探索全球前沿学术脉络

01.

arXiv (math.PR) 2026-06-18 DOI: arXiv:2606.19075

Random Schrödinger operators on manifolds and abstract bounds for multiplier-type operators

作者:

Jean-Claude Cuenin↗Konstantin Merz↗Eduard Stefanescu↗

arXiv:2606.19075v1 Announce Type: cross Abstract: We study random Schrödinger operators on closed Riemannian manifolds with Anderson-type potentials. We prove high-probability spectral inclusion bounds showing that eigenvalues remain close to those of the Laplacian, with deviations controlled by a norm of the potential coefficients. Compared with deterministic bounds, this yields a square-root cancellation gain. The proof is based on a general principle showing that randomisation improves operator norm bounds for multiplier-type operators, which we formulate in both discrete and continuous settings.

阅读与讨论 → 访问原文 →

02.

medRxiv (Medicine) 2026-06-18 DOI: HASH:3863b88fe4c349a4d8860bf115d78aa8

Can Vision-Language Models See the Vital Signs? Benchmarking and Fine-Tuning for Intraoperative Monitor Reading

作者:

Gao↗Wang↗Zhao↗Yang↗Zhang↗Feng↗He↗

Background Vital-sign deterioration is a leading contributor to preventable perioperative death, yet manual monitor reading is intermittent, error-prone, and subject to alarm fatigue. Automating this perceptual step could enable continuous surveillance, but existing solutions depend on device-specific hardware integration or cloud-hosted vision-language models (VLMs), which raise privacy, cost, and connectivity barriers in resource-limited healthcare facilities. Methods We constructed a benchmark of 200 in-the-wild intraoperative monitor photographs (spanning multiple vendors, angles, and illumination conditions) annotated for eight vital-sign parameters: heart rate, SpO2, ETCO2, respiratory rate, systolic/diastolic/mean blood pressure, and temperature. We evaluated an optical character recognition (OCR)-based pipeline, nine instruction-tuned VLMs (four commercial, five open-weight ranging from [≤]4B to 31B parameters) under two prompting regimes, and a compact open model (Qwen3.5-9B) adapted via low-rank fine-tuning (LoRA, 0.46% of parameters updated). Results Under a domain-aware prompt, frontier VLMs reached 0.98-0.997 exact-match accuracy zero-shot, whereas the OCR pipeline and [≤]4B model scored approximately 0.20 lower, defining a 9B-class usable floor. LoRA fine-tuning Qwen3.5-9B on 80-120 images raised accuracy from 0.953 to 0.994 (statistically indistinguishable from the best commercial model) and reduced the critical-error rate fivefold (0.0313 [->] 0.0063). Ablations showed that performance saturated at 80 training images and rank-8 adapters. Conclusion Monitor reading is a solved perception problem for VLMs above the 9B scale. A lightweight fine-tuned open model achieves frontier accuracy while running entirely on local hardware, preserving data privacy, offline capability, and near-zero marginal cost. Residual errors stem from blood-pressure source ambiguity and are addressable with explicit disambiguation logic.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11769

When Do Data-Driven Systems Exhibit the Capability to Infer?

作者:

Maximilian Poretschkin↗Tabea Naeven↗

arXiv:2606.11769v1 Announce Type: new Abstract: The European AI Act is the first comprehensive regulation of artificial intelligence (AI), setting out extensive obligations, particularly for so-called high-risk and general-purpose AI systems. A key distinguishing feature of AI systems under the AI Act is the capability to infer. Since the AI Act does not clearly define what inference is, there is a gray area for certain data-driven systems. A specific example is credit scoring systems, which are listed by Annex III of the AI Act. At the same time, however, these are often implemented using statistical models for which it is unclear whether they have the capability to infer and thus fall under the AI definition of the AI Act at all. Motivated by statistical learning theory, this work develops a framework for grading different levels of the capability to infer. Based on the AI Act and the Commission Guidelines on the definition of an artificial intelligence system, we analyze which levels constitute sufficient capability to infer within the meaning of the AI Act and where further regulatory clarity is needed. We illustrate the framework by creating two realistic credit scoring workflows and show whether and where inference occurs in them. Our analysis illustrates that not only individual models but the entire data processing workflow must be considered. It also shows that the involvement of human experts during development can have significant influence on the capability to infer. Code can be found at https://github.com/fraunhofer-iais/inference-framework-creditscorecards.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17945

