探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18596

Better Adherence, Richer Context: A Field Evaluation of LLM-Powered Conversational Voice Diaries for Sleep

作者:

Amama Mahmood↗Bokyung Kim↗Honghao Zhao↗Molly E. Atwood↗Luis F. Buenaver↗Michael T. Smith↗Chien-Ming Huang↗

arXiv:2606.18596v1 Announce Type: cross Abstract: Sleep diaries are central to behavioral sleep medicine and cognitive behavioral therapy for insomnia, yet daily completion is difficult to sustain, and static forms often provide limited context for interpreting night-to-night sleep variation. We designed an LLM-powered conversational voice diary that delivers clinically grounded morning and evening sleep diary questions through proactive smart-speaker prompts, structured conversational intake, and adaptive follow-up dialogue. We evaluated the system in a four-week between-subjects field study with 30 university students, comparing it with a text-based mobile diary using matched diary items, reporting windows, and reminder intervals. Compared with the text-based diary, the conversational voice diary showed higher adherence and elicited more detailed contextual self-report about routines, stressors, environmental conditions, and other sleep-related factors. Participants also described the voice diary as easier to integrate into daily routines, despite longer perceived completion time. However, voice-based conversational intake produced lower completeness for some structured diary fields, revealing a trade-off between expressive richness and structured precision. These findings show both the promise and the challenge of using LLM-powered conversational voice assistants for longitudinal health self-report.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14536

Provably Safe, Yet Scalable Reinforcement Learning

作者:

Kai S. Yun↗Zeyang Li↗Navid Azizan↗

arXiv:2606.14536v1 Announce Type: new Abstract: Safe reinforcement learning (RL) aims to learn policies that optimize rewards while satisfying constraints. Predominant approaches rely on soft-constrained policy optimization, which has achieved empirical success but does not provide formal safety guarantees for the learned policy. In contrast, methods with strict guarantees typically rely on explicit certificate functions, whose construction requires the direct synthesis and verification of control-invariant sets, a process that scales poorly with state dimension and often yields overly conservative behavior. In this paper, we present the Provably Safe, yet Scalable RL (PS2-RL) framework, a novel two-phase architecture for learning provably safe policies in a scalable manner, designed to overcome the key bottlenecks of prior methods. Rather than explicitly computing invariant sets, PS2-RL leverages a learned backup policy to forward-integrate the system dynamics, generating an implicit control-invariant set online. In the first phase, the backup policy is trained with our proposed safe-arrival value function, which characterizes the optimal backup policy for invariant-set construction. In the second phase, an RL policy is trained end-to-end through a differentiable projection layer that strictly enforces the safety guarantees induced by the learned backup policy. By maximizing the volume of the implicit control-invariant set in the first phase, the resulting PS2 policy from the second phase is performant and scalable, while maintaining provable safety. Crucially, PS2-RL imposes no restrictions on the underlying RL algorithm and can be plugged into any existing training pipeline. We establish theoretical guarantees for the proposed framework and evaluate it on robotic control tasks with state dimensions up to 10, a regime in which prior provably safe RL methods struggle or become impractical.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16475

AI systems out-persuade expert humans

作者:

Kobi Hackenburg↗Caroline Wagner↗Luke Hewitt↗Ben M. Tappin↗Ed Saunders↗Hannah Rose Kirk↗Helen Margetts↗Christopher Summerfield↗

arXiv:2606.16475v1 Announce Type: cross Abstract: Many societal decisions are settled by contests of persuasion. Conversational AI is a powerful new entrant in these contests, but whether it can out-persuade skilled and highly incentivized humans has remained unclear. Here, in a series of four preregistered experiments (n = 18,978 conversations from 6,923 people), we pitted AI systems against a range of human persuaders, including laypeople, winners of a separately preregistered four-round online persuasion tournament, professional canvassers, and world championship debaters. We found that AI systems were reliably more persuasive than expert humans, even when expert humans chose their issues, researched in advance, underwent hours of live, structured practice, and were incentivized with {\pounds}1,000 cash bonuses. In a follow-up study, AI's advantage persisted after experts received a coaching tool that let them practice against the AI that beat them, review their performance history, and see what AI would have said at key moments. We found converging evidence that AI's advantage stemmed from rapidly deploying larger quantities of information: after coaching, expert humans could tie an AI constrained to respond at human speeds and with human-length messages. In a final study, we show that AI's advantage extends to consequential real-world behavior: AI was nearly 3x more effective than professional canvassers from a UK fundraising firm at raising real-money donations to Save the Children. Together, these results establish that frontier AI systems out-persuade expert humans in conversation, with significant implications for political communication.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2603.12261

