探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-16 DOI: HASH:247d272b33a7a52f98cdc8ff18eefcb8

Development of a symptom-based severity score anchored to health-related quality of life post-COVID-19 within the population-based EPILOC cohorts

作者:

Peter↗R. S↗Sedelmaier↗Nieters↗Schilling↗Matits↗Goepel↗Merle↗Steinacker↗J. M↗Kern↗W. V↗…

Purpose Because simple symptom counts treat all symptoms as equally important and may not adequately capture the HRQoL impact of heterogeneous post-COVID-19 symptoms, we aimed to develop an HRQoL-anchored symptom severity score providing an interpretable measure of post-COVID-19 disease burden. Methods Baseline data from the population-based EPILOC and EPILOC Omicron surveys (adults aged 18-65 years) were used to develop a symptom-based severity score anchored to physical and mental HRQoL assessed with the SF-12. A two-stage modelling approach was applied to identify HRQoL-relevant symptoms and to derive symptom-specific weights for physical and mental component scores, incorporating 30 ordinal symptom severity variables. Symptom-specific weights were extracted to compute physical, mental, and composite severity scores. Score interpretation was examined using external reference measures, including EPILOC case status, self-reported health recovery, and functional consequences. Results A total of 19,004 participants (mean age 44.3 years, 59.6% female) were included. Sixteen symptoms contributed to the physical and eleven to the mental HRQoL score, with a limited subset accounting for most of the HRQoL loss. Severity scores were heavily right-skewed, with 50.6% of participants showing no measurable HRQoL impairment. Higher scores correlated with lower self-reported recovery, and increased probability of rehabilitation use and health-related changes in working time, supporting convergent and criterion-related validity. Conclusions This study introduces a transparent, HRQoL-anchored symptom severity score that measures graded post-COVID-19 burden beyond simple symptom counts. The score may be particularly suited for longitudinal assessment of recovery trajectories.

阅读与讨论 → 访问原文 →

02.

medRxiv (Medicine) 2026-06-16 DOI: HASH:3f270ea261d512e150c6fb255dffd515

Care Delivery Gap framework: a proof-of-concept patient-reported measure of guideline-referenced care-process omissions in sickle cell disease

作者:

Agbalalah↗Rowaiye↗

Abstract Background:Sickle cell disease (SCD) is concentrated in sub-Saharan Africa, where delivery of guideline-referenced care remains challenging. Current evaluation approaches rely largely on access indicators and clinical outcomes, which do not directly measure care delivery. We developed the Care Delivery Gap (CDG) framework, a patient-reported approach for identifying care-process omissions, and conducted a proof-of-concept study to assess feasibility and explore variation across income strata. Methods: We conducted a cross-sectional framework-development study involving a proof-of-concept sample of 52 individuals with SCD or caregivers recruited through clinics and moderated SCD communities across Africa, North America, and Europe between June 2025 and March 2026. The CDG framework assessed patient-reported omissions in specialist involvement, follow-up continuity, cardiovascular screening, and biochemical surveillance. Analyses were descriptive. Results: Substantial multi-domain care-process omissions were identified despite high reported healthcare engagement. Across geographic income strata, cardiovascular screening was reported by 4/35 (11%) LMIC versus 16/17 (94%) HIC participants, and regular follow-up within the preceding 12 months by 14/35 (40%) versus 16/17 (94%), respectively. High CDG scores, representing 1 omissions across three or four domains, occurred in 20/35 (57%) LMIC compared with 1/17 (6%) HIC participants. Similar disparities were observed across specialist review and vitamin B12 surveillance domains. Conclusion: A structured patient-reported framework identified multi-domain omissions in guideline-referenced SCD care, including among individuals reporting healthcare access. The divergence between access indicators and reported care delivery suggests that service contact alone may not reflect care quality. The framework provides a feasible foundation for future process-level quality measurement in high-burden settings.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2308.06035

Attention, not scale, drives human-AI alignment in multimodal language prediction

作者:

Viktor Kewenig↗Andrew Lampinen↗Samuel A. Nastase↗Christopher Edwards↗Quitterie Lacome D'Elascombe↗Akilles Rechardt↗Jeremy I Skipper↗Gabriella Vigliocco↗