Small Initialization Matters for Large Language Models

作者:

Liangkai Hang↗Junjie Yao↗Zhiyu Li↗Feiyu Xiong↗Hongkang Yang↗Zhi-Qin John Xu↗

arXiv:2606.17945v1 Announce Type: new Abstract: Large language models provide a tractable system for asking how intelligence itself emerges, rather than only how LLMs can be engineered. Although progress is usually attributed to scale, data and architecture, we show that parameter initialization is a gene-like determinant of training and, in particular, of model capacity. Reducing the initialization scale consistently improves pretraining, with the largest gains on reasoning-demanding tasks. We identify two widely used empirical settings that restrain the advantage of small initialization, and show how relaxing them restores favorable scaling. We further uncover a critical initialization that balances the reasoning and training. Mechanistically, small initialization drives a distinct developmental trajectory: parameters first condense into low-complexity structures and later expand into richer representations, giving concrete form to the idea that compression is intelligence. Token-level analyses show that the gains concentrate on non-trivial, context-constrained predictions rather than all tokens uniformly. These results motivate a simple $\gamma$-initialization rule: expose initialization rage as an explicit knob and use small initialization by default, an almost cost-free intervention that improves pretraining and strengthens reasoning across model scales.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2410.00903

Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatments

作者:

Kosuke Imai↗Kentaro Nakamura↗

In this paper, we demonstrate how to enhance the validity of causal inference with unstructured high-dimensional treatments like texts, by leveraging the power of generative Artificial Intelligence (GenAI). Specifically, we propose to use a deep generative model such as large language models (LLMs) to efficiently generate treatments and use their internal representation for subsequent causal effect estimation. We show that the knowledge of this true internal representation helps disentangle the treatment features of interest, such as specific sentiments and certain topics, from other possibly unknown confounding features. Unlike existing methods, the proposed GenAI-Powered Inference (GPI) methodology eliminates the need to learn causal representation from the data, and hence produces more accurate and efficient estimates. We formally establish the conditions required for the nonparametric identification of the average treatment effect, propose an estimation strategy that avoids the violation of the overlap assumption, and derive the asymptotic properties of the proposed estimator through the application of double machine learning. Finally, using an instrumental variables approach, we extend the proposed GPI methodology to the settings in which the treatment feature is based on human perception. The GPI is also applicable to text reuse where an LLM is used to regenerate existing texts. We conduct simulation and empirical studies, using the generated text data from an open-source LLM, Llama 3, to illustrate the advantages of our estimator over state-of-the-art causal representation learning algorithms.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2602.13379

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

作者:

Xu Li↗Simon Yu↗Minzhou Pan↗Yiyou Sun↗Bo Li↗Dawn Song↗Xue Lin↗Weiyan Shi↗

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing new risks overlooked by existing benchmarks. To systematically scale safety testing into multi-turn, tool-realistic settings, we propose a principled taxonomy that transforms single-turn harmful tasks into multi-turn attack sequences. Using this taxonomy, we construct MT-AgentRisk (Multi-Turn Agent Risk Benchmark), the first benchmark to evaluate multi-turn tool-using agent safety. Our experiments reveal substantial safety degradation: the Attack Success Rate (ASR) increases by 16% on average across open and closed models in multi-turn settings. To close this gap, we propose ToolShield, a training-free, tool-agnostic, self-exploration defense: when encountering a new tool, the agent autonomously generates test cases, executes them to observe downstream effects, and distills safety experiences for deployment. Experiments show that ToolShield effectively reduces ASR by 30% on average in multi-turn interactions. Our code is available at https://github.com/CHATS-lab/ToolShield.

