve through interaction with their environments rather than parameter scaling alone, is further positioned as a key research frontier, drawing insights from self-improving
agents,
agent gyms, and test-time compute scaling. Applications across radiology, pathology, ophthalmology, and hospital workflows are examined together with deployment challenges including
hallucination, cascading failures, and
fairness. By consolidating more than 300 references, with particular emphasis on advances from 2025 to 2026, this survey provides a roadmap toward trustworthy, self-improving medical imaging systems for real clinical practice.
Read the full abstract ▾
All authors Chunzheng Zhu, Lei Tian, Bohan Tan, Ziqi Zhou, Yuxuan Sun, Yijun Wang, Chengchao Lv, Yilin Wen, Yijun He, Jinghao Lin, Yihang Chen, Chee Wei Tan, Qianshan Wei, Lei Zhao, Bin Pu, Kenli Li, Yuan Xue, Jianxin Lin
Artificial Intelligence
STAMP: Provenance-Guided Credit Assignment for Deep Search Agents
Ke Xu, Han Xu, Xinran Chen et al. (+6 more)
Reinforcement learning for deep-search
agents has largely focused on trajectory-level scoring – outcome correctness, citation-aware rewards, and evidence coverage. Yet the actions that expose supporting documents receive no targeted credit, a gap we call the reward-credit mismatch. We propose STAMP, in which a reference-based verifier judges whether each cited document supports an entity or relation in a training-time evidence graph, and first-exposure attribution traces each supported citation back to the action that first surfaced it. This step credit is injected through sign-preserving advantage modulation, which redistributes advantage across steps without changing the trajectory-level reward or the relative ranking of trajectories within each group. On BrowseComp, BrowseComp-ZH, and xbench-DS, STAMP improves the GRPO baseline by +2.0/+5.5/+3.0 points under matched SFT initialization, training data, and search tools, and composes with both outcome-only and citation-rubric base rewards. Component ablations confirm that the provenance-based credit signal and the sign-preserving advantage modulation each contribute to the gains.
Read the full abstract ▾
All authors Ke Xu, Han Xu, Xinran Chen, Yuqian Wang, Zhixuan Li, Xiaojian Liu, Changwo Wu, Jianqiang Xia, Yuchen Li
Artificial Intelligence · Cross-listed from cs.RO
Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation
Haojie Huang, Linfeng Zhao, Haotian Liu et al. (+9 more)
Representing manipulation actions as 2D trajectories in the camera plane provides a compact and interpretable basis for learning complex 3D manipulation policies. However, it also creates challenges from out-of-frame trajectories and limited precision. We propose Pix2Act, an imitation learning method that addresses these challenges by generating continuous image-space keypoint trajectories in each camera plane and losslessly recovering end-effector poses via triangulation. This reformulates high-dimensional 3D control as a simpler, more learnable 2D prediction problem. Crucially, it aligns observations and actions in the same coordinate space, enabling equivariant transformations to jointly rotate individual camera images together with their image-space actions. We analyze the
symmetry properties of this augmentation and design a network architecture that can fuse multiple camera views while respecting their per-view rotations. As a result, Pix2Act implicitly enlarges the support of the data distribution and learns invariant action structures across transformations, yielding improved generalization and overall performance. Across diverse simulated and real-world manipulation tasks, Pix2Act outperforms state-of-the-art baselines and remains robust under camera perturbations.
