探索全球前沿学术脉络

01.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.20009

The use of Peres lattices in periodically driven systems

作者:

Luk\'a\v{s} Honsa↗Jan St\v{r}ele\v{c}ek↗Jakub Novotn\'y↗Pavel Cejnar↗

arXiv:2606.20009v1 Announce Type: new Abstract: We demonstrate the strength of the method of Peres lattices in periodically driven quantum systems. The method, which has previously been used mostly in stationary systems, enables us to efficiently detect resonances in the driven system, to monitor the onset of chaos, and to recognize critical properties of the Floquet modes. It also allows quick comparisons of the spectra of Floquet modes for various driving Hamiltonians and transparent tests of the iterative approximation techniques based on effective stationary Hamiltonians.

阅读与讨论 → 访问原文 →

02.

arXiv (quant-ph) 2026-06-24 DOI: arXiv:2606.24803

Introduction to matrix-product states and tensor networks

作者:

Gr\'egoire Misguich↗

arXiv:2606.24803v1 Announce Type: cross Abstract: These notes provide an introduction to tensor-network methods in quantum many-body physics, with an emphasis on matrix-product states (MPS). They develop the basic tensor-network language, including graphical notation, virtual indices, bond dimensions, gauge freedom, canonical forms, QR and singular-value decompositions, and the role of entanglement in controlling the efficiency of the representation. The main MPS algorithms are then introduced, including contractions, correlation functions, matrix-product operators, DMRG, and time-evolution methods. The notes also briefly discuss projected entangled-pair states (PEPS) as a higher-dimensional generalization of MPS, together with the basic ideas behind approximate PEPS contraction. Finally, tensor-network representations of mixed states, quantum channels, and Lindblad dynamics are presented, with applications to thermal states and open quantum systems. The presentation is accompanied by short Julia code examples based on ITensor, ITensorMPS, and TensorMixedStates. These notes were written for the 9th Les Houches Summer School on Computational Physics: Open Quantum Systems, held in June 2026.

阅读与讨论 → 访问原文 →

03.

medRxiv (Medicine) 2026-06-10 DOI: HASH:0930667e05386cfba4cc33e6ee6fa917

Impact of Early Treatment on Symptom Improvement and Procedural Events among Men with BPH and Bothersome Lower Urinary Tract Symptoms: A Contemporary Analysis of the American Urological Association Quality (AQUA) Registry

作者:

Ernandez↗Najafi↗Roehrborn↗C. G↗Lerner↗L. B↗

PURPOSE: As the armamentarium of BPH therapies continues to expand, it remains imperative to maximize patient satisfaction and minimize decisional regret. We sought to determine the impact of time from BPH diagnosis to index treatment on symptom improvement and subsequent procedural events. MATERIALS AND METHODS: We queried the American Urological Association Quality Registry for men [&ge;] 40 years old with BPH, available IPSS data, and no receipt of prior BPH treatment. Index treatment included medication, surgery, or minimally invasive surgical therapy (MIST). Outcomes included IPSS over 3 years of follow-up, change in percentage of mild lower urinary tract symptoms (LUTS) by 3 months, and time to procedural event. Patients were stratified by time from index diagnosis to treatment by 3 years. Outcomes were compared across time-to-treatment cohorts with appropriate statistical tests with p < 0.05 as significant. RESULTS: 43,919 patients met criteria with 19,642 pursuing treatments. Patients pursued treatment at comparably lower baseline IPSS compared to prior prospective series. Patients undergoing surgery and MIST had significantly higher baseline IPSS, while medical comorbidities were significantly more common among men initiating pharmacotherapy. Early surgery and MIST were associated with significant improvement in IPSS within 6-12 months and an increase in mild LUTS by 3 months. All forms of early treatment were associated with delayed time to procedural events, including catheterization and fulguration. CONCLUSIONS: Early procedural intervention for BPH is associated with early symptom improvement and delayed time to procedural events among real-world, contemporary practice.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12497

$\mu$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models

作者:

Egor Cherepanov↗Nikita Kachaev↗Daniil Zelezetsky↗Aydar Bulatov↗Artem Pshenitsyn↗Yuri Kuratov↗Alexey Skrynnik↗Aleksandr I. Panov↗Alexey K. Kovalev↗

arXiv:2606.12497v1 Announce Type: new Abstract: Vision-language-action (VLA) models predict chunks of future actions from the current observation, an assumption that fails under partial observability, where decisions depend on information no longer visible. Existing memory-augmented VLAs simultaneously introduce recurrence, retrieval, compression modules, auxiliary objectives, hierarchical memory, or task-specific architectural changes, so the contribution of recurrence itself remains entangled with surrounding machinery. We present a controlled isolation study of recurrence in a strong pretrained VLA backbone. Our formulation augments the transformer with a small set of learnable memory tokens carried across timesteps and updated through self-attention, trained end to end with truncated backpropagation through time, with no auxiliary losses and no architectural changes. We instantiate this as $\mu$VLA, a family of OpenVLA-OFT variants parameterized by memory width m, TBPTT length K, and the memory update rule (cross-step gradients or a detached EMA), so that recurrence is the only varying factor. On MIKASA-Robo, $\mu$VLA improves average success rate on five training tasks from 0.42 to 0.84 at the strongest setting and reaches 0.23 on held-out tasks with the same memory structure versus 0.07 for the memoryless baseline. On tasks requiring different memory structure, performance remains near baseline. On LIBERO, the strongest recurrent variant achieves 96.2% average success, indicating no regression under full observability. We interpret these results as a calibration of the capability envelope of minimal in-backbone recurrence, identifying the regime in which it is sufficient and the regime where additional memory structure is required. Demos and videos can be found in https://avanturist322.github.io/mu-vla/.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18327

Self-CTRL: Self-Consistency Training with Reinforcement Learning

作者:

Itamar Pres↗Laura Ruis↗Melat Ghebreselassie↗Belinda Z. Li↗Jacob Andreas↗

arXiv:2606.18327v1 Announce Type: cross Abstract: Language models (LMs) that faithfully describe their own behavior can more easily be audited, understood, and trusted by users. This paper describes Self-Consistency Training with Reinforcement Learning (Self-CTRL), a method that optimizes for consistency between a LM's self-explanations and behavior on related inputs by updating explanations to better predict behavior or updating behavior to better match explanations. We apply our method in two domains. First, we study a formal probabilistic reasoning task in which LMs must learn to imitate a family of biased samplers and evaluated on their ability to report the associated biases. We find that consistency training improves the correlation between self-reported and behaviorally-measured latent biases from $R^2=0.24$ to $R^2=0.64$ on a set of held-out distributions, matching the generalization of direct ground-truth supervision. Second, we study a constitutional AI domain in which LMs must describe when they will refuse or comply with user requests. Here, Self-CTRL produces rules that faithfully describe the model's behavior on held-out requests, improving the refusal predictions of a third-party auditor model from $36\%$ to $92\%$. In the other direction, behavior updates improve alignment, reducing HarmBench failure rate from $15.0\%$ to $0.5\%$ without substantially increasing refusal on harmless prompts. By aligning explanations and behavior, our work provides a general recipe for training AI models to be safer, more transparent, and more controllable.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14389

MooMIns – Monocular 3D Reconstruction and Object Pose Estimation from Multiple Instances

作者:

Robert Langend\"orfer↗Markus Hillemann↗Markus Ulrich↗

Simultaneous 3D reconstruction and 6D object pose estimation from a single monocular image is an inherently ill-posed problem. In industrial settings, however, multiple instances of an object are often randomly arranged in bins, implicitly providing several views of the same object within a single image. We show that this implicit multi-view geometry can be exploited to simultaneously reconstruct the object in 3D and estimate the 6D pose of each visible object instance. We present MooMIns, a new Gaussian-splatting-based approach that inverts the original Gaussian splatting formulation: instead of rendering a single scene from multiple cameras, we render multiple object instances from a single camera. Our method is initialized with SAM3 instance segmentation masks and a modified Structure from Motion (SfM) pipeline. In contrast to learned monocular depth estimation, we perform true geometry-based reconstruction from image evidence, avoiding hallucinations caused by training data priors. We evaluate MooMIns on synthetic and real bin-picking scenarios, and demonstrate accurate reconstruction of previously unseen objects as well as reliable pose estimation of individual instance

