Explore the Frontier of Global Academia

01.

arXiv (math.PR) 2026-06-25 DOI: arXiv:2606.25135

Convergence Rates for Semistochastic Processes

Authors:

James Broda↗Alexander Grigo↗Nikola P. Petrov↗

arXiv:2606.25135v1 Announce Type: new Abstract: We study processes that consist of deterministic evolution punctuated at random times by disturbances with random severity; we call such processes semistochastic. Under appropriate assumptions such a process admits a unique stationary distribution. We develop a technique for establishing bounds on the rate at which the distribution of the random process approaches the stationary distribution. An important example of such a process is the dynamics of the carbon content of a forest whose deterministic growth is interrupted by natural disasters (fires, droughts, insect outbreaks, etc.).

Read & Discuss → View Source →

02.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2505.15201

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

Authors:

Christian Walder↗Deep Karkhanis↗

Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and reward them independently. This optimizes for pass@1 performance and prioritizes the strength of isolated samples at the expense of the diversity and collective utility of sets of samples. This under-utilizes the sampling capacity, limiting exploration and eventual improvement on harder examples. As a fix, we propose Pass-at-k Policy Optimization (PKPO), a transformation on the final rewards which leads to direct optimization of pass@k performance, thus optimizing for sets of samples that maximize reward when considered jointly. Our contribution is to derive novel low variance unbiased estimators for pass@k and its gradient, in both the binary and continuous reward settings. We show optimization with our estimators reduces to standard RL with rewards that have been jointly transformed by a stable and efficient transformation function. While previous efforts are restricted to k=n, ours is the first to enable robust optimization of pass@k for any arbitrary k

Read & Discuss → View Source →

03.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.24626

SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation

Authors:

Chenyang Zhu↗Jiayu Yao↗Kushal Chawla↗Youbing Yin↗Nathan Wolfe↗Pengshan Cai↗Jingyu Wu↗Spencer Hong↗Sangwoo Cho↗Shi-Xiong Zhang↗Daben Liu↗Sambit Sahu↗…

arXiv:2606.24626v1 Announce Type: new Abstract: As autonomous agents tackle increasingly complex multi-step, multi-agent tasks, their execution trajectories have scaled beyond the constraints of even the largest context windows. Current methods for effectively diagnosing agent failures load the full trajectory into an LLM's context window, which suffers from attention dilution and fails when agentic traces inevitably exceed context limits. To address this, we introduce SAFARI (Scaling long-horizon Agentic Fault AttRibution via active Investigation), a framework that replaces linear context loading with a tool-augmented diagnostic loop. By equipping LLMs with a specialized toolbox to read and search trajectory segments alongside a persistent Short-Term Memory (STM) for cross-turn reasoning, SAFARI effectively decouples diagnostic accuracy from architectural context limits. Our experiments demonstrate that SAFARI outperforms state-of-the-art results by 20% on the Who&When dataset within a 1M token budget, and by 19% on TRAIL GAIA subset on a 25K token budget. Most significantly, SAFARI maintains a 0.58 precision even when the target fault resides 5x beyond the model's native context window, a scenario where traditional evaluators fail entirely.

Read & Discuss → View Source →

04.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17233

Uncertainty Quantification of Engineering Structures by Polynomial Chaos Expansion and Multivariate Active Learning

Authors:

Qitian Lu↗Jafar Jafari-Asl↗Panagiotis Spyridis↗Lukas Novak↗

arXiv:2606.17233v1 Announce Type: new Abstract: In many engineering applications, a single high-fidelity model produces multiple quantities of interest (QoIs) under the same input parameters, e.g. finite element models of complex physical systems. To alleviate the high computational cost of direct model evaluations, surrogate models are widely used to construct efficient approximations of model responses. Naturally, the accuracy of surrogates strongly depends on the quality of the experimental design (ED). However, a single ED may not provide an adequate representation for all outputs simultaneously, especially when different outputs exhibit varying sensitivities to the input variables. A straightforward solution is to perform separate sampling for each output, but this results in increased sampling complexity and computational cost. From a statistical perspective, such an approach also ignores potential correlations among all outputs and may compromise data consistency. To address this issue, an adaptive sequential sampling method for constructing polynomial chaos expansion surrogate models is generalized for vector valued QoIs. The method sequentially selects new samples from a candidate pool based on their local contribution to the output variance, while balancing distance-based exploration of the input space and exploitation of aggregated variance information across all outputs. Its performance is compared with non-sequential Latin Hypercube Sampling through several numerical examples from engineering problems. Numerical results demonstrate that the proposed strategy improves both surrogate accuracy and stability, and provides a more reliable estimation of second-order statistics.