Humans routinely draw on visual context to predict upcoming words. To what extent current vision-language models produce comparable behaviour is unclear. Here we placed five state-of-the-art pretrained systems side-by-side with 600 human participants in a web-based Visual-World Paradigm. On each of 100 six-second movie clips, models and participants received either text only or synchronised video and text and judged how likely a specified target word was to appear next; human eye movements were tracked throughout. Adding visual context increased model-human alignment in predictability ratings across all architectures (average Delta r = 0.18) with no impact of parameter size. When visual context was informative, transformer attention significantly increased alignment. Attention maps from two transformer models corresponded with human gaze, explaining up to 70% of the inter-participant variance when the scene contained informative cues. Notably, cross-modal attention reliably tracked anticipatory human fixations on semantic cues. These results suggest that current transformer-based vision-language models can approximate human behaviour exploiting visual context during language prediction - and that selective attention to informative cues, not sheer model scale, is the principal driver of this alignment.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11508

Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction

作者:

Yifan Xue↗Srimukh Prasad Veccham↗Saee Paliwal↗Tyler Shimko↗Micha Livne↗

arXiv:2606.11508v1 Announce Type: new Abstract: Accurate prediction of absorption, distribution, metabolism, and excretion (ADME) properties is critical to drug discovery, but remains challenging because ADME endpoints are noisy, interdependent, and often data-limited. We propose a molecular graph-transformer pretraining framework that combines chemistry-specific self-supervision with contrastive mutual information machine learning (cMIM). Our method encodes molecular graphs into latent variables, reconstructs SMILES strings from the graph-derived latent codes, and augments the contrastive objective with domain-specific self-supervised chemistry tasks. Rather than treating these tasks as auxiliary regularizers with separately tuned loss weights, we formulate reconstruction, contrastive discrimination, and chemistry-specific supervision as unit-weighted log-probability factors in a single probabilistic latent-variable objective. For fine-tuning, we propose a multi-task GNN readout architecture with task-specific multilayer perceptron heads, preserving shared representation learning while mitigating negative transfer and improving the modeling of heterogeneous, nonlinear task relationships. Across Biogen, ExpansionRX, and ChEMBL-MT, the resulting Contrastive KERMT pretraining improves over the KERMT baseline by 7.6%, 9.9%, and 9.5% respectively (averaged over significantly-improved endpoints). Adding ADME-adjacent molecules to the pretraining corpus further improves transfer, and the contrastive component sharpens chemically meaningful latent neighborhoods.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2604.21335

Sub-Token Routing for KV Cache Compression

作者:

Wei Jiang↗Wei Wang↗

Transformer inference often requires a large KV cache, especially for long-context language modeling and multimodal generation. Existing compression methods usually reduce cache cost by selecting, evicting, quantizing, or compressing cached tokens, or by reducing the visual-token sequence before language-model inference. We introduce sub-token routing, a KV-compression method that adds a finer control axis inside retained tokens. It splits each retained value vector into groups and keeps only selected groups, while leaving query and key states unchanged. The method is designed to work after token-level reduction. First, a token-reduction method determines which tokens are retained. Then, sub-token routing compresses the value states inside those retained tokens. Experiments under matched KV budgets show that adding sub-token routing improves token-level reduction performance in both LLM and VLM settings, including Quest on LLaMA-2-7B and Qwen2.5-7B, and FastV/VisionZip across LLaVA and Qwen-VL models. The gains are larger at smaller KV budgets, suggesting that value-group routing is especially useful when further token removal becomes costly. Overall, token-level reduction and sub-token routing provide complementary ways to reduce KV cost.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.13995

Dialogue SWE-Bench: A Benchmark for Dialogue-Driven Coding Agents

作者:

Brendan King↗Jeffrey Flanigan↗

AI coding agents have rapidly transformed software engineering, powering widely used interactive coding assistants. Despite their interactive real-world use, existing benchmarks evaluate them as fully-autonomous systems. In this work, we introduce Dialogue SWE-Bench, an automatic benchmark dataset for evaluating the ability of coding agents to resolve real-world software engineering problems through dialogue with a user. We design a novel, persona-grounded user simulator to support our task evaluation, and augment our task evaluation with automatic evaluations of dialogue quality. We also propose a new schema-guided agent, aimed at improving the dialogue capabilities of off-the-shelf coding agents, which improves over strong baselines by 3-14%. Our results indicate that better coding models do not always correspond to better dialogue models, suggesting that dialogue capability is a distinct and currently understudied dimension of coding agent performance.

阅读与讨论 → 访问原文 →

07.