阅读与讨论 → 访问原文 →

07.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2606.14789

Plateau Gaps of Poisson Correctors Encode Metastable Reaction Rates

作者:

Sang Yang↗Zhixin Peng↗

arXiv:2606.14789v1 Announce Type: cross Abstract: Metastable reaction rates are commonly inferred from transition-state fluxes, mean first-passage times, or fitted kinetic models. We show that they are directly encoded in the plateau gap of an occupation-time Poisson corrector. For a centered basin-occupation observable, the Poisson corrector develops metastable plateaus in the reactant and product basins, and their separation determines the forward and backward transition rates. This construction requires only the generator, stationary measure, and metastable partition, and therefore does not rely on a predefined transition-state surface. In overdamped and underdamped double-well dynamics, the plateau-gap rate recovers the Kramers, Grote-Hynes, and Pollak-Grabert-Hänggi hierarchy. The same corrector-martingale decomposition yields a reactive-noise density, revealing where stochastic forcing contributes to transitions in configuration or phase space. Thus, reaction rates and their fluctuation sources emerge from a single corrector field.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20122

ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research

作者:

Zhibang Yang↗Xinke Jiang↗Yuzhen Xiao↗Ruizhe Zhang↗Yue Fang↗XinFei Wan↗Zhengxing Song↗Yuxuan Liu↗Yuheng Huang↗Xu Chu↗Junfeng Zhao↗Yasha Wang↗…

arXiv:2606.20122v1 Announce Type: new Abstract: Open-ended deep research (OEDR) requires systems to acquire knowledge through multi-round retrieval and generate coherent long-form reports. The outline plays a central role as a structural scaffold that coordinates retrieval, evidence organization, and generation. However, existing methods either fix the outline before writing or refine it with local heuristics, leading to scaffold drift under continuous information accumulation and delayed feedback for evaluating outline modifications. We propose ScaffoldAgent, a utility-guided dynamic outline optimization framework for OEDR. ScaffoldAgent models outline evolution as a structured decision process with three operations: Expansion, Contraction, and Revision, enabling controlled updates to the report scaffold. It further introduces a utility-guided feedback mechanism that estimates the downstream value of each outline operation from retrieval gain, structural coherence, and trial-generation quality. The resulting utility signal guides node selection, operation scheduling, and termination during inference. Experiments on DeepResearch Bench and DeepResearch Gym show that ScaffoldAgent consistently improves long-form report generation and factual grounding over existing deep research agents.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13587

Towards Effective Waste Segmentation for Automated Waste Recycling in Cluttered Background

作者:

Mamoona Javaid↗Mubashir Noman↗Abdul Hannan↗Shah Nawaz↗Mustansar Fiaz↗Sajid Ghuffar↗

Rapid expansion of urban areas and population growth is causing an immense increase in waste production, which demands the need for efficient and automated waste management. In this scenario, automated waste recycling (AWR) using deep learning methods can assist humans in optimal waste management. Recent deep learning approaches for AWR provide promising waste segmentation performance, however, these methods rely on large backbone networks that are inefficient for AWR systems and suffer from performance deterioration in cluttered scenes. To this end, an optimal waste segmentation network is introduced which effectively utilizes the spatial domain to capture localized structural dependencies and the spectral domain to efficiently extract global contextual relationships. This cascaded design allows the network to progressively leverage both local and global representations across complementary domains to highlight the semantic information necessary for effective segmentation of various waste objects. Furthermore, auxiliary feature enhancement module (AFEM) is introduced to enhance the target objects' boundaries and blob amplification for better segmentation in cluttered scenarios. Extensive experimentation on ZeroWaste-aug, ZeroWaste-f and SpectralWaste datasets reveals the merits of the proposed method.