Read & Discuss → View Source →

05.

arXiv (quant-ph) 2026-06-25 DOI: arXiv:2606.25011

Fast and Parallel High-Rate STAR Architecture for Megaquop Quantum Simulation

Authors:

Refaat Ismail↗Milan Kornja\v{c}a↗Hong-Ye Hu↗Nishad Maskara↗Sheng-Tao Wang↗Hengyun Zhou↗Chen Zhao↗

arXiv:2606.25011v1 Announce Type: new Abstract: Fault-tolerant quantum simulation is approaching a phase where encoding overhead, logical Clifford operations, magic-state preparation, and rotation synthesis must be optimized together for efficient implementation. Space-Time efficient Analog Rotation (STAR) architectures reduce two of these costs by preparing small-angle rotation magic states directly, and the transversal STAR variant further lowers the Clifford overhead. Existing concrete implementations, however, largely inherit the low $O(1/d^2)$ encoding rate of the surface code, while high-rate codes have not yet been integrated into comparably explicit architectures. Here, we introduce a high-rate STAR architecture for local lattice Hamiltonian simulation based on a symmetry-driven co-design of the algorithm, QEC code, and neutral-atom hardware. Translation symmetries of the target lattice determine the choice of bicycle chain codes, a tunable family of self-dual bivariate bicycle codes that natively implement Clifford gates required for lattice simulation. Disjoint logical representatives allow STAR injections to be performed in parallel on all $k$ logical qubits in a code block, amortizing resource state preparation and enabling practical post-selection rates. On neutral-atom platform, the same translation symmetry compiles the key logical operations into low-depth, hardware-native acousto-optic-deflector shifts. End-to-end estimates show that an $8 \times 8$ transverse-field Ising simulation to $T^* \approx 8 (zJ)^{-1}$ requires $2240$ physical qubits and $\sim 200$ s per shot, a $\sim 5.5\times$ space reduction relative to a surface code STAR baseline at comparable speed; for Fermi-Hubbard dynamics to $T^* \approx 4 (zt)^{-1}$, the corresponding estimates are $\sim 6300$ physical qubits and $\sim 200$ s per shot. These results provide a concrete route toward early fault-tolerant quantum simulation with high-rate codes.

Read & Discuss → View Source →

06.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2605.11165

COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication

Authors:

Ben Rachmut↗Luise Ge↗William Yeoh↗Ning Zhang↗Yevgeniy Vorobeychik↗

arXiv:2605.11165v2 Announce Type: replace Abstract: Federated learning (FL) in heterogeneous environments remains challenging because client models often differ in both architecture and data distribution. While recent approaches attempt to address this challenge through client clustering and knowledge distillation, simultaneously handling architectural and statistical heterogeneity remains difficult. We introduce COSMOS, a model-agnostic framework that enables server-side personalization using only pseudo-label communication. Clients train local models and predict on the public data; the server clusters clients by prediction similarity, trains a cluster-specific model for each group using its own compute, and distills the resulting models back to clients. We provide the first theoretical analysis showing that distillation from the learned cluster models can yield exponential personalization risk contraction, going beyond the convergence-to-stationarity guarantees typically provided in model-agnostic FL. Experiments across benchmarks demonstrate that COSMOS consistently outperforms all model-agnostic FL baselines while remaining competitive with state-of-the-art personalized FL methods. More broadly, our results highlight personalized server-side learning with pseudo-labels as a promising paradigm for scalable and model-agnostic federated learning in highly heterogeneous environments.

Read & Discuss → View Source →

07.

arXiv (CS.LG) 2026-06-24 DOI: arXiv:2606.24143

AsyncOPD: How Stale Can On-Policy Distillation Be?