Nature Medicine 2026-06-08 DOI: HASH:343c619d8269c65c96f2e2be8eb5bc08

Apitegromab for lean mass preservation during tirzepatide-induced weight loss: a randomized, double-blind, placebo-controlled phase 2 trial

作者:

Richard E. Pratley↗

Loss of lean mass in proportion to total weight loss is observed with incretin mimetic therapies such as tirzepatide and has the potential to adversely affect health and function. Apitegromab is an investigational, fully human monoclonal antibody that selectively inhibits myostatin activation and is, thereby, capable of increasing muscle mass. In the randomized, double-blind, placebo-controlled phase 2 EMBRAZE study, adults with overweight or obesity (n = 102) were randomized 1:1 to receive tirzepatide plus apitegromab (10 mg kg−1) or tirzepatide plus placebo. At week 24, apitegromab resulted in a least square mean (80% confidence interval (CI)) of 1.9 (1.2−2.7) kg less lean mass loss than placebo (P = 0.001), despite similar total body weight loss between groups, representing a 54.9% retention of lean mass relative to placebo. In participants receiving apitegromab, trough concentrations of apitegromab and total latent myostatin, a pharmacodynamic marker, both increased over time and reached a plateau after approximately 16 weeks. Incidence of adverse events (AEs) (% (95% CI)) was generally similar across apitegromab-treated participants and placebo-treated participants, with 39 of 51 (76% (63−86%)) and 36 of 51 (71% (57−81%)) participants experiencing an AE, respectively. Serious adverse events (SAEs) were balanced and experienced by one of 51 (2% (0−10%)) participants in each arm. In summary, this proof-of-concept study demonstrated that selective targeting of myostatin by apitegromab was well tolerated and effective in preserving lean mass when combined with tirzepatide. ClinicalTrials.gov identifier: NCT06445075 . In the phase 2 EMBRAZE study, participants receiving tirzepatide and apitegromab lost less lean mass compared to participants receiving tirzepatide and placebo.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2605.04853

Hybrid Iterative Neural Low-Regularity Integrator for Nonlinear Dispersive Equations

作者:

Zhangyong Liang↗Huanhuan Gao↗

arXiv:2605.04853v2 Announce Type: replace Abstract: We propose HIN-LRI, a hybrid framework that augments a classical numerical solver with a neural operator trained to correct the solver's structured truncation error. A base low-regularity integrator provides a consistent first-order approximation to nonlinear dispersive PDEs, while a lightweight neural network, operating on a low-dimensional latent manifold, learns the residual defect that analytical methods cannot close. An explicit time-step scaling on the neural correction ensures that its Lipschitz contribution remains $\mathcal{O}(\tau)$, yielding a Gronwall stability factor bounded uniformly in the step size and independent of the spatial resolution. The network is trained end-to-end through a solver-in-the-loop objective that unrolls the full iteration and penalises trajectory error in a Bourgain-type norm, aligning learning with multi-step solver dynamics rather than isolated one-step targets. Under stated assumptions, the global error satisfies $C(\varepsilon_{net}+\delta)\,\tau^\gamma\ln(1/\tau)$, where $\varepsilon_{net}$ measures the network approximation quality and $\delta$ the training shortfall. Experiments on three dispersive benchmarks with rough data show that HIN-LRI improves accuracy over analytical integrators, splitting methods, and neural PDE surrogates, with stable spatial refinement, effective out-of-distribution transfer, and modest online overhead.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15972

Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning

作者:

Ji Feng↗Zhouxing Shi↗

With large language models (LLMs) increasingly applied to mathematical reasoning, formal proof assistants such as Lean can be leveraged to verify reasoning outputs with machine-checkable rigor, enabling use cases such as answer selection in test-time scaling with K sampled candidate answers. However, employing Lean requires that LLM outputs, originally in natural language, first be formalized. Existing Lean-based answer-selection work uses an autoformalization model to generate a formal statement in Lean for each candidate answer independently, incurring a significant computational cost. We propose BASE, a base-and-edit pipeline that formalizes a single base candidate per problem and derives the remaining K-1 statements by editing the answer expression in place. To facilitate this, we train a rewriter model LEANSCRIBE to localize the answer in the base formalization and generate a reusable edit function for the other K-1 candidates. BASE simultaneously improves selection accuracy and reduces formalization cost - a Pareto improvement that holds on all 12 (dataset, solver) configurations across four benchmarks and three solvers, cutting autoformalizer calls by about 5x at K=8, with the reduction expected to become larger as K grows. Code is available at https://github.com/ucr-rai/base-and-edit.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14153