Read the full abstract ▾
All authors Haojie Huang, Linfeng Zhao, Haotian Liu, Zhang Ye, Si-Yuan Huang, Mingxi Jia, Boce Hu, Fangzhou Lin, Yu Qi, Dian Wang, Robin Walters, Robert Platt
Artificial Intelligence · Cross-listed from cs.CR
AMT-X: Phase-Structured Multi-Turn Red-Teaming with Checklist-Gated Evaluation
Yi Ting Shen, Kentaroh Toyoda and Alex Leung
Safety evaluation of large
language models (LLMs) relies largely on single-turn attack
datasets and single-judge scoring, underestimating risk from adaptive multi-turn adversaries and reporting a single success rate that does not separate partially actionable outputs from those carrying complete operational detail. We propose AMT-X (Adaptive Multi-Turn Exploitation), a phase-structured multi-turn red-teaming framework. Unlike prior multi-turn attacks that rely on ad hoc escalation or free-form per-goal plans, AMT-X casts the attack as an explicit, reproducible multi-phase state machine driven by semantic signals from the victim, and replaces single-judge scoring with a multi-role jury whose phase-conditioned checklists gate success on actionable harm. Across six frontier victim models (queried under their default safety
alignment, without added moderation layers) and seven Moderation sub-categories, AMT-X attains overall attack success rates of 97.6-100% under a lenient score threshold, but 66.7-78.6% under a stricter gate requiring complete, real, and operational detail: a gap of up to 33 percentage points between partially and fully actionable harm.
Read the full abstract ▾
Artificial Intelligence
The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation
Chenglin Yu, Hongquan Gui, Ying Yu et al. (+2 more)
LLM
agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an
agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces. We introduce AgentFootprint, a cross-framework
benchmark of post-run
agent storage footprint. Its serialization-aware metric suite measures total retention, channel composition, duplication, growth, compressibility, and conversation-history reconstructability. It addresses a measurement trap: naive byte-level measurement understates duplication by an order of magnitude because database paging and JSON escaping obscure repeated content. A fixed-trace control separates
agent-generated logical volume from persistence-layer amplification: replaying the same trajectory through seven persisting frameworks yields a 6.7x spread. Under identical models, tools, and tasks, configurations with 100% accuracy differ by 15.7x in retained bytes, although their defaults support different recovery and audit capabilities. Three full-history configurations grow superlinearly on a repeated-observation stress task. Exported trajectories from 108 instance-normalized SWE-bench Verified submissions span three orders of magnitude per instance, with no detectable correlation with resolve rate. A content-addressed store reduces retention by 4.8x-32.7x while preserving every reconstructability score. These results establish persistent storage as a resource metric to report jointly with accuracy and reconstructability.
Read the full abstract ▾
All authors Chenglin Yu, Hongquan Gui, Ying Yu, Tao Zeng, Ming Li
Artificial Intelligence
NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management
Changlun Li, Peixian Ma, Qiqi Duan et al. (+2 more)
Large
language models (LLMs) based
agents are beginning to participate in portfolio construction and
market analysis, where decisions must be justified under evolving information and risk constraints. Current assessment practice, however, remains poorly aligned with this setting: many studies rely on static examinations or report only terminal portfolio returns, while the intermediate evidence, analyst judgments, and execution steps that produced those returns stay largely invisible. We introduce NextFund, an evaluation platform that makes financial-
agent behavior observable under live
market conditions. The platform couples time-consistent
market access, coordinated multi-
agent analysis, and persistent logging of the full decision path from observation to trade. Through an interactive Trading Arena, users can compare models across
markets, inspect equity curves, and drill from leaderboard outcomes down to individual justifications. We present NextFund on Hong Kong, U.S., and China A-share equities, illustrating how inspectable decision histories enable fairer benchmarking and more actionable diagnosis. Our demo is available at https://paradoox.cn/nextfund/.