Authors:

Wonjun Kang↗Kevin Galim↗Seunghyuk Oh↗Minjun Kang↗Sanghyun Park↗Donghoon Kim↗Minjae Lee↗Minseo Kim↗Rishabh Tiwari↗Yuchen Zeng↗Hyung Il Koo↗Kangwook Lee↗…

arXiv:2606.24143v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts can dominate training time for reasoning workloads. Asynchronous training pipelines can alleviate this bottleneck by decoupling rollout generation from learner updates, but doing so introduces stale-policy data. While prior work has studied stale data in asynchronous RL, its effects in OPD remain underexplored. We present the first systematic study of staleness in asynchronous OPD, focusing on a practical setting where teacher feedback is implemented through local KL losses and full-vocabulary teacher logits are too expensive to store or transfer, necessitating finite teacher-score caches. We first show that KL direction changes the stale-data problem: teacher-weighted forward KL is more robust to stale rollouts, whereas student-weighted reverse KL is vulnerable. Second, for this vulnerable reverse-KL case, we study whether methods designed to stabilize asynchronous RL can mitigate OPD staleness. In our experiments, they do not improve over a simpler OPD-specific surrogate: recomputing the reverse-KL signal under the current student at learner time. Third, we analyze how finite teacher-score caches create a bias-variance tradeoff for sparse and sampled reverse-KL OPD estimators. This motivates multi-sample Monte Carlo (MC), which preserves MC correctability while reducing one-sample variance. Finally, we present and open-source AsyncOPD, a fully asynchronous OPD training pipeline built from these estimator choices. Experiments show that AsyncOPD improves training throughput by $1.6\times$ to $3.8\times$ over strict synchronous training while reaching comparable accuracy.

Read & Discuss → View Source →

08.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12918

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Authors:

Chejian Xu↗Zhaorun Chen↗Jingyang Zhang↗Freddy Lecue↗Avni Kothari↗Sarah Tan↗Wenbo Guo↗Bo Li↗

arXiv:2606.12918v1 Announce Type: cross Abstract: Hierarchical multi-agent systems (MAS) are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particularly under coordinated adversarial behaviors such as privilege escalation and cross-agent collusion. Existing red-teaming approaches for MAS remain limited: they rely on heuristic selection of target agents and perturb isolated message streams, leaving critical questions unanswered as which agents are most responsible for system safety, and how compromised agents can coordinate to bypass defenses. We propose MAStrike, a closed-loop framework for collusive red-teaming in hierarchical MAS. We propose the first agent-level Shapley value analysis for MAS, quantifying each agent's marginal contribution to system robustness under task-specific distributions. GGuided by this attribution, MAStrike identifies vulnerable agent coalitions and generates coordinated, role-aware adversarial manipulations. These attacks are iteratively refined through structured causal diagnosis, attributing failure cases to uncompromised agents that block adversarial attempts. We further build a comprehensive MAS red-teaming benchmark and controllable environments spanning diverse hierarchical topologies and domains, including finance, software engineering, and CRM. Extensive experiments across MAS built on multiple frontier models show that MAStrike substantially outperforms heuristic baselines. Our analysis further uncovers non-trivial Shapley value distributions and higher-order interaction structures among agents, revealing critical vulnerabilities and coordination patterns that are overlooked by prior single-agent or template-based methods.

Read & Discuss → View Source →

09.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12984

SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants

Authors:

Yimin Hu↗Mengtao Xu↗Hao Guo↗Yuheng Song↗Xiaoyong Zhu↗Bo Zheng↗

Image-based AI assistants are now deployed at production scale on e-commerce platforms, where a single uploaded image can trigger fundamentally different user intents: product search, style recommendation, visual encyclopedia, or utility tool calls, each demanding its own response format, tool invocation, and domain knowledge. Without per-intent behavioral constraints, LLM-based systems conflate these heterogeneous modes and fall short of domain quality standards, while the breadth and dynamism of the intent space render manual engineering infeasible. To address this, we present SkillChain, which closes the production feedback loop on Skill evolution, automating the lifecycle of Skills through three stages: Skill Creator for bootstrapping from task specs and trajectories, Route Optimizer for routing alignment, and Body Refiner for iterative Skill Body refinement via dual-path LLM-Judge evaluation. Deployed on a production-scale e-commerce image assistant, SkillChain substantially improves aggregate response quality, with the strongest gains on structural compliance and content quality; a one-week online A/B experiment further confirms significant gains in user engagement, content consumption, and long-term retention.