Encoder Winners Do Not Reliably Transfer Across VLA Backbone Scale: A Frozen-Backbone Grafting Diagnostic

作者:

Qingping Zeng↗Fei She↗

Vision-language-action (VLA) policies typically inherit their vision encoder from upstream VLM releases, but it is unclear whether an encoder choice validated on a small VLA transfers to a larger backbone. We introduce a frozen-backbone grafting diagnostic: the vision tower of a released VLA is replaced by a candidate encoder under a fixed protocol (adaptive average pooling, LayerNorm, and a single trainable linear projector), with the language model and action expert frozen. Across four encoders, two LIBERO suites, two backbones (SmolVLA-450M and $\pi_{0.5}$-3.3B), and two-to-three seeds per cell (40 main grafting runs plus native, LoRA, pooling, and zero-/shuffled-image controls, all scored by offline action MSE), the small-backbone winner does not reliably select the large-backbone top tier: SigLIP is best on SmolVLA across both suites, while on $\pi_{0.5}$ DINOv2-small leads the spatial suite and the object suite is a seed-sensitive near-tie band; three of the four backbone-suite comparisons (and 11 of 12 seed-level cells) support backbone-dependent rankings. The grafting wrapper is itself non-neutral with opposite sign across backbones (+45-56% MSE on the SmolVLA native tower, -50-52% on $\pi_{0.5}$), so all conclusions are conditional on the fixed grafting protocol. We position frozen grafting as a cheap target-backbone diagnostic to run before committing to an encoder at scale, not as a closed-loop deployment claim.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17601

Test-Time Training for Robust Text-Guided Open-Vocabulary Object Counting

作者:

Hao-Yuan Ma↗Yuda Zou↗Li Zhang↗Yongchao Xu↗

Text-guided Open-vocabulary Object Counting (TOOC) enables counting arbitrary object categories specified by text prompts, offering substantially greater flexibility than conventional closed-set counting. However, existing TOOC methods are developed and evaluated primarily on ideal images, while real-world scenes often suffer from adverse conditions such as rain, fog, darkness, and sensor noise, which severely degrade visual quality and impair vision-language alignment. To bridge this gap, we introduce Robust-TOOC, the first benchmark for evaluating TOOC under diverse corruption conditions, which covers six representative degradation types: rain, fog, darkness, Gaussian noise, salt-and-pepper noise, and mixed corruption. To improve robustness while preserving the original counting architecture, we propose Dual-TTT, a dual-architecture test-time training framework for TOOC. Specifically, during test-time training, Dual-TTT updates only the Text-guided Lightweight Denoising module (TL-Denoiser), while keeping the original counting network frozen. Inspired by diffusion models, the TL-Denoiser is optimized to remove corruption-aware noise from image representations under degraded conditions. Since only the TL-Denoiser is trained at test time, Dual-TTT is annotation-free and can be seamlessly integrated into existing TOOC models without modifying their original architecture. Extensive experiments on multiple recent TOOC baselines demonstrate the effectiveness of our method.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11712

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

作者:

Youwang Deng↗

User-side memory in LLMs is typically scored as a single "personalization" capability: given a user's history, is the output more user-aware? We show this aggregate metric hides opposite-direction failures. Memory factorises into at least three orthogonal axes – behavioral consistency (style, voice), factual presence (recall facts in history), and factual absence (abstain when a fact is absent) – and no single substrate wins all three. Comparing per-user gamma-LoRA (a small LoRA adapter trained on each user's history; gamma denotes per-user, not per-task) against BGE-large dense top-K retrieval on a controlled 50-user synthetic corpus and a real-data probe (LaMP-3), we find gamma-LoRA decisively wins behavioral style while RAG decisively wins factual absence – and the same query-projection cells in attention layers 21-35 causally load-bear both effects in opposite directions (zeroing those LoRA weights raises absence-probe TPR by +33 pp and drops presence-probe TPR by 20 pp). On the more heavily RLHF-tuned Llama-3.1-8B-Instruct the asymmetry strengthens, not heals: parametric memory's behavioral advantage collapses while its absence-calibration deficit against retrieval widens – an alignment tax on parametric user-memory. On real-data LaMP-3, gamma-LoRA underperforms a majority baseline; a 9-condition mitigation sweep diagnoses this as instruction-following collapse, not substrate failure (a 9x2 cross-product shows the eval-time {1..5} logit mask drives main_acc to >=0.995 on every recipe), and the best training-time fix replicates bit-identically on Llama. Finally, substrate-selection routing is question-classification, not calibration: a 110M DistilBERT on the question text alone beats every logit-based router. We contribute the diagnostic framework, the diagnosed real-data negative, the alignment-tax replication, and the routing-as-classification finding.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.02995