Read the full abstract ▾
All authors Changlun Li, Peixian Ma, Qiqi Duan, Zhenyu Lin, Peineng Wu
Artificial Intelligence
A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery
Prashant Devadiga, Abhishek, Adithya Mishra et al. (+9 more)
The rapid expansion of capabilities in Large
Language Model (LLM)
agents has exposed a critical architectural bottleneck: when
agents are given access to a flat, monolithic registry of tools, the model must evaluate hundreds or thousands of options simultaneously. This leads to decision-space explosion, context window saturation, and degraded routing accuracy. To address these limitations, this paper presents a hierarchical, skill-based architecture for agentic orchestration. Capabilities are organized as a rooted tree where internal nodes make routing decisions and leaf nodes execute deterministic tasks. The runtime enforces a single-step execution loop governed by a Last-In-First-Out (LIFO) stack, giving the
agent a form of
memory akin to a Pushdown Automaton, therefore enabling it to track nested execution contexts and resume deterministically from any depth. Capability discovery follows a manifest-driven, lazy-loading protocol: only the immediate children of the active node are loaded, so
memory and
prompt costs scale with the explored path rather than the global registry. By replacing global
memory with localized stack frames, the architecture prevents outputs from one execution branch from leaking into another, establishing the isolation guarantees required for deployment in regulated enterprise environments. We also discuss UPI Help, an AI-powered digital payments support product, as a motivating production deployment context. We provide a mathematical formalization of the orchestration state, detailed algorithmic analysis of the execution loop, and controlled
benchmarks comparing flat and hierarchical routing under increasing tool catalogs, multi-step workflow pressure, and visible schema-
token exposure per LLM call.
Read the full abstract ▾
All authors Prashant Devadiga, Abhishek, Adithya Mishra, Alok Singh, Amisha Sinha, Asit Desai, Gaurang Dahad, Harshit Bhushan, Mandati Pramod Reddy, Prakhar Gupta, Rupesh Patil, Siddhi Behere
Artificial Intelligence · Cross-listed from cs.SD
BeatEdit: Symbolic Music Generation as Explicit Editing
Haoyu Gu, Lekai Qian, Haowu Zhou et al. (+2 more)
Music creation is fundamentally a process of revision. Yet symbolic music generation remains dominated by paradigms that produce complete sequences from scratch, with limited support for selective modification. Edit-based methods have proven effective for text transformation tasks, but remain largely unexplored for symbolic music. We trace this absence to the representational level: conventional event-based music encodings lack the structural properties required by explicit music editing. In contrast, the BEAT encoding, a beat-grid-anchored representation originally designed for autoregressive generation, possesses structural properties amenable to editing. We propose BeatEdit, the first framework for symbolic music generation based on explicit edit operations, recasting generation as producing new content by editing a draft rather than synthesizing from scratch. BeatEdit comprises three complementary mechanisms along an axis of increasing edit density: per-
token sequence tagging for error correction, iterative refinement for accompaniment editing, and tag-then-fill for segment completion. All these mechanisms share a single encoding and pre-trained backbone, achieving higher precision and perceptual quality than autoregressive and
diffusion methods across all three tasks, while remaining efficient, with single-pass inference completing in under 100 ms. Cross-encoding evaluation further reveals that encoding design substantially influences editing effectiveness, with notable encoding-method interaction effects. Code is available at https://github.com/Haoyu-Gu/BeatEdit-code
Read the full abstract ▾
All authors Haoyu Gu, Lekai Qian, Haowu Zhou, Qi Liu, Shuai Wang
Artificial Intelligence · Cross-listed from cs.RO
VIA: Visual Interface Agent for Robot Control
Hengyuan Hu, Jensen Gao, Priya Sundaresan et al. (+3 more)
Robot manipulation is a complex task that requires visual perception, physical
reasoning, planning, and closed-loop control. General-purpose foundation models (FMs) have grown remarkably capable of some of these, especially perception and
reasoning. Inspired by the growing ability of FM-powered
agents to operate software through visual interfaces, we ask whether that same competence suffices to control a
robot directly given the right interface. We present VIA (Visual Interface
Agent), a framework that recasts
robot control as an agentic task where an off-the-shelf
agent drives a manipulator directly through an interface. The interface is a virtual workspace of interactable visual components where the
agent can probe pixels of interest with mouse-like tools and command a virtual end-effector to set new target poses with a small set of general tools. We show that VIA enables
agents of varying capabilities to perform diverse tabletop manipulation tasks in simulation. We also use VIA to drive an off-the-shelf mobile manipulation
robot in the real world to complete tasks that require both
navigation and manipulation. Both settings are zero-shot, requiring no
robot training or additional action primitives. Performance scales well with the size and strength of the underlying FMs. These results suggest that frontier
agents already possess skills that transfer directly to
robot control given the right interface: your coding or computer-use
agent is, in a sense, secretly a
robot-control
agent.