Read & Discuss → View Source →

10.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.18106

Deep Reinforcement Learning for Minimum Zero-Forcing Sets

Authors:

Steve Halley↗Maur\'icio Gruppi↗

arXiv:2606.18106v1 Announce Type: new Abstract: This paper explores the problem of finding the minimum zero-forcing set on undirected graphs and proposes an adapted machine-learning framework to solve the problem. The minimum zero-forcing set problem is a graph coloring problem where the color of an initial set of nodes propagates throughout a network. The set of nodes is zero-forcing if it forces all uncolored nodes to change color under the constraint of the color-change rule. There are several applications to this problem across different domains such as network science, network control, and designing logical circuits. Finding the minimum zero-forcing set is shown to be NP-hard. We propose a reinforcement learning framework, SD-ZFS, that adapts the S2V-DQN architecture to the ZFS problem. We train several models on this adapted framework and analyze the performance across graph datasets that have varying structures. We evaluate how the models trained on the framework generalize, scale, and transfer to different network types. The results demonstrate the effectiveness of the framework when compared against the optimal solution and greedy heuristic. We provide further insight into how the ZFS problem can be solved through machine-learning and the influence of network structure on the problem.

Read & Discuss → View Source →

11.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2305.06145

Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID

Authors:

Xulin Li↗Yan Lu↗Bin Liu↗Jiaze Li↗Yating Liu↗Qi Chu↗Mang Ye↗Wanli Ouyang↗Nenghai Yu↗

In cloth-changing person re-identification (CCReID), it is critical to learn clothes-invariant feature, which can provide discriminative ID features that remain robust against clothing changes. However, a spurious correlation currently limits existing ReID methods from effectively extracting these clothing-invariant features. This spurious correlation arises from clothing ownership: clothing is rarely shared across different identities, so models tend to memorize clothing cues for identity recognition, and this strategy generalizes poorly to unseen clothing. In this paper, we propose Causal Clothes-Invariant Learning (CCIL), which explicitly shifts CC-ReID from likelihood learning P (Y|X) to causal intervention learning P (Y|do(X)) to block the clothing shortcut. CCIL realizes this intervention through three modules: a Confounder Dictionary, an Intervention Module, and Disentangle Regularization. The causality-based modeling makes the entire model naturally clothes-invariant, effectively preventing the capture of spurious correlations in feature learning. Extensive experiments validate the effectiveness of CCIL. On PRCC and DeepChange datasets, CCIL achieves Rank-1 accuracies of 66.4% and 59.2%, outperforming state-of-the-art methods by 1.4 and 4.1 percentage points, respectively.

Read & Discuss → View Source →

12.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13794

An integrated interpretable control effectiveness learning and nonlinear control allocation methodology for overactuated aircrafts

Authors:

Umut Demir↗Aamir Ahmad↗Walter Fichter↗

arXiv:2606.13794v1 Announce Type: cross Abstract: Nonlinear dynamics and the strong couplings that arise between multiple effectors undermine the assumptions behind conventional, linear control allocation techniques. When flight enters regimes where nonlinear effects dominate, linear allocators exhibit reduced accuracy due to increased model mismatch, which subsequently degrades performance and robustness of the flight control system. High fidelity onboard models and black box data driven approaches can recover accuracy across the flight envelope, but respectively impose computational burdens prohibitive for real time allocation and sacrifice the interpretability required for verification and fault diagnosis. This paper addresses these limitations by learning an explicit, physics constrained analytical model of the control effectiveness mapping from representative flight data using Sparse Identification of Nonlinear Dynamics. The resulting mapping is compact, interpretable, and admits analytical derivatives, enabling efficient computation within nonlinear solvers that additionally incorporate actuator dynamics, without requiring an onboard model. An online adaptation mechanism monitors prediction residuals and refreshes the model when significant plant changes are detected, providing graceful reconfiguration under actuator failures and varying operating conditions. The methodology is evaluated on a high fidelity nonlinear benchmark aircraft across a range of aggressive maneuvers, achieving accuracy comparable to a full nonlinear onboard model while substantially reducing computational cost relative to established baselines.