阅读与讨论 → 访问原文 →

07.

arXiv (math.PR) 2026-06-18 DOI: arXiv:2606.18458

Stable size-biasing and the positive scale-mixture order of generalized Gaussian laws

作者:

Domingos S. P. Salazar↗

arXiv:2606.18458v1 Announce Type: new Abstract: Let $X_r\sim N_r(0,1)$ be the centered unit-scale generalized Gaussian random variable with density proportional to $\exp(-|x|^r/2)$. We prove that, for $p,q>0$, there exists a strictly positive random variable $V$, independent of $X_q$, such that $X_p\stackrel{d}{=}VX_q$ if and only if $p\le q$. Moreover, the law of $V$ is unique. For $pq$, the required Mellin quotient, viewed as the candidate characteristic function of $\log V$, is unbounded by Stirling's formula, and hence cannot be a characteristic function. The factor laws form a multiplicative cocycle, $V_{p,r}\stackrel{d}{=}V_{p,q}V_{q,r}$, for $p\le q\le r$, where the factors on the right-hand side are independent copies. Thus the Mellin quotient isolated by Dytso, Bustin, Poor and Shamai is realized constructively throughout the $p

阅读与讨论 → 访问原文 →

08.

bioRxiv (Bioinfo) 2026-06-18 DOI: HASH:2e76c8e1562952ec829b18fc544963dd

Looking beyond stereotyped neuron structures reveals links between beading and morphological rearrangements in aging phenotypes.

作者:

Gomez↗Nguyen↗Lagergren↗Flores↗San Miguel↗

Understanding how neuronal morphology changes during aging and acute stress is essential for elucidating mechanisms of neurodegeneration. The highly branched PVD neuron of Caenorhabditis elegans provides a powerful model for studying dendritic remodeling and degeneration-associated phenotypes such as dendritic beading. However, the complexity of this arbor presents substantial challenges for automated segmentation and quantitative analysis. In this study, we adapted a convolutional neural network (CNN)-guided region growing framework for automated dendrite tracing, coupled with two topology-based algorithms for categorizing dendritic segments by branching degree. The segmentation algorithm achieved high accuracy relative to manual tracing, with a median Dice coefficient of 0.82, while reducing analysis time by approximately tenfold. Automated dendrite categorization demonstrated strong agreement with manual annotations across branching orders, though position-based mapping performance declined with age due to progressive morphological distortion. Leveraging this platform, we investigated mechanistic differences in dendritic beading patterns observed during aging and cold shock. Consistent with prior work, aging was associated with decreased inter-bead spacing, whereas cold shock produced increased bead dispersion with stress severity. Structural analysis revealed that these trends were not driven by dendritic pruning or reduced arbor complexity. Instead, while a traditional anatomically unflexible paradigm falsely implicated lower-degree dendrites as highly vulnerable, our branching-informed framework revealed that age-dependent beading is fundamentally dictated by a segments history of successive branching events. Conversely, acute cold shock triggered systemic beading that expanded across all dendritic orders in a severity-dependent manner. Together, these findings demonstrate that chronic aging and acute stress engage distinct degenerative pathways (compartment-specific lineage vulnerability versus global architectural collapse) rather than gross morphological loss, as well as highlighting the need for paradigms that enable reliable analysis of changing morphologies.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12828

Topical Phase Transitions in Artificial Intelligence Research: Large-Scale Evidence and an Early-Warning Signature for Emerging Topics

作者:

Rasul Khanbayov↗Hasan Kurban↗

arXiv:2606.12828v1 Announce Type: new Abstract: Do research topics in artificial intelligence grow gradually, or do they advance through abrupt, detectable jumps? Analyzing 80,814 accepted main-track papers from five premier AI conferences (ACL, CVPR, ICLR, ICML, NeurIPS) spanning 2017 to 2025, we show major AI topics advance through topical phase transitions: remaining marginal for years, then surging across venues within one to three years. Large language models became the dominant cross-venue topic by 2025, diffusion models rose with comparable abruptness, and language-model methods crossed into computer vision via vision-language models, whereas reinforcement learning compounded smoothly, distinguishing genuine phase transitions from ordinary growth. This structure is our primary contribution: a large-scale, cross-venue characterization of how AI research reorganizes. We then ask whether a transition leaves a detectable footprint before it peaks. We define an early-warning signature, four publication-dynamics criteria frozen on 2017-2021 data, and evaluate it out of sample on 2023-2025 transitions, obtaining a precision of 27% and recall of 63% against a 13.5% base rate. Applied to 2025 data, the signature flags reasoning and test-time compute, agentic AI, multimodal LLMs, retrieval-augmented generation, and world models as topics to monitor over 2026-2028. The source code is also publicly available on GitHub at https://github.com/KurbanIntelligenceLab/ai-phase-transitions.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16497