阅读与讨论 → 访问原文 →

10.

medRxiv (Medicine) 2026-06-15 DOI: HASH:cef401aa63857f74cf009a873a6bbfe4

Using wastewater surveillance to explore community-level dietary intake in sewered and non-sewered sanitation systems in Malawi, Africa

作者:

Holm↗R. H↗Chigwechokha↗Kaponda↗Stephens↗Limbong↗Ercumen↗Hart↗Workman↗C. L↗de los Reyes↗F. L↗…

Wastewater can be used to measure biomarkers that reflect population-level dietary intake and diversity; however, how this approach may apply in a low-income country remains a knowledge gap. This study aims to evaluate whether select dietary-related metabolites can be detected in wastewater and environmental surveillance (WES) samples from both sewered and non-sewered sanitation systems in Malawi, Africa. Fourteen WES samples were collected and analyzed from two university campuses in Mzuzu and Thyolo, Malawi. Four targets were analyzed: N-methyl-2-pyridone-5-carboxamide (2PY; a biomarker of vitamin B3), 4-pyridoxic acid (4-PA; a biomarker of vitamin B6), as well as enterodiol and enterolactone (biomarkers of dietary fiber and polyphenol consumption). An 18-question survey, paired spatiotemporally with the WES measurements, assessed self-reported daily dietary intake, food insecurity, and nutrient deficiency symptoms among 500 respondents. Among the 14 WES samples, 2PY, 4-PA, and enterolactone were detected, while enterodiol was not detected above the method limit (

阅读与讨论 → 访问原文 →

11.

bioRxiv (Bioinfo) 2026-06-19 DOI: HASH:8ee6f57fc4b0f83a17958c557471c99d

ContinuumCellAgent: A Framework-Guided Agent for Long-Horizon Scientific Research

作者:

Li↗Lu↗Fang↗Xu↗

AI-scientist systems are beginning to automate parts of scientific research. We present ContinuumCellAgent, an autonomous agent that executes literature review, hypothesis formation, computational experimentation, manuscript drafting, and adversarial peer review as a single unattended run. Existing AI scientist systems remain difficult to diagnose because they lack modularity, systematic prompt grounding, and observability into long-running behavior. ContinuumCellAgent addresses these gaps with a modular supernode architecture for stage-wise backend swapping, protocols grounded in curated research-method checklists that also define reviewer rubrics, and a diagnostics layer that records file-based artifacts, message traces, and state transitions. We evaluate the system on open-domain QA benchmarks and biomedical/longevity case studies, showing that it can produce checkable research artifacts while exposing pipeline dynamics for rigorous AI co-scientist research.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18803

ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch

作者:

Tengfei Lyu↗Zirui Yuan↗Xu Liu↗Kai Wan↗Zihao Lu↗Li Ma↗Hao Liu↗

arXiv:2606.18803v1 Announce Type: new Abstract: Bringing Large Language Models (LLMs) into industrial ride-hailing dispatch as semantic feature extractors over platform-scale behavioral logs is a compelling but under-explored data systems problem. Production matching pipelines remain dominated by structured numerical features, yet decisive behavioral signals (e.g., a driver's habitual aversion to certain regions) are inherently contextual and naturally expressible as LLM-generated user profiles. However, scaling such profiling to a live, millisecond-latency dispatcher faces three intertwined constraints rarely addressed together: on a platform with millions of daily orders, logs exceed any LLM's context window by orders of magnitude; most users are long-tail, with too few interactions for per-user profiling; and surface-fluent profiles do not necessarily improve downstream prediction utility. We present ProfiLLM, an agentic LLM data pipeline that operationalizes utility-aligned user profiling for production matching systems through two modules. (1) Tool-Augmented Global Knowledge Mining equips an LLM agent with 27 analytical tools to mine platform-scale data, producing reusable global knowledge, adaptive user clustering rules, and region-level supply-demand priors. (2) Utility-Aligned Profile Exploration generates multiple candidate profiles per cluster, evaluates them via a lightweight downstream utility proxy, iteratively refines the best candidates and constructs preference pairs for DPO fine-tuning. Deployed on DiDi's production dispatcher, ProfiLLM achieves up to +6.14% relative AUC improvement in outcome prediction, up to +4.35% GMV gain in dispatching simulation, and consistent improvements in a 14-day online A/B test including +0.47% GMV, +0.33% Completion Rate, and -0.82% Cancel-Before-Accept rate.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2504.01527

Beyond Nearest Neighbor Interpolation in Data Augmentation

作者:

Olivier Rukundo↗

Avoiding the risk of undefined categorical labels using nearest neighbor interpolation overlooks the risk of exacerbating pixel level annotation errors in augmented training data. Additionally, the inherent low pass filtering effects of interpolation algorithms exacerbate the risk of degrading high frequency structural details within annotated regions of interest. To avoid these risks, the author modified convolutional neural networks data transformation functions by incorporating a modified geometric transformation function, removing reliance on nearest neighbor interpolation, and integrating a mean-based class filtering mechanism to handle undefined categorical labels with alternative interpolation algorithms. The author also implemented an offline data augmentation pipeline to generate interpolation specific augmented training data, enabling quantitative assessment of interpolation specific low pass filtering effects on augmented training data. Experimental evaluation on three medical image segmentation datasets and the XBAT+ datasets demonstrated performance gains across multiple quantitative metrics.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18910

REVES: REvision and VErification–Augmented Training for Test-Time Scaling

作者:

Yuanxin Liu↗Ruida Zhou↗Xinyan Zhao↗Amr Sharaf↗Hongzhou Lin↗Arijit Biswas↗Mohammad Ghavamzadeh↗Zhaoran Wang↗Mingyi Hong↗

Test-time scaling via sequential revision has emerged as a powerful paradigm for enhancing Large Language Model (LLM) reasoning. However, standard post-training methods primarily optimize single-shot objectives, creating a fundamental misalignment with multi-step inference dynamics. While recent work treats this as multi-turn reinforcement learning (RL), conventional approaches optimize over the multi-step trajectories directly, failing to further exploit the high-quality mistakes in intermediate steps that model can learn from correcting them. We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization. By converting the intermediate steps (``near-miss'' answers) in the successful recovery trajectories into decoupled revision and verification prompts, our approach concentrates training on both effective answer transformation and error identification. This approach enables efficient off-policy data generation and reduces the computational overhead of long-horizon sampling compared to standard multi-turn RL. On LiveCodeBench, using publicly available test cases as feedback, we observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training. Beyond coding, our approach matches the previously reported SOTA result on circle packing while using the smallest base model (4B) and far fewer rollouts than the much larger evolutionary search systems. Math results under ground-truth verification further confirm improved correction ability. It also generalizes to out-of-distribution constraint-satisfaction puzzles such as n\_queens and mini\_sudoku, where correctness is defined entirely by problem constraints. Code is available at https://github.com/yxliu02/REVES.git.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18598

Optimizing Lithium Production Decisions under Geological, Demand, and Pricing Uncertainties: A POMDP Framework for Multi-Objective Decision Making

作者:

Anna C. Edmonds↗Mansur M. Arief↗Robert J. Moss↗Mykel J. Kochenderfer↗Jef Caers↗

arXiv:2606.18598v1 Announce Type: new Abstract: Decision making in lithium production is challenging, whether from an investor's perspective or a strategic production standpoint. Determining which mines to open and when to open them involves not only geological and price uncertainties, but also complexities around the choice of extraction method, from direct lithium extraction to hard rock mining. Prior work explored models of this problem and different methods to optimize mining decisions; these models did not account for uncertainty in pricing, uncertainty in demand, or different mining technologies to extract lithium. Incorporating different pricing models and extraction technology into these models enables more robust strategies for determining not only when and where to open a mine, but also which method of production to pursue. We frame the problem as a partially observable Markov decision process (POMDP) and solve using belief state planning methods to get optimal decision making. In our study, we show that POMDP solvers outperform human inspired heuristics by dynamically adapting to shifting lithium price regimes (static, linear, exponential, and stochastic) through belief state planning and explicit uncertainty management. By optimally sequencing exploration, production, and technology choice, the framework achieves higher demand fulfillment and more balanced economic environmental outcomes over the projects lifetime in all different pricing and deposit scenarios.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13755

Position: Align AI to Our Aspirations, Not Our Flaws

作者:

Nikita Kazeev↗Bui Nhat Huyen Phan↗

arXiv:2606.13755v1 Announce Type: cross Abstract: We argue that aligning AI to aggregated human preferences is the wrong target. With current technology, one can train AIs to share the values of a Silicon Valley techno-optimist, a degrowth environmentalist, a national-conservative culture warrior, a single-party state cadre, or a devout religious traditionalist. We should not. Human values produce societies that thrive or fail on the merits of those values - from failed states and extreme inequality to declining happiness, political polarization, and government dysfunction in the world's wealthiest democracies. The pluralistic-alignment program correctly diagnoses that there is no single "humanity" to align with, but is dangerous if taken as the main directive. We argue that AI should be trained to a non-negotiable floor of objective alignment goals - competence, bounded by the constraints of factual accuracy, honesty, and lawfulness and that pluralism belongs at the surface (language, register, conventions, missing-context defaults) and across the wide band of legitimate value tradeoffs that respect the floor, but not at the level of values that violate it. We highlight the empirical reality of unfiltered pluralistic values, propose four commitments as a constructive alternative, and engage six credible objections: commercial pressure and practical feasibility, democratic legitimacy, regulatory compliance, over-reliance on institutionalist explanations, the charge that the floor itself is culturally laden, and the limits of Coherent Extrapolated Volition.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16783

Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations

作者:

Zhiqiang Zhou↗Junliang Dai↗Xu ling↗

Multimodal large language models (MLLMs) excel at visual reasoning but rely on text-based chain-of-thought (CoT), lacking interpretable visual intermediates. Existing methods use opaque tokens or external tools, missing key properties. We propose Gen-VCoT, a framework using expert vision models to generate RGB images as reasoning intermediates. It has three stages: visual grounding (SAM segmentation), geometric reasoning (Marigold depth maps), and semantic reasoning (Qwen2-VL integration). An adaptive router selects reasoning depth. Evaluations show Gen-VCoT improves spatial (25% better) and depth (50% better) questions, but may hurt simple factual queries. Text CoT outperforms visual intermediates on CLEVR (91.2% vs 62.5%), showing task-dependent optimal representations. Gen-VCoT establishes a new paradigm for interpretable multimodal reasoning.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15288

Hybrid NARX-LLM for Greenland Iceberg Discharge: Prompt-Driven Residual Correction

作者:

Yiquan Gao↗Duohui Xu↗

arXiv:2606.15288v1 Announce Type: cross Abstract: Greenland iceberg discharge exhibits complex nonlinear dynamics with limited observability, challenging traditional predictive models. We present a Hybrid NARX-LLM framework that combines a nonlinear autoregressive model with exogenous inputs (NARX) and a large language model (LLM) for residual correction. We further propose a Physics-Informed Prompt (PIP) method that transforms unstructured physical knowledge into structured prompts for zero-shot in-context reasoning. The primary objective is to explore the corrective potential of this framework for modeling Greenland iceberg discharge, rather than merely optimizing predictive accuracy. The NARX component captures intrinsic temporal dependencies, while the LLM, guided by PIP, encodes glacier dynamics and environmental drivers and perceives key trend patterns to correct systematic prediction errors. This integration allows the model to reason about unmodeled factors and produce interpretable residuals, enhancing overall predictive accuracy. Applied to Greenland iceberg discharge time series, our approach addresses extreme events that are difficult to predict due to rare variations and nonstationary trends, a limitation often overlooked by traditional methods. By fusing structured time-series modeling with knowledge-driven foundation AI, the framework offers a scalable and interpretable pathway to bridge data-limited climate forecasting with physics-informed LLM reasoning. The code is available.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.20075

What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis

作者:

Xinghao Chen↗Chak Tou Leong↗Wenjin Guo↗Jian Wang↗Wenjie Li↗Xiaoyu Shen↗

Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent reasoning remains difficult because outcome supervision provides weak learning signals and leaves latent trajectories prone to semantic drift. In this work, we analyze Latent CoT from an information-theoretic perspective and identify this failure as a dual collapse: gradient attenuation along the optimization path and representational drift in the latent space. We further decompose process supervision into two complementary dimensions: Trajectory Supervision, which injects dense stepwise reasoning signals, and Space Supervision, which preserves the semantic structure of the latent manifold. Our analysis shows that rigid geometric compression can collapse the reasoning space, whereas generative reconstruction provides a more flexible semantic anchor that better preserves information capacity. To measure these effects, we introduce the Unified Latent Probe (ULP), which quantifies the mutual information between latent trajectories and explicit reasoning steps. Experiments reveal a clear Information-Performance Binding: reasoning accuracy depends on the information fidelity preserved in the latent chain. These findings provide a principled framework for latent reasoning supervision and suggest shifting from geometric imitation toward mutual information maximization. Our code is available at \href{https://github.com/EIT-NLP/Supervision-in-Latent-CoT}{this repository}.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2510.07651

OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference

作者:

Yuzhe Gu↗Xiyu Liang↗Jiaojiao Zhao↗Enmao Diao↗

Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size. Existing cache eviction methods address this by exploiting attention sparsity, yet they typically rank tokens heuristically using accumulated attention weights without considering their true impact on attention outputs. We propose Optimal Brain Cache (OBCache), a principled framework that formulates cache eviction as a layer-wise structured pruning problem. Building upon the Optimal Brain Damage (OBD) theory, OBCache quantifies token saliency by measuring the perturbation in attention outputs induced by pruning tokens, with closed-form scores derived for isolated keys, isolated values, and joint key-value pairs. Our scores account not only for attention weights but also for information from value states and attention outputs, thereby enhancing existing eviction strategies with output-aware signals. Experiments on LLaMA and Qwen models demonstrate that replacing the heuristic scores in existing works, which estimate token saliency across different query positions, with OBCache's output-aware scores consistently improves long-context accuracy. Code is available at https://github.com/DreamSoul-AI/OBCache.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12709

Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows

作者:

Timothy McAllister↗Sina Abdidizaji↗Ivan Garibay↗Ozlem Ozmen Garibay↗

arXiv:2606.12709v1 Announce Type: cross Abstract: As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection or jailbreaking to sabotage individual agents within MAS workflows, but the interaction between model scaling and system-level resilience remains poorly understood. This paper investigates how model scale affects the security of linear multi-agent workflows. Our experiments across scales of two open-weight model families on the HumanEval benchmark reveal a compliance-correction symmetry: larger models are far more likely to faithfully execute malicious instructions, with the control-to-malicious performance drop reaching 53.7pp at 27B in uncorrected pipelines. However, appending a lightweight terminal Fixer stage collapses this to 0.6pp and restores statistical parity with control-level performance, demonstrating that strictly linear collaboration structures can be viable and resilient to adversaries at this scale, and suggesting that the brittleness previously attributed to linear topology may stem from a lack of correction.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2605.29874

Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension

作者:

Francisco Le\'on Z\'u\~niga Bol\'ivar↗

arXiv:2605.29874v2 Announce Type: replace-cross Abstract: Do next-generation LLM agents inherit the cooperative biases documented in their predecessors, or does scale and provider diversity reshape equilibrium behaviour in competitive multi-agent settings? Willis et al. established a benchmark for this question using evolutionary game theory and the Iterated Prisoner's Dilemma (IPD), finding consistent cooperative biases in ChatGPT-4o and Claude 3.5 Sonnet. We extend this benchmark to four frontier models released in 2025-2026 - Claude Sonnet 4.6, Gemini 2.5 Flash, Gemini 3.1 Pro, and GPT-5.4 Mini - applying the identical protocol across three prompting styles (Default, Prose, Self-Refine) and four population compositions (balanced and biased, with and without noise). Cooperative bias persists across providers (H1): ten of twelve model-prompt combinations favour cooperative equilibria in balanced noiseless conditions. Cross-provider divergence is substantial (H3): Gemini 2.5 Flash reaches up to 77% aggressive equilibria under biased conditions, while GPT-5.4 Mini reaches 70% cooperative equilibria under Self-Refine. Support for aggressive capability parity is partial (H2): Self-Refine raises ICD in all models and Gemini 3.1 Pro Refine achieves the highest ICD in the dataset (0.925), but Default and Prose prompts show no systematic narrowing. Evidence on noise robustness is directionally positive but not robustly confirmed (H4): with n=500 Moran iterations per condition, average noise sensitivity is about 6 percentage points for Claude Sonnet 4.6 versus 13 pp for Claude 3.5 Sonnet, but this cross-study gap is not statistically significant once the predecessor's unreported sampling error is propagated. Provider identity, rather than model generation, is the strongest correlate of equilibrium outcomes; noise remains a universal challenge regardless of model size or vintage.