Read & Discuss → View Source →

13.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2606.25181

Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable Assistant

Authors:

Milosz Dudek↗Daria Hemmerling↗Kamil Kwarciak↗Maciej Stroinski↗Maria Pensko↗Mateusz Kowalewski↗Leonid Pavlovskyi↗Sebastian Jurczak↗Anna-Mariia Vitkovska↗Zuzanna Miodonska↗Natalia Mocko↗Michal Krecichwost↗…

arXiv:2606.25181v1 Announce Type: cross Abstract: Early identification of speech sound errors in children is often limited by access to specialists, motivating lightweight screening tools that can operate outside the clinic. We present a screening pipeline for Polish-speaking children focused on sibilant substitutions, coupling a wav2vec2-based CTC token recognizer with alignment-based error typing and a template-grounded caregiver assistant for screening, not diagnosis. On a held-out test set of 10 unseen children comprising 559 utterances, the recognizer achieves 88.7 percent exact sequence match. As a conservative screening proxy, we flag a mismatch when the system emits substitution-evidence bracketed tokens at the target segment, yielding 72.9 percent precision, 61.4 percent recall, F1 = 0.67, and a 2.7 percent false-alarm rate on target-correct items. We describe the assistant's safety boundaries and outline a clinician-in-the-loop validation plan for future deployment.

Read & Discuss → View Source →

14.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2606.24147

Progressive Alignment Objectives for Aligner-Encoder based ASR

Authors:

Jaeyong Lee↗Masato Mimura↗Takafumi Moriya↗

Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th encoder position, so the encoder must learn the alignment internally without cross-attention or a transducer lattice. In practice, this alignment often forms abruptly in the upper layers, making training sensitive and brittle on long utterances. We propose InterAligner, which adds an intermediate Aligner objective so alignment can form progressively across depth, together with an intermediate CTC loss (InterCTC) to stabilize optimization. On LibriSpeech with a 17-layer Conformer, a final-only Aligner reaches 5.0/7.8 WER (test-clean/other). InterCTC improves to 3.4/6.0, and InterAligner further reduces WER to 3.1/5.6 with the largest gains on long utterances.

Read & Discuss → View Source →

15.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2510.18832

Sharp Transitions for Subsystem Complexity

Authors:

Yale Fan↗Nicholas Hunter-Jones↗Andreas Karch↗Shivan Mittal↗

arXiv:2510.18832v2 Announce Type: replace-cross Abstract: The circuit complexity of time-evolved pure quantum states grows linearly in time for an exponentially long time. This behavior has been proven in certain models, is conjectured to hold for generic quantum many-body systems, and is believed to be dual to the long-time growth of black hole interiors in AdS/CFT. Achieving a similar understanding for mixed states remains an important problem. In this work, we study the circuit complexity of time-evolved subsystems of pure quantum states. We find that for greater-than-half subsystem sizes, the complexity grows linearly in time for an exponentially long time, similarly to that of the full state. However, for less-than-half subsystem sizes, the complexity rises and then falls, returning to low complexity as the subsystem equilibrates. Notably, the transition between these two regimes occurs sharply at half system size. We use holographic duality to map out this picture of subsystem complexity dynamics and rigorously prove the existence of the sharp transition in random quantum circuits. Furthermore, we use holography to predict features of complexity growth at finite temperature that lie beyond the reach of techniques based on random quantum circuits. In particular, at finite temperature, we argue for an additional sharp transition at a critical less-than-half subsystem size. Below this critical value, the subsystem complexity saturates nearly instantaneously rather than exhibiting a rise and fall. This novel phenomenon, as well as an analogous transition above half system size, provides a target for future studies based on rigorous methods.

Read & Discuss → View Source →

16.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18699

TW-LegalBench: Measuring Taiwanese Legal Understanding

Authors:

Fei-Yueh Chen↗Chun Huang Lin↗Chan Wei Hsu↗Kuan Hsuan Yeh↗Zih-Ching Chen↗Kuan-Ming Chen↗Patrick Chung-Chia Huang↗

Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet their performance on jurisdiction-specific legal reasoning remains underexplored. We present TW-LegalBench that utilizes Taiwanese legal system's rich official corpus open to the public to fill the gap in evaluating LLMs on Taiwanese law, among common-law benchmarks that focus on English sources and civil-law benchmarks focusing on sources of Simplified Chinese. TW-LegalBench comprises three task types: (1) over 16,000 multiple-choice questions (MCQs) across five years of official examinations in 18 professional domains; (2) 117 open-ended essay questions (OEQs) from examinations for legal professionals with official scoring rubrics; and (3) more than 14,000 legal judgment prediction (LJP) instances covering hundreds of crime categories. We evaluate 13 LLMs using accuracy for MCQs, a decomposed LLM-as-Judge framework based on the scoring rubric points for OEQs, and metrics for sentencing accuracy and statute citation for LJP. Our results reveal that top-performing models exceed the passing threshold for qualified lawyers (passing rate: 11%) but fall short of that for judges and prosecutors (passing rate: 1~2%). For LJP, while models demonstrate reasonable verdict type accuracy and sentence prediction capability, they struggle to cite exact legal articles. These findings highlight that reliable legal text generation remains challenging for LLMs, even though their performance on qualification examinations approaches human level.