The Latent Color Subspace: Emergent Order in High-Dimensional Chaos

作者:

Mateusz Pach↗Jessica Bader↗Quentin Bouniot↗Serge Belongie↗Zeynep Akata↗

Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due to limited understanding of how semantic information is encoded. We develop an interpretation of the color representation in the Variational Autoencoder latent space of FLUX.1 [Dev], revealing a structure reflecting Hue, Saturation, and Lightness. We verify our Latent Color Subspace (LCS) interpretation by demonstrating that it can both predict and explicitly control color, introducing a fully training-free method in FLUX based solely on closed-form latent-space manipulation. Code is available at https://github.com/ExplainableML/LCS.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2605.13092

Adaptive Kernel Density Estimation with Pre-training

作者:

Ruitong Zhang↗Ke Deng↗

arXiv:2605.13092v2 Announce Type: replace-cross Abstract: Density estimation in high-dimensional settings is an important and challenging statistical problem.Traditional methods based on kernel smoothing are inefficient in high dimensions due to the difficulties in specifying appropriate location-adaptive kernels. In this work, we introduce pre-training, a key idea behind many cutting-edge AI technologies, to the context of non-parametric density estimation. By establishing a pre-trained neural network that can recommend an appropriate location-adaptive kernel for each sample point, efficient density estimation with adaptive kernels is achieved in high dimensions. A wide range of numerical experiments show that this strategy is highly effective for improving density-estimation accuracy, when the target distribution is close to the distribution family for pre-training. When the target distribution is substantially different from the pre-training distribution family, the benefit from the proposed pre-training strategy may be diluted, but can be reactivated by an additional fine-tuning procedure.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2504.03991

Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Models

作者:

Siddharth Srikanth↗Varun Bhatt↗Boshen Zhang↗Werner Hager↗Charles Michael Lewis↗Katia P. Sycara↗Aaquib Tabrez↗Stefanos Nikolaidis↗

Understanding how humans collaborate and communicate in teams is essential for improving human-agent teaming and AI-assisted decision-making. However, relying solely on data from large-scale user studies is impractical due to logistical, ethical, and practical constraints, necessitating synthetic models of multiple diverse human behaviors. Recently, agents powered by Large Language Models (LLMs) have been shown to emulate human-like behavior in social settings. But, obtaining a large set of diverse behaviors requires manual effort in the form of designing prompts. On the other hand, Quality Diversity (QD) optimization has been shown to be capable of generating diverse Reinforcement Learning (RL) agent behavior. In this work, we combine QD optimization with LLM-powered agents to iteratively search for prompts that generate diverse team behavior in a long-horizon, multi-step collaborative environment. We first show, through a human-subjects experiment, that humans exhibit diverse coordination and communication behavior in this domain. We then present a series of experiments showing that our approach captures behaviors that are difficult to observe without large-scale data collection, and a follow-up user study to show that these generated behaviors are human-like. Our findings highlight the combination of QD and LLM-powered agents as an effective tool for studying teaming and communication strategies in multi-agent collaboration.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11583

Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching

作者:

Zhuoyi Peng↗Hanlin Gu↗Lixin Fan↗Yi Yang↗

arXiv:2606.11583v1 Announce Type: new Abstract: Text-attributed graphs (TAGs) underlie real-world applications such as citation networks, social media, and e-commerce. Few-shot graph learning on TAGs is hard: with only a handful of labels per class and the rest of the graph unannotated, neither GNNs nor LLMs can learn well on their own. GNNs read topology and fail on cold nodes; LLMs read text and fail on text-ambiguous nodes. Existing LLM-GNN methods all follow the same recipe: designate one model as the golden teacher and use its outputs (e.g., features or pseudo-labels) to supervise the other. We argue this golden-teacher assumption breaks under sparse supervision: neither model is golden, and treating either as such transfers its blind spots into the student. We therefore ask: can we avoid designating either model as the golden teacher, and still perform effective graph learning? We answer with LLM-GNN Co-Teaching, a bidirectional co-teaching framework in which neither model is fixed as teacher. The GNN and LLM exchange their most confident pseudo-labels under an architecture-specific small-loss criterion, and both update every round. Supervision is then mined from the trajectory: whenever a node moves from cross-model contradiction at round t to cross-model agreement at round t+1, the LLM's two answers on the same input form a preference pair (old contradicting self < new peer-endorsed self) for DPO training. We call this Round-based Pseudo-Label Preference Optimization (RPL-PO). On six benchmarks, LLM-GNN Co-Teaching consistently outperforms GNN-as-Judge and all prior methods, with absolute 3-shot gains of 7.86% on Cora and 7.73% on ogbn-arxiv; improvements carry over to 5-shot and to zero-shot cross-dataset transfer. Error-structure analysis further shows that abandoning the golden-teacher assumption substantially improves the LLM's graph learning capability on challenging samples.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19380

AgentArmor: A Framework, Evaluation, \& Mitigation of Coding Agent Failures

作者:

Kenneth Ge↗Andre Assis↗

arXiv:2606.19380v1 Announce Type: cross Abstract: Software engineering and deployment are increasingly being delegated to AI coding agents. The scale of their adoption is surfacing rare, but highly destructive, failure modes. In this paper, we study these failure modes as stemming from three distinct mechanisms: underspecification, where default model behavior is unsafe; capability errors, where the safe action is available but the model does not adhere to it due to bias or capability limitations; and agent harness errors, where the model fails to execute the safe action through the harness. We evaluate these across 8 different evaluations, each inspired by real-life deployment failures, totaling 20 coding environments and 59 synthetic transcript templates. Based on this evaluation, we propose AgentArmor, an agent harness modification, to mitigate these errors. By adding an extended system prompt, a separate command classifier, a ``3 strikes'' policy, deterministic guardrails, and tools for the agent to edit its own context, we show that AgentArmor is safer across a statistically significant number of samples. Thus, we suggest concrete mitigations for current coding agents and a design philosophy for future agent harness features.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20227

QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation

作者:

Xinyi Zheng↗Ling Shi↗Tianlong Yu↗Yongxin Zhao↗Lorenz Goette↗Kailong Wang↗

arXiv:2606.20227v1 Announce Type: new Abstract: Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to keep pace. However, existing benchmarks lack fine-grained control over logical complexity and struggle to balance semantic diversity with logical consistency. To address these issues, we propose QMFOL, an automated framework for generating monadic first-order logic reasoning tasks with quantifiable and controllable complexity. It constructs formal logical structures using conjunction and disjunction patterns, enabling precise control over reasoning depth, width, label types, and distractors. These structures are then translated into natural language via LLMs, with logical consistency ensured through round-trip verification using an external prover. Based on our framework, we build QMFOLBench, a benchmark comprising 2880 instances with 960 configurations across diverse logical and semantic dimensions. Evaluations on six large reasoning models (LRMs) and two LLMs show that performance degrades and computational overhead increases with rising logical complexity. Models perform better on True-labeled tasks than on False or Unknown ones, and exhibit sensitivity to semantic variation. Overall, QMFOL offers a scalable and reliable approach for constructing deductive reasoning benchmarks with controllable complexity, enabling more precise evaluation of reasoning capabilities in modern language models.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2602.19502

Human-Guided Agentic AI for Multimodal Clinical Prediction: Lessons from the AgentDS Healthcare Benchmark

作者:

Lalitha Pranathi Pulavarthy↗Raajitha Muthyala↗Aravind V Kuruvikkattil↗Zhenan Yin↗Rashmita Kudamala↗Saptarshi Purkayastha↗

arXiv:2602.19502v2 Announce Type: replace Abstract: Agentic AI systems are increasingly capable of autonomous data science workflows, yet clinical prediction tasks demand domain expertise that purely automated approaches struggle to provide. We investigate how human guidance of agentic AI can improve multimodal clinical prediction, presenting our approach to all three AgentDS Healthcare benchmark challenges: 30-day hospital readmission prediction (Macro-F1 = 0.8986), emergency department cost forecasting (MAE = $465.13), and discharge readiness assessment (Macro-F1 = 0.7939). Across these tasks, human analysts directed the agentic workflow at key decision points, multimodal feature engineering from clinical notes, scanned PDF billing receipts, and time-series vital signs; task-appropriate model selection; and clinically informed validation strategies. Our approach ranked 5th overall in the healthcare domain, with a 3rd-place finish on the discharge readiness task. Ablation studies reveal that human-guided decisions compounded to a cumulative gain of +0.065 F1 over automated baselines, with multimodal feature extraction contributing the largest single improvement (+0.041 F1). We distill three generalizable lessons: (1) domain-informed feature engineering at each pipeline stage yields compounding gains that outperform extensive automated search; (2) multimodal data integration requires task-specific human judgment that no single extraction strategy generalizes across clinical text, PDFs, and time-series; and (3) deliberate ensemble diversity with clinically motivated model configurations outperforms random hyperparameter search. These findings offer practical guidance for teams deploying agentic AI in healthcare settings where interpretability, reproducibility, and clinical validity are essential.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17065

PIVOT: Bridging Black-Scholes Implied-Volatility and Price Objectives via Differentiable Jäckel Operator

作者:

Raeid Saqur↗Yannick Limmer↗Anastasis Kratsios↗Blanka Horvath↗Hans Buehler↗

arXiv:2606.17065v1 Announce Type: cross Abstract: Modern option-learning systems operate in two coordinates: price space, where markets quote and no-arbitrage constraints are most naturally enforced, and implied volatility (IV) space, where volatility surfaces are smoothed, regularized, and evaluated. The bottleneck is interface, not approximation: Jäckel's seminal "Let's Be Rational" (LBR) solver already inverts the Black-Scholes price to machine precision efficiently. What is missing is a differentiable layer that preserves LBR in the forward pass and avoids backpropagating through its branch logic. Such a layer must also confront the unavoidable singularity of the inverse map in the low-vega regime, where the sensitivity 1/vega diverges as vega -> 0. We close this gap with PIVOT, the Price-Implied-Volatility Objective Translator. PIVOT keeps the LBR forward pass intact and supplies the backward pass by implicit differentiation through the smooth Black-Scholes/Black-76 price map, with an explicit gating contract: invalid domains return NaN, well-conditioned rows receive the exact 1/vega gradient, and low-vega rows are attenuated rather than silently regularized. On a single H100, a fused Triton kernel reaches 1.79e9 IV/s at machine precision (9.3e-14 max relative error vs. the reference C solver); end-to-end label generation sustains 48.9M/s on synthetic chains and 16.6M/s on SPX OptionMetrics. In a HyperIV-style one-day reproduction on SPX, PIVOT-augmented objectives Pareto-dominate the baselines, reducing held-out price MAE by up to 43.4% and the strongest three-seed gated objective improving price MAE by 38.8% and IV MAE by 21.3% jointly; cross-asset results on RUT, VIX, and NDX show directional price-MAE gains of 40.1%, 24.2%, and 16.7%, while an ungated IV-roundtrip control collapses to a degenerate near-zero surface, confirming the gate as a correctness contract rather than a tuning knob.