Read the full abstract ▾
All authors Hengyuan Hu, Jensen Gao, Priya Sundaresan, Satvik Sharma, Jeannette Bohg, Dorsa Sadigh
Artificial Intelligence · Cross-listed from cs.SD
MusicMark: A Robust Generative Watermarking Framework for Music Generation
Seohwan Yun, Jeeyoung Yun, Yongjin Kim et al. (+2 more)
AI music generation has rapidly advanced alongside commercial platforms, raising the need for reliable watermarking for provenance and attribution. However, existing audio watermarking research has largely focused on
speech, and applying
speech-oriented methods to music is challenging due to music's complex structure and rich acoustic texture. Most existing methods are post-hoc, adding imperceptible perturbations after generation rather than
embedding watermarks as part of the content. This makes them fragile under transformations and especially vulnerable to neural codec re-synthesis, which can discard imperceptible residual signals. Moreover, since generation and watermarking are decoupled, the watermarking step can be bypassed or omitted, weakening provenance guarantees. To address these issues, we propose MusicMark, which, to the best of our knowledge, is the first generative watermarking framework for music. Specifically, MusicMark embeds watermark messages into the semantic latent space during generation, incorporating the watermark as part of the musical content and ensuring robustness against diverse attacks, particularly neural codec re-synthesis. To this end, we introduce a watermark adapter into a
diffusion-based generation model to embed watermark messages across denoising steps. The adapter and detector are trained with a joint objective that preserves fidelity by constraining watermarked latents close to their unwatermarked reference latents, while improving robustness through attack augmentations. Experiments demonstrate that MusicMark substantially outperforms post-hoc baselines across diverse attacks including neural codec re-synthesis, while maintaining comparable generation quality. We further introduce a cover-song attack, converting the singing voice while preserving musical content, and show that MusicMark remains more robust than post-hoc methods.
Read the full abstract ▾
All authors Seohwan Yun, Jeeyoung Yun, Yongjin Kim, Juyeon Lee, Sungwoong Kim
Artificial Intelligence · Cross-listed from cs.LG
The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning
Joyjeet Singh
Deep
equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved
equilibrium should encode the result of genuine iterative inference. We report a cautionary study of a port-
Hamiltonian DEQ with a learned initialization on two
reasoning tasks – ProofWriter entailment over frozen DeBERTa
embeddings and a BFS-verified graph-reachability
benchmark – in which the implicit computation is a silent no-op. Across tasks, seeds, and controlled ablation arms, the solved
equilibrium equals the solver's start point to numerical precision, and bypassing the solver entirely changes test accuracy by +0.00 percentage points in 18 of 19 training runs. Controlled interventions falsify the tempting explanation: removing the anchoring term reproduces every result, and retraining with noise-decoupled starts yields a solver that converges to the noisy start while the decoder learns to ignore it. The single escaping run diverges instead ($\|h^{*}-z_0\|=171$), producing a co-adapted noise channel whose removal improves accuracy. Iteration counts are uncorrelated with ground-truth difficulty ($r=0.009$), and the full apparatus never outperforms a two-layer MLP on either task. We trace the mechanism to gradient starvation along two distinct routes, show that the standard zeroing ablation is confounded and gives wildly seed-dependent answers where the correct substitution test gives a stable zero, and distill a four-test diagnostic protocol for
auditing claimed implicit computation. All experiments run on a single free Colab GPU; code, raw logs, and analysis scripts are released.
Read the full abstract ▾