Read & Discuss → View Source →

17.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11482

Building Social World Models with Large Language Models

Authors:

Haofei Yu↗Yining Zhao↗Guanyu Lin↗Jiaxuan You↗

Understanding and predicting how social beliefs evolve in response to events – from policy changes to scientific breakthroughs – remains a fundamental challenge in social science. Given LLMs' commonsense knowledge and social intelligence, we ask: Can LLMs model the dynamics of social beliefs following social events? In this work, we introduce the concept of the Social World Model (SWM), a general framework designed to capture how social beliefs evolve in response to major events. SWM learns state-transition functions for social beliefs by mining temporal patterns in social data and optimizing the evidence lower bound, without the need for explicit human annotations linking events to belief shifts, or for expensive census data. To evaluate SWM, we introduce a benchmark, SWM-bench, derived from real-world prediction markets, specifically Kalshi and Polymarket. SWM-bench includes over 12k data points for social belief prediction tasks spanning diverse domains such as politics, finance, and cryptocurrency. Our experimental results show that SWM significantly outperforms time-series foundation models, achieving state-of-the-art results on Kalshi data and demonstrating competitive performance on Polymarket data, while offering interpretable insights into the underlying mechanisms of social belief dynamics.

Read & Discuss → View Source →

18.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19852

Prompt, Plan, Extract: Zero-Shot Agentic LLMs Workflows for Lung Pathology Extraction from Clinical Narratives

Authors:

Aman Pathak↗Cheng Peng↗Mengxian Lyu↗Ziyi Chen↗Reema Solan↗Sankalp Talankar↗Yasir Khan↗Hiren Mehta↗Aokun Chen↗Yi Guo↗Yonghui Wu↗

Information extraction from pathology reports is essential for cancer staging, tumor registry population. Yet key data remains embedded in narrative reports, making manual extraction labor-intensive and error-prone. Traditional supervised Natural Language Processing pipelines address this through fully supervised Named Entity Recognition and Relation Extraction, but require expensive manual annotation and suffer cascading failures when upstream entities are missed. In this study, we developed a zero-shot, agentic workflow, and evaluated five open-source generative Large Language Models (LLMs) to populate 13 College of American Pathologists synoptic fields from lung resection pathology reports. We compared them against a state-of-the-art supervised GatorTron NER-RE baseline using a novel, registry-aligned evaluation framework. The baseline achieved Micro-F1of 0.960, while the best zero-shot model (GPT-OSS-20B) achieved Micro-F1 of 0.893 (recall: 0.949), accurately extracting complex relations like Pathologic Stage without task-specific training. These results suggest that open-source, zero-shot agentic LLMs are a low-cost solution for extracting lung pathology information.

Read & Discuss → View Source →

19.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18832

Target-confidence Recourse Using tSeTlin machines: TRUST

Authors:

K. Darshana Abeyrathna↗Sara El Mekkaoui↗Nils Enric Canut Taugb{\o}l↗Anuja Vats↗

arXiv:2606.18832v1 Announce Type: cross Abstract: Counterfactual explanations are widely used to provide algorithmic recourse in high-stakes decision-making systems. Most existing methods seek the smallest change to an input that flips a model's decision. However, decision-makers often rely not only on predicted labels but also on confidence thresholds and risk margins. Counterfactuals that barely cross a decision boundary can be fragile and unstable under noise or model variation. In this paper, we propose Target-confidence Recourse Using tSeTlin machines (TRUST), a framework in which users explicitly specify the desired prediction confidence for recourse. Rather than generating counterfactuals and evaluating confidence afterward, TRUST directly searches for minimal changes that satisfy a user-defined confidence target, enabling comparison of recourse options in terms of cost, confidence, and robustness. We instantiate TRUST using a Probabilistic Tsetlin Machine (PTM) combined with Bayesian optimization. The probabilistic clause-based structure of PTM links prediction confidence to the stability of decision rules. We show that counterfactuals satisfying the same rules can still differ substantially in reliability depending on how securely they satisfy those rules, revealing whether decisions are supported by robust or fragile clause activations. Experiments on synthetic and real-world datasets demonstrate that target-confidence counterfactuals produce more robust and interpretable recourse than conventional boundary-based approaches. Across multiple benchmarks, TRUST achieves perfect robustness while maintaining low recourse cost, including an L2 distance of 0.10 on the Haberman dataset at 0.92 confidence. By explicitly controlling confidence and exposing rule-level stability, TRUST provides actionable recourse for high-stakes decision support.