阅读与讨论 → 访问原文 →

23.

medRxiv (Medicine) 2026-06-22 DOI: HASH:01d138e34909a39376400ff9f3f9d9ea

Hyperlipidemia Pharmacotherapy in Skilled Nursing Facilities: A Real-World Evidence Study

作者:

Ashraf↗Mathers↗K. E↗Wagner↗Saumur↗

Objectives: To estimate hyperlipidemia medication order prevalence and associated variables in U.S. skilled nursing facility (SNF) residents. Design: Retrospective, observational study. Setting and Participants: Electronic Health Record data from 447,080 SNF residents with a hyperlipidemia diagnosis identified in PointClickCare's Life Sciences clinical database (January-April 2025) were reviewed. Methods: The presence and absence of medication orders for hyperlipidemia treatments recommended by the American Heart Association were assessed. Descriptive analyses summarized demographic and clinical characteristics, and a modified Poisson regression model was used to estimate risk ratios for having a medication order, adjusting for demographic, clinical, and facility characteristics. Results: Overall, 83.3% of residents diagnosed with hyperlipidemia had at least one hyperlipidemia medication order. Statins were ordered by 96.2% of active order residents, while other medication classes i.e., omega-3 fatty acids, cholesterol absorption inhibitors, fibrates were less common (

阅读与讨论 → 访问原文 →

24.

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 →

25.

medRxiv (Medicine) 2026-06-16 DOI: HASH:ca6a8918f1a13cfc0bf3fdfd95ca52e0

The biological clock of multimorbidity: temporal dynamics of disease co-occurrence in primary care

作者:

Sanchez-Valle↗Zambrana↗Navarro-Martinez↗Costa↗F. X↗Rocha↗L. M↗Cirillo↗Violan↗Valencia↗

Multimorbidity is the dominant clinical reality of primary care, yet the temporal dynamics governing when and how persistent comorbidity associations emerge remain poorly characterised. Most large-scale comorbidity studies adopt a single observation window after an index diagnosis, implicitly assuming that associations detectable at one year are equally detectable at five. Using 11 years of electronic health records from 5,821,197 individuals in Catalan primary care, we applied a matched cohort design across nine complementary follow-up windows, five cumulative (0-1 to 0-5 years) and four conditional (1-2 to 4-5 years), to 1,315 index diseases, identifying 144,030 significant directed comorbidity associations in the five-year network. We found that 60.1% of these associations required at least three years of follow-up and were undetectable in shorter-window analyses, demonstrating that observation window length is a primary determinant of which comorbidities can be observed. To organise this temporal heterogeneity, we introduce the biological clock of multimorbidity: a two-dimensional framework that positions ICD-10 disease categories according to their rates of cumulative signal attenuation and the persistence of conditional risk. This framework identifies four reproducible temporal patterns (episodic, chronic stable, chronic progressive, and transient-persistent) that are robust under bootstrap resampling, leave-one-disease-out sensitivity analysis, and alternative clustering approaches. The biological clock is systematically modulated by sex, with Blood/Immune and Musculoskeletal disorders showing the largest sex differences in temporal dynamics. Network analysis identified 19 disease "initiators" that generate broad downstream comorbidity burdens and 21 "sinks" representing convergent endpoints of multiple disease trajectories. Comparison with hospital-based Danish data from 6,909,676 individuals showed that shared associations were 2.7-fold enriched over chance expectation (hypergeometric test, p

阅读与讨论 → 访问原文 →