阅读与讨论 → 访问原文 →

12.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.14577

Trap-Quenched Matter-Wave Optics for Dual Species Lensing

作者:

Gabriel M\"uller↗Timoth\'e Estrampes↗Claudia Puertas Gonz\'alez↗Jannik Str\"ohle↗David B. Reinhardt↗Dana Codruta Marinica↗Ethan R. Elliott↗Jason R. Williams↗Nathan Lundblad↗Eric Charron↗Ernst M. Rasel↗Matthias Meister↗…

arXiv:2606.14577v1 Announce Type: cross Abstract: Dual-species atom interferometry in space promises precise tests of the Universality of Free Fall (UFF), with a sensitivity that grows quadratically with the extended interrogation time accessible in weightlessness. These tests demand exquisite control over the expansion energies of both condensed sources as well as over their differential center-of-mass dynamics. We propose a trap-quenched collimation technique featuring in-trap excitations of collective modes compatible with state-of-the-art atom-chip setups. Using NASA's Cold Atom Laboratory aboard the International Space Station, we demonstrate it on a single-species $^{87}$Rb condensate. By controlling the center-of-mass release dynamics we observe free expansion times up to 700 ms and measure a two-dimensional expansion energy of $k_B \cdot 78\pm 9 \;\mathrm{pK}$ in the imaging plane. A detailed model of the magnetically-induced dynamics indicates that this corresponds to a two-dimensional expansion energy of about $k_B \cdot 15^{+12}_{-5}\; \mathrm{pK}$ along two of the condensate's eigenaxes. Finally, we theoretically study this trap-quenched collimation scheme for a $^{41}$K-$^{87}$Rb mixture, predicting a simultaneous collimation that meets the expansion energy requirements for a state-of-the-art UFF test at the $10^{-15}$ accuracy level.

阅读与讨论 → 访问原文 →

13.

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 →

14.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13436

Evaluation Sovereignty in Metadata-Driven Classification: A Multi-Track Framework for Weakly Supervised Information Systems

作者:

Raymond Vasquez↗

arXiv:2606.13436v1 Announce Type: new Abstract: Evaluation in machine learning is typically treated as a neutral measurement process. However, in operational information systems, evaluation outcomes are often conditioned by the processes used to generate labels. This paper does not seek to improve classification performance. Instead, it examines the validity of performance measurement under differing label-authority regimes. This issue is particularly relevant in large-scale metadata-driven systems, where labels are often incomplete, inconsistent, or weakly supervised. We introduce evaluation sovereignty, defined as the degree to which performance metrics are independent of label authority and supervision regime, and propose a multi-track evaluation framework that systematically varies training and evaluation label sources. Using hierarchical multi-label classification on large-scale scientific metadata, we demonstrate that models exhibiting strong performance under operational ("silver") evaluation degrade substantially under independent ("gold") evaluation, particularly for fine-grained classification. For example, Micro-F1 decreases from approximately 0.54 to 0.03. Notably, ranking-based metrics remain above baseline, revealing a divergence between latent model signal and classification validity. These findings suggest that commonly reported performance metrics may reflect alignment with labeling processes rather than true predictive capability. We therefore reconceptualize evaluation validity as a system-level property shaped by label governance and provide a practical methodology for auditing intelligent systems operating under weak supervision.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18782

RedactionBench

作者:

Sean Brynj\'olfsson↗Shashvat Jayakrishnan↗Esha Sali↗Diptanshu Purwar↗Madhav Aggarwal↗

Large Language Models are increasingly applied to sensitive domains that require redaction of personally identifiable information (PII). While redacting PII is a data cleaning prerequisite, existing benchmarks conflate extraction mechanics with privacy semantics. A public phone number is not equivalent to a phone number in a medical record. Whether information constitutes a violation depends heavily on who holds it, why, and in what context, fundamentally differentiating redaction from simple entity recognition. Grounded in contextual integrity, we introduce RedactionBench, a manually annotated benchmark comprising 200 diverse documents across 11 domains, mostly seeded from real-world sources. We also introduce R-Score, a novel character-level metric that treats semantically similar redactions equally and nullifies shallow formatting choices, such as varying masking styles for phone numbers. Evaluations across Named Entity Recognition models, entity extraction Small Language Models, and frontier models equipped with agentic tools demonstrate that contextual redaction remains an unsolved problem. A human evaluation with over 80 users on RedactionBench reveals a stark dichotomy in privacy perceptions. Annotators show consensus with target labels for mandatory redactions (89.4 percent) and safe text preservations (94.1 percent), but fail to agree on contextual redactions (47.7 percent). This variance demonstrates the subjective nature of contextual privacy and motivates R-Score, which decouples contextual ambiguity from strict precision. We compare 35 models across families and report their performance in redacting PII. Finally, we release RedactionBench to establish a baseline for future privacy-preserving systems, hoping to inspire efficient model design and standardized evaluations.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11337

Can AI Agents Synthesize Scientific Conclusions?