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

作者:

Dayuan Fu↗Mohan Jiang↗Tongyu Wang↗Dian Yang↗Jiarui Hu↗Liming Liu↗Jinlong Hou↗Pengfei Li↗

GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective. We present daVinci-kernel, a reinforcement learning framework that couples skill discovery with skill exploitation through a dynamically evolving skill library. daVinci-kernel jointly trains three agents sharing one LLM backbone: a Skill Selection Agent that retrieves relevant techniques via BM25 and LLM reranking, a Policy Agent that generates multi-turn CUDA/Triton kernels conditioned on selected skills, and a Skill Summary Agent that distills successful rollouts into reusable skills. Candidate skills are added only after execution-based verification confirms reproducible speedups. All three agents share a single LLM backbone, are initialized via a structured SFT cold start on diversity-filtered data, and are then jointly optimized end-to-end with multi-turn REINFORCE and per-agent advantage estimation. On KernelBench, daVinci-kernel-14B achieves 37.2%, 70.6%, and 32.2% on Level 1, Level 2, and Level 3 under the Fast$_1$ threshold, outperforming the strongest prior RL-trained model, Dr.Kernel-14B.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.07591

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

作者:

Wanghan Xu↗Shuo Li↗Tianlin Ye↗Qinglong Cao↗Yixin Chen↗Hengjian Gao↗Yiheng Wang↗Qi Li↗Kun Li↗Sheng Xu↗Shengdu Chai↗Fangchen Yu↗…

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17887

AI Adoption Across a Multinational Workforce: Sociotechnical Conditions for GenAI Acceptance in Human Resources

作者:

Dalia Ali↗Maria Jos\'e Rodr\'iguez Vel\'azquez↗Manoel Horta Ribeiro↗Vera Liao↗Orestis Papakyriakopoulos↗

arXiv:2606.17887v1 Announce Type: cross Abstract: Generative AI (GenAI) deployment in the workplace is accelerating rapidly. Nevertheless, questions of who adopts, who benefits, and who is left behind and why are still understudied. In this paper, we investigate these dynamics in the context of a multinational tech company transitioning from a legacy Human Resources (HR) search system to a GenAI-supported system, analyzing search log data, survey data (n=25), and ten semi-structured interviews. Our findings show that adoption depended on the fit between the GenAI system's design assumptions and employees' work positionalities (role, spoken language, tenure). Further, we find that employees' trust in GenAI answers was built through source-checking, comparison among systems, and seeking input from colleagues or HR when in doubt. Our contribution is twofold. First, we provide empirical evidence of workplace GenAI adoption during a live organizational transition, showing that adoption is influenced by factors such as situational fit, search literacy, and trust calibration. It is also further shaped by knowledge conditions such as the system's content quality, employee training, and guidance. Second, we translate these findings into design considerations for inclusive deployment and adoption in high-stakes environments such as HR. We argue that organizations should design systems considering the role and context-sensitive benefits they yield to different social groups. They also need to treat the organizational knowledge infrastructure as AI infrastructure to improve the accountability and usability of GenAI systems

阅读与讨论 → 访问原文 →

13.

medRxiv (Medicine) 2026-06-15 DOI: HASH:906c675e09538418839805181ddd2830

Diabetes and the Life-Course: Evidence from Panel Data and Electronic Health Records

作者:

Heitzig↗Mackenna↗Rehkopf↗

Incidence of type 2 diabetes is increasing at ages when education, work, family, and financial transitions are taking place, yet we lack robust evidence of whether earlier treatment changes life-course outcomes and over which time span this takes place. This paper uses the medical cutoff for diabetes diagnosis (HbA1c of 6.5 percent) as a natural experiment to study the effects of diabetes treatment using electronic health records (EHR) and panel data. This paper has three main findings. First, using EHR data, we find that there is a sharp increase in the probability of both diagnosis of diabetes and prescription when the HbA1c equals 6.5 percent. Second, we find that treating diabetes reduces HbA1c levels, weight, BMI, and blood pressure and increases the amount of care received, proxied by the number of HbA1c tests. Both the diagnosis and a prescription are independently able to produce positive changes in metabolic health, although a prescription is more effective in this regard. Third, we conclude that treating diabetes does not have a significant effect on life-course outcomes for a cohort of young Americans aged 24-32, although it does result in a reduction in HbA1c levels that are seen even eight years after the intervention. Taken together, these findings suggest that receiving a diagnosis and prescription are both effective treatments for diabetes, but they do not translate to significant alterations in the lives of young adults in the medium-term.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2504.17730

Bandstructure of a coupled BEC-cavity system: effects of dissipation and geometry

作者:

David Baur↗Simon Hertlein↗Alexander Baumg\"artner↗Justyna Stefaniak↗Tilman Esslinger↗Gabriele Natale↗Tobias Donner↗

arXiv:2504.17730v2 Announce Type: replace-cross Abstract: We present a theoretical model for a transversally driven Bose-Einstein condensate coupled to an optical cavity. We focus on the interplay between different coherent couplings, which can trigger a structural phase transition, known as the superradiant phase transition. Our approach, based on band structure theory and a mean-field description, enables a comprehensive analysis of the nature of the system's excited modes, precursing the phase transitions. By incorporating dissipative couplings, intrinsic to these systems, we find non-Hermitian phenomena such as the coalescence of crossing precursor modes and the emergence of exceptional points (EPs). The general formulation of our model allows us to explain the role of an angle between transverse pump and the cavity deviating from $90^\circ$. This offers us a unified perspective on the plethora of different implementations of such systems.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.18049

ConTex: Reformulating Counterfactual Generation For Time Series Forecasting

作者:

Jan Voets↗Hasan Tercan↗Tobias Meisen↗Sebastian Baum↗

arXiv:2606.18049v1 Announce Type: new Abstract: Decision-making with deep learning-based time series forecasting requires not only accurate predictions but also actionable insights. However, current architectures do not inherently provide such information. Specifically, guidance is needed on how current conditions must be modified to shift from a predicted outcome to a desired future scenario. Counterfactual explanations provide a natural framework for this task, as they represent minimal input changes that alter the model's prediction, indicating when and how intervention is required. Existing approaches rely on instance-wise optimization, leading to inconsistency across instances, high computational costs, and limited applicability in real-time settings. To address these limitations, we reformulate counterfactual generation for time series forecasting as the problem of learning a globally consistent intervention strategy, allowing counterfactuals to be generated through a single shared function. We propose Counterfactual Time Series Explanations (ConTex), a model-agnostic, decomposed architecture comprising a temporal context encoder and a conditional encoder, followed by two heads that capture interventions in terms of temporal relevance and modification strength. This structure overcomes the instability and inconsistency of instance-based approaches by producing targeted, interpretable interventions across time and feature dimensions in a single forward pass, making it suitable for real-time applications. Across multiple forecasting architectures and benchmark datasets, ConTex achieves state-of-the-art validity while generating sparse counterfactuals that minimize the number of necessary interventions. Additionally, our approach reduces computational cost by at least 12-36x compared to instance-wise generation and supports real-time inference at approximately 0.007 seconds.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19755

SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling

作者:

Haotian Xu↗Zeyang Zhang↗Linbao Li↗Huadi Zheng↗Yu Li↗Cheng Zhuo↗

arXiv:2606.19755v1 Announce Type: cross Abstract: Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with speculative inference: they either introduce additional computation or disrupt the draft-verify mechanism, negating acceleration benefits. This reveals a fundamental incompatibility between current safety methods and speculative decoding. We propose SafeSpec, a safety-aware speculative inference framework that integrates risk estimation directly into the verification process. SafeSpec attaches a lightweight latent safety head to the target model to jointly evaluate semantic validity and safety in a single forward pass. When unsafe generations are detected, SafeSpec applies rollback and safety-guided reflective multi-sampling to recover safe continuations rather than terminating generation. We model jailbreak attacks as distributional shifts over generative trajectories, where adversarial prompts increase the probability of harmful continuations without eliminating safe ones. Under this model, SafeSpec performs risk-aware trajectory recovery within the speculative decoding process. Across multiple models and adversarial benchmarks, SafeSpec achieves a substantially improved safety-efficiency trade-off. On Qwen3-32B, SafeSpec reduces attack success rates by 15% while preserving a 2.06x inference speedup on benign workloads, demonstrating that speculative acceleration and inference-time safety can be jointly optimized.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.05608

Agentic Software: How AI Agents Are Restructuring the Software Paradigm

作者:

Zhenfeng Cao↗

arXiv:2606.05608v2 Announce Type: replace-cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents – systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource – constitutes a fundamental restructuring of what software is, not an incremental tool improvement. We formalize the distinction between traditional deterministic software and agentic software: in the former, code is the carrier of pre-written decision logic; in the latter, the agent itself is the software, and its decision logic is generated at runtime. We trace the historical arc from licensed software to SaaS to Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users – with the agentic shift transferring not just operational complexity but decision-making complexity itself. We introduce Agentic Engineering as an expansion of the software engineering discipline into a new paradigm, distinct in its core object of study (agent systems rather than static source code), its control model (LLM-driven rather than human-predefined), and its human role (intent architect rather than code author). Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17786

Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars

作者:

Pascal Riachi↗Sofie Kamber↗Stella Brogna↗Andrew Gloster↗Rafael Wampfler↗

Training psychotherapists in evidence-based interventions such as Acceptance and Commitment Therapy (ACT) requires repeated practice with meaningful feedback, yet opportunities for safe, standardized training are limited by ethical, logistical, and resource constraints. We introduce a system designed to support ACT-oriented psychotherapy training through spoken dialogue with an embodied virtual patient. The system uses large language models to simulate patient behavior conditioned on profiles derived from real therapy sessions and configurable clinical scenarios, while a separate automated evaluator provides turn-by-turn feedback on therapist responses based on established ACT fidelity criteria. Rather than aiming to replace supervision, the system is intended to support deliberate practice by enabling experimentation, reflection, and immediate feedback in low-risk settings. Expert evaluation with practicing psychologists confirmed high realism in patient behavior and demonstrated that immediate turn-by-turn ACT feedback increased therapists' awareness of intervention choices and enabled effective experimentation with alternative responses. Quantitative evaluation across 49 therapy transcripts identified GPT-4o-mini as the optimal feedback model, achieving the lowest mean absolute error (MAE = 6.12) in replicating human supervisor ACT fidelity ratings with statistically significant agreement. This work demonstrates the potential of fidelity-aware simulated patients as a scalable complement to psychotherapy training.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13604

Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch

作者:

Haochen Wu↗Yi Hou↗Shiguang Xie↗

arXiv:2606.13604v1 Announce Type: new Abstract: Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational outcomes such as delivery speed, courier utilization, and merchant congestion. We present a deployed reinforcement learning system at DoorDash that adapts dispatch objective weights in a large-scale food-delivery marketplace using delayed signals. Rather than replacing the combinatorial assignment optimizer, a store-level policy learned from logged marketplace data selects a discrete multiplier that shifts the dispatch optimizer's tradeoff between delivery quality and batching efficiency. This interface enables offline policy learning under noisy, delayed, and coupled feedback while preserving production feasibility constraints and operational safeguards. We train a shared value function using centralized offline data and decentralized store-level execution, with Double Q-learning targets and a conservative regularizer to reduce out-of-distribution value overestimation. In a production switchback experiment, the offline-trained policy increases batching and reduces courier-side time costs without degrading customer-facing delivery quality. Results illustrate how world feedback from a live economic and logistics system can be used to safely adapt decision policies online.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18694

Attention as Frustrated Synchronization

作者:

Joshua Nunley↗

A network of oscillators that synchronizes perfectly computes nothing further, so an attention architecture built from synchronization must locate its computation in structured departures from agreement. We introduce the Frustrated Synchronization Network (FSN), whose token states are phases on a torus and whose entire value pathway is one learned complex coupling kernel over harmonics and a one-step delay. Each component of the kernel is a frustration in the sense of the synchronization literature. The complex phases are static Kuramoto-Sakaguchi frustration angles, the signed harmonics are repulsive Daido components, and the delay term, which couples each token to the successors of the tokens it attends to, is algebraically identical to Kuramoto-Sakaguchi coupling whose frustration angle is the data's own transition, so next-token prediction is implemented as synchronization frustrated by the data. At matched one-million-parameter and training budgets on character-level text and code, the FSN's validation loss is below a tuned RoPE-SwiGLU transformer's at every epoch measured, and the comparison survives training the baseline to convergence: every thirty-epoch enwik8 seed finishes below the transformer's converged fifty-epoch loss of 1.611, and the FSN's completed fifty-epoch runs converge to 1.5953 +/- 0.0014. A variant with every feed-forward block replaced by mean-field coupling to learned collective modes, leaving no multilayer perceptron in the stack, tracks the transformer. On natural text the unfrustrated base layer falls behind the converged transformer at every copy depth, worst on long-range copy events; the kernel reverses the deficit at every depth of four and beyond. Headline comparisons are at the one-million-parameter scale; a scale ladder is complete through four million parameters with the advantage persisting, and remaining arms are marked as in progress.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2605.04267

QUIVER: Cost-Aware Adaptive Preference Querying in Surrogate-Assisted Evolutionary Multi-Objective Optimization

作者:

Florian A. D. Burnat↗

arXiv:2605.04267v2 Announce Type: replace Abstract: Interactive multi-objective optimization systems face a budget allocation dilemma: one can spend resources on expensive objective evaluations or on eliciting decision-maker preferences that identify the relevant region of the Pareto set. Moreover, preference elicitation itself spans modalities with different information content and cognitive burden, ranging from cheap, noisy pairwise preference statements (PS) to richer but costlier indifference adjustments (IA). We study cost-aware optimization under an unknown scalarization and introduce QUIVER (Query-Informed Value Estimation for Regret), a surrogate-assisted evolutionary multi-objective optimizer that adaptively chooses between objective evaluations and heterogeneous preference queries. At each step, QUIVER selects the next action by maximizing the expected decision-quality improvement per unit total cost. Across DTLZ and WFG benchmarks under synthetic decision-maker models, QUIVER achieves the lowest final utility regret on challenging WFG problems (utility regret of 2.14 on WFG4, 2.82 on WFG9: a 25% improvement over baselines), outperforming all single-modality baselines. We analyze how the optimal mix of PS and IA adapts to problem difficulty: on easy problems (DTLZ2), QUIVER selects 80\% PS queries; on hard problems (WFG9), it shifts to 35% IA queries. This adaptive modality selection demonstrates cost-aware preference learning in action.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.13808

The Culture Funnel: You Can't Align What isn't in the Data

作者:

Ananya Sahu↗Mehrnaz Mofakhami↗Daniel D'Souza↗Thomas Euyang↗Julia Kreutzer↗Marzieh Fadaee↗

Current cultural alignment approaches focus on inference-time interventions, assuming models already contain sufficient cultural knowledge. We argue modern LLM pipelines suffer from a cultural data funnel. Using a multidimensional tagging framework across pretraining, fine-tuning, alignment, and reasoning datasets, we show explicit cultural signals decline sharply during post-training, while geographically concentrated, task-specialized data dominates. Multilinguality enhances geographic diversity of cultural knowledge but does not ensure balanced representation. Our tags improve downstream cultural benchmark performance, demonstrating that advances require shifting focus in training data pipelines. To facilitate future research, we release our culturally tagged dataset with 5.6M samples at https://huggingface.co/datasets/CohereLabs/CultureMarkers.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12200

Implicit Neural Representations of Individual Behavior

作者:

Andrew Kang↗Priya Narasimhan↗

arXiv:2606.12200v1 Announce Type: cross Abstract: We study policy representation learning from unlabeled multi-policy behavioral data. Each episode is generated by a fixed policy, but policy labels are unavailable. This setting appears in robotics play, demonstrations, games, racing, and other datasets where heterogeneous behaviors are mixed without annotations. We introduce Behavioral INR, a self-supervised generative model that adapts implicit neural representations (INRs) from vision to behavior. Instead of mapping coordinates to RGB values, Behavioral INR represents a policy as a state-action function mapping states to subsequent actions. An episode-level latent modulates this function through FiLM layers, yielding a generative prior over policies and allowing policy identity to be inferred without supervision. Because INRs treat each datapoint as samples from an underlying function, the same model naturally accommodates variable episode lengths and different sampling granularities, as in vision INRs with different image resolutions. We also define policy-level out-of-distribution (OOD) shifts along state-distribution and action-distribution axes, which arise when policies overlap in states or actions but are not captured by standard behavioral OOD settings based only on new agents or environments. We evaluate on synthetic Gaussian random field data, MuJoCo demonstrations with controlled OOD splits, and real-world chess, Formula 1 racing, robotics, and Seek-Avoid datasets. Behavioral INR most consistently improves policy identifiability in the hardest continuous state-action settings, especially when longer episodes, more policies, and OOD splits reduce the usefulness of marginal shortcuts; amortized history encoders remain competitive when policy identity can be recovered from symbolic repetition or low-dimensional action statistics. We release code and checkpoints.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15359

DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising

作者:

Paolo Giaretta↗Zeyang Li↗Navid Azizan↗

arXiv:2606.15359v1 Announce Type: new Abstract: Diffusion models have emerged as powerful tools for planning and control by learning multimodal distributions over actions and trajectories. Yet reliable inference-time safety enforcement remains a key barrier to their deployment in safety-critical tasks. Existing approaches typically project each denoising iterate onto the feasible set, even though constraints are defined only on the final clean trajectory. Enforcing feasibility on noisy intermediate samples can therefore overconstrain the sampling dynamics, substantially degrading sample quality. To address this limitation, we introduce DiRecT (Diffusion-based planning via Receding-horizon denoising with Terminal constraints), a training-free algorithm for constrained sampling from diffusion models via stochastic optimal control (SOC). DiRecT enforces constraints only on the final clean sample, avoiding unnecessary restrictions on the intermediate denoising dynamics. Inspired by model predictive control, we derive a principled receding-horizon surrogate for the otherwise intractable constrained SOC formulation, yielding an efficient algorithm that cleanly separates stochastic denoising from constraint satisfaction, progressively steering samples toward feasible final trajectories without distorting the learned diffusion dynamics. Furthermore, DiRecT is highly flexible: it can leverage off-the-shelf or domain-specific optimizers, incorporate priors over environment dynamics, and optimize additional soft rewards. Extensive experiments on safe planning benchmarks demonstrate that DiRecT substantially improves deployment safety and task performance over existing diffusion-based planning baselines.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12378

Illumination-Robust Camera-Based Heart-Rate Estimation for Physiological Sensing in Robots

作者:

Zhi Wei Xu↗Torbj\"orn E. M. Nordling↗

Physiological awareness is important for service, social, and assistive robots that interact with humans in everyday environments. Remote photoplethysmography (rPPG) enables non-contact heart-rate (HR) estimation from an RGB camera, making it a promising sensing modality for robot-mounted vision systems. However, illumination variation remains a major barrier to robust deployment. This paper presents an end-to-end spatial-temporal transformer framework for remote HR estimation on a new dataset with varied illumination. Our estimator integrates PRNet-based 3D face alignment, clip-level illumination augmentation, the Residual Temporal Standardization Module, and controlled hybrid temporal-frequency supervision. The training objective combines a Soft-Shifted Pearson waveform loss with a spectral Kullback-Leibler divergence loss, where a tuned weight ($\mathbf{\beta}$) controls the contribution of frequency-domain heart-rate guidance. Experiments on a static all-level mix protocol covering three illumination levels show that $\mathbf{\beta}=5$ provides the strongest result among the tested beta settings, achieving a best-run HR mean absolute error (MAE) of 0.79 bpm and an HR correlation of 0.982. Compared with the PhysFormer baseline evaluated on our dataset, our estimator reduces HR MAE by 93.6 %, while increasing HR correlation from 0.088 to 0.982, making it usable when illumination varies.

阅读与讨论 → 访问原文 →