Patcher: Post-Hoc Patching of Backdoored Large Language Models

作者:

Anjun Gao↗Yueyang Quan↗Yufei Xia↗Zhuqing Liu↗Minghong Fang↗

arXiv:2606.02995v2 Announce Type: replace-cross Abstract: Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existing defenses often require comprehensive attack information or multiple triggered examples, making them impractical when defenders only observe a single reported failure case without knowing whether it stems from a backdoor attack or a natural alignment bug. This paper presents Patcher, a post-hoc defense framework that repairs backdoored language models using only a single reported failure case and the model parameters. Patcher operates in two stages. First, it localizes backdoor triggers by computing response-conditioned gradient-based saliency scores and applying adaptive clustering to separate triggers from benign context. Second, it patches the model through a constrained fine-tuning objective that breaks the trigger-response association while preserving benign-task utility and robustness to non-triggered jailbreak attacks through KL-divergence constraints. We conduct extensive evaluations across multiple backdoor attack strategies and demonstrate that Patcher successfully localizes triggers and neutralizes backdoors while maintaining model utility. We further show robustness against adaptive attacks designed to evade our defense. This work represents a significant step toward practical defenses against training-time attacks in deployed language models.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15601

SCAN: A Decision-Making Framework for Effective Task Allocation with Generative AI

作者:

Fendi Tsim↗Alina Gutoreva↗

arXiv:2606.15601v1 Announce Type: cross Abstract: We introduce SCAN – a human-centric decision-making framework to facilitate learners for effective task allocation with Generative Artificial Intelligence (GenAI) based on Vygotsky's Zone of Proximal Development and Metacognition. In SCAN, we systematize and formalize AI-human interaction by introducing a task-identification approach with four "sub-zones": Substitute, Complement, Aid, and Non-negotiable. After describing the four sub-zones, we demonstrate how SCAN framework can be applied for knowledge workers in the workplace and students in education to metacognitively "scan" their use of Generative AI. We then discuss how such framework can be related to cognitive load theory, cognitive offloading, sycophancy, three decision-making modes in human-AI interactions (automation, augmentation, and collaboration), future of work such as upskilling and deskilling, and how it accounts for both human-human and human-AI learning. We propose that SCAN offers a great starting point before discussing whether GenAI complements or replaces our abilities when completing a task, with a general objective of sustaining lifelong learning, and a specific goal of reaching hybrid intelligence.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2603.27450

FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies

作者:

Chenxiao Gao↗Edward Chen↗Tianyi Chen↗Bo Dai↗

arXiv:2603.27450v2 Announce Type: replace Abstract: Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation. However, efficient reinforcement learning (RL) upon these policies remains a challenge due to the lack of explicit log-probabilities for vanilla policy gradient estimators. While numerous attempts have been proposed to address this, the field lacks a unified perspective to reconcile these seemingly disparate methods, thus hampering ongoing development. In this paper, we bridge this gap by introducing a comprehensive taxonomy for RL algorithms with diffusion/flow policies. To support reproducibility and agile prototyping, we introduce a modular, JAX-based open-source codebase that leverages JIT-compilation for high-throughput training. Finally, we provide systematic and standardized benchmarks across Gym-Locomotion, DeepMind Control Suite, and IsaacLab, offering a rigorous side-by-side comparison of diffusion-based methods and guidance for practitioners to choose proper algorithms based on the application. Our work establishes a clear foundation for understanding and algorithm design, a high-efficiency toolkit for future research in the field, and an algorithmic guideline for practitioners in generative models and robotics. Our code is available at https://github.com/typoverflow/flow-rl.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15333

Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning

作者:

Zirui Pang↗Chenlong Zhang↗Haosheng Tan↗Zhuoran Jin↗Jiaheng Wei↗Zixin Zhong↗

LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility. Recent RL-based methods such as RULE reformulate unlearning as learning a refusal behavior, but their on-policy optimization repeatedly samples from the same forget and retain/boundary prompts throughout training. We identify a critical inefficiency in this process: easy cases quickly converge and provide little useful gradient signal, while hard cases near the forget/retain boundary continue to produce low-reward rollouts that are discarded after a single use. To address this issue, we propose ReRULE, an off-policy replay enhancement for reinforcement unlearning. ReRULE stores low-reward hard-case rollout groups in a replay buffer during early GRPO training and reuses them in later stages through importance-sampled off-policy updates, redirecting computation toward boundary cases that still require learning. Theoretically, we show that ReRULE yields a tighter hard-case convergence bound than pure on-policy RULE. Empirically, ReRULE improves MUSE-Books Retain Quality from 46.3 to 56.2 while adding only 5–11% training time across benchmarks. Its limited improvement on the simpler TOFU setting further supports the intended conditional behavior: replay is most beneficial when the hard/easy disparity is pronounced.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16944

A Causal Model of Theory of Mind in Conflict for Artificial Intelligence

作者:

Nikolos Gurney↗

arXiv:2606.16944v1 Announce Type: new Abstract: Theory of mind (ToM), the capacity to ascribe mental states to others and use those ascriptions for prediction and inference, is widely assumed to be essential for effective human-machine integration. Existing AI-ToM models address how to mentalize, but leave the question of when largely unaddressed. The central question is: under what situational and agent-level conditions is ToM engagement causally warranted in conflict? This paper presents a structural causal model formalized as a directed acyclic graph (DAG), treating ToM as a mechanism activated by situational and agent-level conditions rather than as an always-on capacity. The model specifies four exogenous variables capturing situational and agent-level conditions, five endogenous mediators, and a mechanistic ToM node producing engagement states through three distinct causal pathways: a tractability pathway, a reasoning-depth pathway, and an enabling-cause pathway. The primary outcome is epistemic accuracy, which decouples social reasoning from behavioral policy and generalizes across social phenomena beyond conflict. The framework gives AI systems a principled, resource-rational decision procedure for mentalizing, with implications for efficiency, trust, and the development of robust artificial social intelligence. Simulation validation, empirical human-machine teaming studies, and ethical considerations arising from conflict-optimized mentalizing are discussed.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.17990

WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics

作者:

Madhav Kanda↗Sharad Agarwal↗Rodrigo Fonseca↗Alok Gautam Kumbhare↗Pedro Las-Casas↗

arXiv:2602.17990v2 Announce Type: replace Abstract: Multi-agent LLM systems that generate structured workflows from natural-language requests are now deployed in production across cloud automation, DevOps, and enterprise process orchestration. Operating such systems exposes a recurring change-management problem. Routine updates, such as re-running the same input, swapping the underlying LLM, or refactoring an agent's prompt or orchestration code, frequently produce workflows that differ substantially from previously validated references. Engineers are then left without a principled way to decide whether a change is safe to ship. Automatic workflow evaluation is the natural tool for answering this question. In practice, however, metric scores are poorly calibrated, and a numeric change rarely communicates the severity of the underlying degradation. We introduce WorkflowPerturb, a controlled benchmark for studying workflow evaluation metrics by applying realistic, graded perturbations to golden workflows. WorkflowPerturb contains 4,973 golden workflows and 44,757 perturbed variants across three perturbation types (Missing Steps, Compressed Steps, and Description Changes), each applied at severity levels of 10%, 30%, and 50%. We benchmark multiple metric families and analyze their sensitivity and calibration using expected score trajectories and residuals. Our results characterize systematic differences across metric families and support severity-aware interpretation of workflow evaluation scores in change-management settings. Our dataset will be released upon acceptance.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13239

ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm

作者:

Jiaxin Ai↗Tao Hu↗Xuemeng Yang↗Shu Zou↗Hairong Zhang↗Daocheng Fu↗Yu Yang↗Hongbin Zhou↗Nianchen Deng↗Pinlong Cai↗Zhongyuan Wang↗Botian Shi↗…

Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces. In this work,we identify the Component Object Model (COM) as a unified executable abstraction, proposing COM-as-Action: a new paradigm that reframes professional software interaction as deterministic program synthesisrather than sequential visual control. To validate this paradigm in the most demanding environments, weintroduce ComCADBench, the first benchmark for agents operating real industrial CAD software. Ourexperiments reveal a substantial paradigm gap: frontier proprietary models achieve near-zero successunder GUI-based interaction, whereas COM-based execution yields substantial immediate gains. Tobridge the remaining gap between syntactic correctness and geometric accuracy, we develop ComActor, aself-correcting agent trained through a progressive three-stage framework, alongside ComForge, a scalableplatform for large-scale training in Windows containers. Extensive experiments show that ComActorachieves state-of-the-art performance on ComCADBench, with strong resilience in long-horizon taskswhere baselines collapse, and generalizes to external CAD benchmark.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.08867

Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework

作者:

Aman Gupta↗Kevin Rossell↗Edesio Alcoba\c{c}a↗Jose Chrystian Lima Pacheco↗Carolina Baptista de Lima↗Shao Tang↗Luiz Paulo Rabachini↗Luis Moneda↗Herbert Fei↗Daniel Silva↗Rohan Ramanath↗

The rapid rise in LLM capabilities has made AI agents increasingly viable across a broad range of tasks. Among the most promising applications is building production-ready customer-facing agents, a challenge that demands coordinated excellence in evaluation methodology, context engineering, training, and online measurement. Yet these critical pillars are typically developed in isolation, creating blind spots that only surface after deployment. In this paper, we present a unified framework that bridges offline development with online impact for customer support AI agents at Nubank, a company with 100M+ users. Our approach integrates several key components: (1) structured context engineering tailored to customer support agents, (2) systematic human-in-the-loop prompt iteration, (3) rigorous LLM judge evaluation with measured inter-rater agreement and GEPA optimization for consistency, and (4) ideation-to-production validation. A central insight is that evaluation-pipeline quality directly determines iteration velocity. We present results from five production deployments spanning distinct domains: card delivery, debt management, credit-limit support, card management, and product explanation. These deployments deliver consistent customer-satisfaction gains while substantially accelerating iteration. In our card-delivery deployment, large-scale A/B testing yields a 37 percentage-point improvement in AI transactional Net Promoter Score and a 29 percentage-point gain in self-service rate over prior agent variants, alongside a strong correlation between offline simulation metrics and online outcomes, demonstrating that eval-driven development reliably predicts production impact. On most use cases, AI satisfaction reaches within a few percentage points of expert human agents.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2511.12024

Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging

作者:

Jose Reinaldo Cunha Santos A V Silva Neto↗Hodaka Kawachi↗Yasushi Yagi↗Tomoya Nakamura↗

Lensless imaging reconstructs scenes from highly multiplexed measurements, resulting in a severely ill-posed inverse problem. In this work, we identify a fundamental trade-off between measurement consistency, perceptual quality, and inference speed across lensless reconstruction paradigms. Traditional methods favor consistency but produce perceptually degraded results, supervised approaches achieve high-quality reconstructions with fast inference but may violate physical constraints, and diffusion-prior methods achieve high perceptual quality and consistency–particularly when structured constraints such as range-null decomposition are used–but remain slow due to iterative sampling. Motivated by this observation, we propose Null-Space Diffusion Distillation (NSDD), a single-pass reconstruction model that distills structured diffusion-prior inference into an efficient feed-forward network. NSDD learns to produce high-quality reconstructions that preserve measurement consistency while avoiding costly iterative sampling. Experimental results demonstrate that NSDD achieves perceptual quality and consistency competitive with diffusion-prior methods, while providing significantly faster inference and offering a favorable balance across all three objectives. Furthermore, ablation experiments show that distilling the range–null decomposition improves reconstruction quality and robustness over unstructured full-reconstruction distillation, including on unseen real scenes. These results highlight the potential of structure-aware distillation for efficient lensless imaging. Code is available at github.com/JRCSAVSN/NullSpaceDiffusionDistillation.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18469

Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion

作者:

Somjit Nath↗Jackson J Cone↗Derek Nowrouzezahrai↗Samira Ebrahimi Kahou↗

arXiv:2606.18469v1 Announce Type: cross Abstract: Neuroscientific research has revealed that the brain encodes complex behaviors by leveraging structured, low-dimensional manifolds and dynamically fusing multiple sources of information through adaptive gating mechanisms. Inspired by these principles, we propose a novel reinforcement learning (RL) framework that encourages the disentanglement of dynamics-specific and reward-specific features, drawing direct parallels to how neural circuits separate and integrate information for efficient decision-making. Our approach leverages locally linear embeddings (LLEs) to capture the intrinsic, locally linear structure inherent in many environments, mirroring the local smoothness observed in neural population activity, while concurrently deriving reward-specific features through the standard RL objective. An attention mechanism, analogous to cortical gating, adaptively fuses these complementary representations on a per-state basis. Experimental results on benchmark tasks demonstrate that our method, grounded in neuroscientific principles, improves learning efficiency and overall performance compared to conventional RL approaches, highlighting the benefits of explicitly modeling local state structures and adaptive feature selection as observed in biological systems.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11836

Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

作者:

Haoning Xu↗Zhaoqing Li↗Huimeng Wang↗Youjun Chen↗Chengxi Deng↗Mengzhe Geng↗Xunying Liu↗

arXiv:2606.11836v1 Announce Type: cross Abstract: This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. More fine-grained, mixed sparsity pruning by layer-level varying number of parameter clusters is also explored. Experiments conducted on the LibriSpeech dataset suggest that when operating with pruning sparsity of 50% on HuBERT-large, consistent WER reductions of 27.73%/18.61% absolute (34.37%/21.91% relative) over the magnitude-based pruning were obtained on the test-clean and test-other subsets before fine-tuning and 0.19%/0.79% absolute (3.36%/4.62% relative) after fine-tuning with only 3 epochs. Similar WER reductions of 2.86%/5.02% absolute (59.21%/55.29% relative) were observed against magnitudebased pruning on Whisper-large-v3 at 10% sparsity, all with no significant WER increase relative to the uncompressed baseline.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15637

HAPI-EP: Towards Hybrid, Adaptive, and Predictive Digital Twins of Cardiac Electrophysiology

作者:

Sumeet Vadhavkar↗Xiajun Jiang↗Yubo Ye↗Maryam Toloubidokhti↗Linwei Wang↗

arXiv:2606.15637v1 Announce Type: new Abstract: A digital twin (DT) of a patient-specific heart offers significant potential in personalized medicine. However, its rapid and dynamic adaptation to an individual's live data and its predictive capability after adaptation remains central challenges. We examine this challenge from its two building blocks: DT formulation where mechanistic and data-driven models show competing merits and limitations, and DT optimization strategies that are largely driven by a reconstruction objective leading to un-identifiable models. We address both bottlenecks via HAPI – an AI framework for building hybrid, adaptive, and predictive DTs with three key enablers. First, HAPI constructs a physics-integrated gray-box model in which an interpretable mechanistic backbone is augmented by a neural component that models its residual to the observed data. Second, rather than attempting to pre-encode all possible variations in a static hybrid model, HAPI enables rapid on-the-fly adaptation of the hybrid model to few-shot live data, achieved by feedforward meta-learners realizing amortized inference of both mechanistic and neural parameters of the hybrid model trained with predictive objectives. Finally, we show that this adaptivity corresponds to the construction of a conditional generative model (i.e., the hybrid DT) that endows it with theoretical identifiability and thus strong performance in predictive scenarios. We demonstrate the proof-of-concept of HAPI in cardiac electrophysiology using a hybrid monodomain model with mechanistic reaction kinetics and neural graph diffusion. Across synthetic and real-data studies, we show that HAPI's mechanistic-neural hybridization and predictive adaptation are critical for obtaining identifiable DTs with strong predictive and out-of-distribution capabilities.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2602.07698

On Sequence-to-Sequence Models for Automated Log Parsing

作者:

Adam Sorrenti↗Andriy Miranskyy↗

Context: Log parsing is a critical standard operating procedure in software systems, enabling monitoring, anomaly detection, and failure diagnosis. However, automated log parsing remains challenging due to heterogeneous log formats, distribution shifts between training and deployment data, and the brittleness of rule-based approaches. Objectives: This study aims to systematically evaluate how sequence modelling architecture, representation choice, sequence length, and training data availability influence automated log parsing performance and computational cost. Methods: We conduct a controlled empirical study comparing four sequence modelling architectures: Transformer, Mamba state-space, monodirectional LSTM, and bidirectional LSTM models. In total, 396 models are trained across multiple dataset configurations and evaluated using relative Levenshtein edit distance with statistical significance testing. Results: Transformer achieves the lowest mean relative edit distance (0.111), followed by Mamba (0.145), mono-LSTM (0.186), and bi-LSTM (0.265), where lower values are better. Mamba provides competitive accuracy with substantially lower computational cost. Character-level tokenization generally improves performance, sequence length has negligible practical impact on Transformer accuracy, and both Mamba and Transformer demonstrate stronger sample efficiency than recurrent models. Conclusion: Overall, Transformers reduce parsing error by 23.4%, while Mamba is a strong alternative under data or compute constraints. These results also clarify the roles of representation choice, sequence length, and sample efficiency, providing practical guidance for researchers and practitioners.

阅读与讨论 → 访问原文 →