Read & Discuss → View Source →

20.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12733

Let's Ask Gauss: Improved One-Run Privacy Auditing

Authors:

Adya Agrawal↗Yu Wei↗Jaspal Singh↗Malik Magdon-Ismail↗Vassilis Zikas↗

arXiv:2606.12733v1 Announce Type: new Abstract: Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guarantees hold in practice. We study empirical privacy auditing for differentially private (DP) machine learning, focusing on efficient one-run methods for mechanisms such as DP-SGD. Prior one-run approaches threshold training examples or "canaries" into binary membership guesses, which discards useful information. We show that, in the white-box DP-SGD setting, canary-aligned signals naturally form a sequence of random variables whose normalized sum is asymptotically Gaussian. Leveraging this distributional perspective, we develop a DP-auditing framework that leads to tighter privacy lower bounds from a single training run.

Read & Discuss → View Source →

21.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2505.02281

Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles

Authors:

Amir Ali Farzin↗Yuen-Man Pun↗Philipp Braun↗Iman Shames↗

arXiv:2505.02281v3 Announce Type: replace-cross Abstract: This paper explores the performance of a random Gaussian smoothing zeroth-order (ZO) scheme for minimising quasar-convex (QC) and strongly quasar-convex (SQC) functions in both unconstrained and constrained settings. For the unconstrained problem, we establish the ZO algorithm's convergence to a global minimum along with its complexity when applied to both QC and SQC functions. For the constrained problem, we introduce the new notion of proximal-quasar-convexity and prove analogous results to the unconstrained case. Specifically, we derive complexity bounds and prove convergence of the algorithm to a neighbourhood of a global minimum whose size can be controlled under a variance reduction scheme. Beyond the theoretical guarantees, we demonstrate the practical implications of our results on several machine learning problems where quasar-convexity naturally arises, including linear dynamical system identification and generalised linear models.

Read & Discuss → View Source →

22.

medRxiv (Medicine) 2026-06-22 DOI: HASH:1e7879d832d4cffaf496156082807a77

Toward less intrusive pubertal assessment: longitudinal evaluation of tanner and non-tanner metrics in East African adolescents

Authors:

Anok↗J. J↗Prodger↗J. L↗White↗Yang↗Park↗D. E↗Bukenya↗S. P↗Kiboneka↗Agaba↗…

Background: Accurate pubertal assessment is essential in pediatric endocrinology and adolescent health research. While Tanner staging remains the gold standard, its subjective nature and invasive genital examination limit feasibility and acceptability, especially in longitudinal studies and culturally sensitive settings. This study evaluated less intrusive pubertal assessment combinations that maintain discriminative accuracy. Methods: We conducted a longitudinal study among 200 uncircumcised, sexually naive males aged 15-17 years in Southwestern Uganda, with quarterly follow-up over three years. Clinicians assessed Tanner staging metrics (pubic hair, testicular volume, penile length, scrotal color), axillary hair, and serum testosterone. Markov transition models estimated Tanner stage progression. Ordinal logistic regression and area under the receiver operating characteristic curve (AUC) analyses quantified discriminative performance of individual and combined metrics. Results: At baseline, participants were distributed across Tanner stages II (6.0%), III (13.5%), IV (55.0%), and V (25.5%). Among individual metrics, pubic hair distribution best predicted overall Tanner stage (AUC=0.867), while penile length was least predictive (AUC=0.833). The full four-metric Tanner model achieved high discrimination (AUC=0.993). However, a less intrusive combination of pubic hair and scrotal color achieved comparable discrimination (AUC=0.942), improving to AUC=0.953 with axillary hair and age. Markov modeling demonstrated frequent bidirectional transitions between Tanner stages IV and V, reflecting variability in longitudinal staging. Conclusions: A minimally intrusive assessment combining pubic hair, scrotal color, axillary hair, and age reliably predicts pubertal stage, offering an acceptable alternative to traditional Tanner staging for research and surveillance contexts where genital manipulation is impractical or unethical.

Read & Discuss → View Source →

23.