作者:

Hayoung Jung↗Pedro Viana Diniz↗Jos\'e Reinaldo Corr\^ea Roveda↗Abner Fernandes da Silva↗Haeun Jung↗Enoch Tsai↗Aleksandra Korolova↗Manoel Horta Ribeiro↗

Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions. Yet, their ability to do so in high-stakes domains such as health remains unclear. We introduce SciConBench, a large-scale live benchmark of 9.11K questions and expert-written conclusions from systematic reviews to evaluate open-domain scientific conclusion synthesis. The benchmark draws on an expert-validated automated evaluation pipeline that decomposes conclusions into atomic facts and measures correctness and comprehensiveness via factual precision and recall. To mitigate data leakage, we further introduce SciConHarness, a clean-room evaluation harness that equips agents with controlled web interaction to ensure valid measurement. Evaluating 8 frontier models and deep research agents, we find that factual quality remains low: under clean-room settings, the best agent achieves only a factual F1 of 0.337. Our clean-room setting consistently reduces performance relative to unconstrained evaluation, suggesting that leakage inflates estimates of models' true synthesis capabilities. Finally, we audit consumer-facing agents (e.g., Google AI Overview, OpenEvidence) and find they frequently generate incomplete and sometimes contradictory conclusions, even when the ground-truth answer is available. Overall, our results show that reliable synthesis of scientific conclusions remains an open challenge, and that clean-room evaluation is essential for assessing open-domain AI agents.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15442

The Reverse Telescoping Coordinate System for Positive Definite Matrices: Geometry, Computation, and Generative Modeling

作者:

Anindya Bhadra↗

arXiv:2606.15442v1 Announce Type: cross Abstract: We design a new unconstrained coordinate system where a $p\times p$ symmetric positive definite (SPD) matrix $\Theta$ is represented by a reverse telescoping map $\Theta(x)=\rm{RT}(x)$, with $x=(v,d,r)\in\mathbb{R}\times\mathbb{R}^{(p-1)}\times\mathbb{R}^{p(p-1)/2}$, representing respectively the log volume or log determinant; and the shape, as encoded by log relative diagonal scales and partial covariances among the nodes. This construction results in important properties not available in other charts, e.g., matrix logarithm, such as Jacobian depending on only the log-determinant. A useful feature of our construction is $x$ contains a lossless symbolic representation of both the matrix and its inverse. Many important computations involving a matrix and its inverse can be performed in $O(p^2)$ in the transformed domain, while it is the rendering of results in matrix forms (on demand) that must incur an $O(p^3)$ cost. Moreover, two unit-determinant matrices in the transformed domain can be joined by a straight line with pathwise unit determinant. For generative modeling, this allows designing a split volume-shape flow model trained by conditional flow matching for transporting the shape over the unit-determinant path, with a separate one-dimensional flow for transporting the volume or the determinant. The forbidding SPD constraint, tamed thus into a powerful guiding force, leads to the surprising insight that it is in some sense easier to design a volume-normalized shape flow for SPD compared to the unconstrained $\mathbb{R}^{p\times p}$, with no intrinsic notion of volume to aid normalization, unlike the determinant of SPD matrices. We apply our construction for up to $p=200$ in generative modeling of SPD matrices on a difficult synthetic bimodal target, and in generating brain connectivity networks by models trained on fMRI data; as well as in intrinsic diffusion on the SPD manifold.

阅读与讨论 → 访问原文 →

18.

Nature (Science) 2026-06-17 DOI: HASH:0633aafc69cd3680b36d97db2d88b3a2

Emergent decadal predictability in Antarctic contribution to sea-level rise

作者:

Felicity S. McCormack↗

Despite large uncertainties associated with future mass loss from the Antarctic Ice Sheet, ice-sheet models show that the rate of sea-level rise from Antarctic ice loss in 2025 is strongly predictive of the rate for the next several decades, regardless of emission pathway or model complexity. This finding is robust across all models that were considered in the Intergovernmental Panel on Climate Change Sixth Assessment Report global mean sea-level projections, including the low-likelihood, high-impact scenarios of sea-level rise. Given this strong near-term decadal predictability, ice-sheet models that can accurately reproduce present-day ice-mass loss provide a reliable basis for near-term sea-level planning and adaptation through to mid-century. The predictability breaks down by the end of the twenty-first century as feedbacks, such as those related to marine ice-sheet retreat, begin to emerge, leading to accelerating ice loss. Drawing on these results, we identify key feedback mechanisms that can account for the transition between near-term decadal predictability and the longer-term, feedback-driven evolution, and suggest priorities for ice-sheet model development aimed at resolving long-term sea-level rise uncertainty. Although Antarctic ice loss projections diverge widely by 2100, this Perspective shows that present-day rates robustly predict mid-century sea level rise, providing a firm basis for near-term planning, while highlighting priorities for model development aimed at resolving longer-term sea level rise uncertainty.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12114

Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models

作者:

Rei Minamoto↗Yusuke Oda↗Daisuke Kawahara↗

Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to ensure compliance with privacy regulations and prevent unintended information leakage. However, in contrast to English and other languages, research into sensitive personal information has been limited in the Japanese language. In this study, we focus on sensitive personal data defined as special care-required personal information (SCPI) under Japan's Act on the Protection of Personal Information (APPI). We construct an SCPI dataset using LLM-based annotation and train machine learning models to rapidly detect SCPI in text. As a result, our SCPI classifier can effectively identify information related to SCPI. This study is the first to explore SCPI detection in Japanese text corpora, highlighting the challenges of accurate detection.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11262

PermDoRA – Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry

作者:

Gowtham Sivaramakrishnan↗Sarvesha Kumar Kombaiah Seetha↗Kishan Gupta Balaji↗Santhosh Baradwaj Vaduvur Ranganathan↗

arXiv:2606.11262v1 Announce Type: cross Abstract: Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference. A common hypothesis is that interference during adapter composition arises from overlap in linear parameter updates, suggesting that enforcing orthogonality or directional independence should improve multi-domain performance. We test this hypothesis using DoRA-RBAC, a hierarchical adapter composition framework based on weight-decomposed low-rank adaptation. We compare conventional Euclidean merging with a geometry-aware Riemannian-inspired merging strategy that approximates the Frechet mean via normalized directional averaging across multiple QA benchmarks (GPQA, PubMedQA, SimpleQA, WMDP) on LLaMA-3.1-8B and Mistral-7B. Our results show that while single-domain performance matches LoRA, geometry-aware merging provides no consistent advantage over standard averaging in multi-domain settings.Diagnostic analysis further reveals that angular alignment and orthogonality of adapter updates are weak predictors of composition performance. These findings suggest that adapter interference is not governed primarily by parameter-space geometry, but is instead consistent with interactions in shared nonlinear representations.

阅读与讨论 → 访问原文 →

21.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2511.04389

Minimum measurements quantum protocol for band structure calculation

作者:

Michal Krej\v{c}\'i↗Lucie Krej\v{c}\'i↗Ijaz Ahamed Mohammad↗Martin Plesch↗Martin Fri\'ak↗

arXiv:2511.04389v2 Announce Type: replace Abstract: Protocols for quantum measurement are an essential part of quantum computing. Measurements are no longer confined to the final step of computation but are increasingly embedded within quantum circuits as integral components of noise-resilient algorithms. However, each observable typically requires a distinct measurement basis, often demanding a different circuit configuration. As the number of such configurations typically grows with the number of qubits, measurements constitute a major bottleneck. Focusing on electronic structure calculations in crystalline systems, we propose a measurement protocol that restricts the required measurement configurations to an absolute minimum of just three, independent of the number of qubits. This makes it one of the few known protocols that do not scale with qubit number. In particular, we derive the measurement protocol from the symmetries of tight-binding (TB) Hamiltonians and implement it within the Orthogonal-Ansatz Variational Quantum Eigensolver (OA-VQE) algorithm. We demonstrate its performance on three systems, namely a two-dimensional CuO$_2$ square lattice (3 qubits), bilayer graphene with hexagonal (Honeycomb) lattice (4 qubits) and three-dimensional diamond lattice (10 qubits). Beyond tight-binding systems, the protocol can be extended to enable efficient initial state preparation for many-body Hamiltonians, such as multi-orbital Hubbard models in a momentum space.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12160

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

作者:

Ao Sun↗

In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal logits from each layer of every token. Our method extracts a compact set of features such as maximum, minimum, mean, standard deviation, and slope-from the token logits across all layers, enabling effective hallucination detection without overfitting. Experiments on TruthfulQA and MMLU datasets demonstrate that CHAIR significantly improves detection accuracy, particularly in zero-shot scenarios, showcasing its robustness and generalizability. Beyond hallucination detection, CHAIR highlights the potential of using internal representations for designing advanced decoding strategies. By leveraging patterns in logits, we suggest that more sophisticated models and adaptive decoding methods could further reduce hallucinations and enhance text completion quality. CHAIR not only offers a practical solution for detecting hallucinations but also lays the groundwork for exploring richer representations in LLMs to improve their factuality and coherence.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2604.06531

A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge

作者:

Asmaa Eldesoukey↗Yongxin Chen↗Abhishek Halder↗

arXiv:2604.06531v3 Announce Type: replace-cross Abstract: The mean-field Schrödinger bridge (MFSB) problem concerns designing a minimum-effort controller that guides a diffusion process with nonlocal interaction to reach a given distribution from another by a fixed deadline. Unlike the standard Schrödinger bridge, the dynamical constraint for MFSB is the mean-field limit of a population of interacting agents with controls. It serves as a natural model for large-scale multi-agent systems. The MFSB is computationally challenging because the nonlocal interaction makes the problem nonconvex. We propose a generalization of the Hopf-Cole transform for MFSB and, building on it, design a Sinkhorn-type recursive algorithm to solve the associated system of integro-PDEs. Under mild assumptions on the interaction potential, we discuss convergence guarantees for the proposed algorithm. We present numerical examples with repulsive and attractive interactions to illustrate the theoretical contributions.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2506.20015

Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons

作者:

Dengyu Wu↗Jiechen Chen↗H. Vincent Poor↗Bipin Rajendran↗Osvaldo Simeone↗

arXiv:2506.20015v2 Announce Type: replace Abstract: Neuromorphic computing offers an energy-efficient alternative to conventional deep learning accelerators, particularly for real-time processing of time-series data. However, many edge applications, such as wireless sensing and audio recognition, generate streaming signals with rich spectral features that are not effectively captured by conventional leaky integrate-and-fire (LIF) spiking neurons. This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons with oscillatory dynamics to process time-domain signals directly, eliminating the need for costly spectral pre-processing. By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity. This temporal sparsity translates into significant savings in both computation and transmission energy. Assuming an OFDM-based analog wireless interface for spike transmission, we present a complete system design and evaluate its performance on audio classification and modulation classification tasks. Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs, while substantially reducing spike rates and total energy consumption during inference and communication.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14314

Communication Policy Evolution for Proactive LLM Agents

作者:

Xinbei Ma↗Jiyang Qiu↗Yao Yao↗Zheng Wu↗Yijie Lu↗Xiangmou Qu↗Jiaxin Yin↗Xingyu Lou↗Jun Wang↗Weiwen Liu↗Weinan Zhang↗Zhuosheng Zhang↗…

arXiv:2606.14314v1 Announce Type: new Abstract: LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.

阅读与讨论 → 访问原文 →