Nature (Science) 2026-06-17 DOI: HASH:a5f2a9c05f945c6c584c25c203e1cce1

Towards Conversational AI for Disease Management

Authors:

Valentin Liévin↗

While large language models (LLMs) have shown promise in diagnostic dialogue1, their capabilities for effective management reasoning—including disease progression, therapeutic response, and safe medication prescription—remain under-explored. We advance the previously demonstrated diagnostic capabilities of the Articulate Medical Intelligence Explorer (AMIE)1−3 through a new LLM-based agentic system optimized for multi-visit clinical management and dialogue. To ground its reasoning in authoritative clinical knowledge, AMIE leverages Gemini’s long-context capabilities4, combining in-context retrieval with structured reasoning to align its output with up-to-date clinical practice guidelines and drug formularies. In a randomized, blinded virtual Objective Structured Clinical Examination (OSCE) study, AMIE was compared to 21 primary care physicians (PCPs) across 100 multi-visit case scenarios designed to reflect UK NICE Guidance and BMJ Best Practice guidelines. AMIE was non-inferior to PCPs in management reasoning as assessed by specialists and scored better in both preciseness of treatments and investigations, and in its alignment with and grounding in clinical guidelines. To benchmark medication reasoning, we developed RxQA, a multiple-choice question benchmark derived from two national drug formularies (US, UK) and validated by board-certified pharmacists. Though AMIE and PCPs both benefited from the ability to access external drug information, AMIE outperformed PCPs on higher difficulty questions. While further research would be needed before real-world translation, AMIE’s strong performance across evaluations marks a significant step towards conversational AI as a tool in disease management.

Read & Discuss → View Source →

24.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2506.01274

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

Authors:

Hosu Lee↗Junho Kim↗Hyunjun Kim↗Yong Man Ro↗

Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame selection strategies, albeit with the rapid development of video-specialized LMMs. Prior works attempted to solve this with static heuristics or external retrieval modules to feed frame-level information, but these approaches often fail to capture visual cues grounded to the given user queries conflating raw visual dynamics with true semantic relevance. In this paper, we introduce ReFoCUS (Reinforcement-guided Frame Optimization for Contextual UnderStanding), the first framework to integrate online policy-gradient reinforcement learning into frame-level optimization for video-LLMs. ReFoCUS aims to learn a frame selection policy, leveraging reward signals derived from reference models to capture their underlying scoring behavior over frame combinations that best support temporally grounded responses. To efficiently explore the large combinatorial frame space, we employ an autoregressive and query-conditional selection architecture that ensures contextual consistency while reducing complexity. Our policy learning removes the need for explicit frame-level supervision, as it implicitly discovers optimal and semantically consistent frame compositions. ReFoCUS consistently improves reasoning accuracy across multiple video QA benchmarks, demonstrating the advantage of aligning frame selection with model-internal utility.

Read & Discuss → View Source →

25.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2602.18291

Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies

Authors:

Zhuoran Li↗Hai Zhong↗Xun Wang↗Qingxin Xia↗Lihua Zhang↗Longbo Huang↗

arXiv:2602.18291v2 Announce Type: replace Abstract: Online Multi-Agent Reinforcement Learning (MARL) is a prominent framework for efficient agent coordination. Crucially, enhancing policy expressiveness is pivotal for achieving superior performance. Diffusion-based generative models are well-positioned to meet this demand, having demonstrated remarkable expressiveness and multimodal representation in image generation and offline settings. Yet, their potential in online MARL remains largely under-explored. A major obstacle is that the intractable likelihoods of diffusion models impede entropy-based exploration and coordination. To tackle this challenge, we propose among the first \underline{O}nline off-policy \underline{MA}RL framework using \underline{D}iffusion policies (OMAD) to orchestrate coordination. Our key innovation is a relaxed policy objective that maximizes scaled joint entropy, facilitating effective exploration without relying on tractable likelihood. Complementing this, within the centralized training with decentralized execution (CTDE) paradigm, we employ a joint distributional value function to optimize decentralized diffusion policies. It leverages tractable entropy-augmented targets to guide the simultaneous updates of diffusion policies, thereby ensuring stable coordination. Extensive evaluations on MPE and MAMuJoCo establish our method as the new state-of-the-art across $10$ diverse tasks, demonstrating a remarkable $2.5\times$ to $5\times$ improvement in sample efficiency.

Read & Discuss → View Source →