Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (quant-ph) 2026-06-25

Bright-state source cancellation in dissipative shortcut Raman atom optics

arXiv:2606.24939v1 Announce Type: new Abstract: Spontaneous Raman scattering limits shortcut-assisted atom optics, but its microscopic origin is obscured once the lossy excited state is adiabatically eliminated. We organize the problem around a single quantity: in the instantaneous dark-bright basis the lower-manifold optical source is carried entirely by the bright-state amplitude, $S=\Omega b$, so that primary spontaneous scattering reduces to the compact functional. This recovers the known dissipative-STIRAP loss in transparent form and makes the action of a shortcut explicit: ideal counterdiabatic STIRSAP cancels the bright-state source, not the optical decay coefficient. We show this cancellation is exact in the full three-level model at the counterdiabatic point, for arbitrary one-photon detuning, Rabi frequency, and pulse duration. The residual source splits into orthogonal quadratures – shortcut mismatch (real) and two-photon Doppler detuning (imaginary) – which invites a velocity-selective protocol that nulls the Doppler quadrature for a chosen momentum class with a second, phase-shifted lower-state field. Our central result is that this source nulling is never superior to simply chirping the two-photon detuning: the two coincide only when the selected class $\delta_c$ is small compared with the bright-state gap, and the nulling degrades and then fails as $\delta_c\to|\mu|$ – precisely the regime of launched or warm clouds and high-order large-momentum-transfer (LMT) optics that motivates velocity selection. The controlling quantity is the magnitude of the residual Hamiltonian perturbation a scheme leaves behind, not the residual source it cancels. As a complement to existing multi-pulse decay budgets, we cast a single-pulse mode-error budget for LMT interferometry entirely in terms of the bright-state source, and delineate when shortcut-assisted Raman control reduces the total scattering cost.

02.
medRxiv (Medicine) 2026-06-18

Cost analysis of overseas versus domestic vaccination of US-bound refugees

Context: To ensure healthy resettlement and protect US health security, the Vaccination Program for US-bound Refugees (VPR) offers some recommended vaccines to refugees overseas before resettlement to the United States. The selected vaccines and number of doses vary by country of departure. VPR was found to be cost-saving in 2018 but had since expanded to more sites. Objective: Assess VPR's current costs and impact on post-arrival domestic vaccination needs and costs. Setting and Participants: A model-based analysis of the Federal government costs for VPR and post-arrival (US) vaccination of resettled refugees separated across five regions: Africa, Asia, the Middle East and North Africa/Republic of Turkiye and Middle East, Europe, and the Americas using fiscal year 2024 data. Design: We quantified and compared full vaccination costs for refugees under two scenarios: (1) 'No VPR' and (2) 'VPR'. Refugees would receive no vaccines overseas and be fully vaccinated after US arrival under 'No VPR'. Under 'VPR', refugees receive one or two doses of selected vaccines overseas before completing vaccination schedules after arrival. Main Outcomes: Costs were reported in 2023 US dollars for 'VPR' and 'No VPR' scenarios and further subdivided by grouping countries/sites depending on whether the International Organization for Migration (IOM) provides vaccination services for refugees (IOM sites) versus non-IOM providers (non-IOM sites). Results: 'VPR' resulted in average net cost savings of $147 per person or $14.7 million per 100,000-refugee cohort compared to providing all vaccines after US arrival ('No VPR'). 'VPR' was cost-saving across most regions, except for IOM sites in Europe, where a net cost of $44 per person was observed. Net cost savings per person were highest for IOM sites in Africa ($333). Conclusions: VPR remains a cost-saving strategy, while protecting US-bound refugees' health and US health security by preventing disease outbreaks during resettlement.

03.
arXiv (CS.AI) 2026-06-15

Silent Failures in Federated Personalization of Foundation Models

arXiv:2606.00947v2 Announce Type: replace-cross Abstract: Foundation models are increasingly personalized on decentralized private data through federated learning and are now deployed at scale under growing regulatory requirements for post-market monitoring. We argue that this convergence creates a distinct and under-recognized class of trustworthiness failures, which we term "Silent Failures." These include amplified bias, fairness collapse, and alignment erosion that may remain difficult to detect because federated learning's privacy constraints limit visibility into model behavior. A landscape analysis of existing benchmarks reveals a structural divide. Federated benchmarks evaluate system performance but provide limited insight into model behavior, whereas centralized trustworthiness benchmarks assess behavior but require model access incompatible with federated privacy. We introduce a taxonomy of six silent failure modes arising from the interaction of foundation model personalization, dataset shift, and core federated constraints. Our analysis shows that privacy-preserving training alone is insufficient for trustworthy deployment. We conclude with a research agenda for privacy-preserving behavioral evaluation and propose that silent failures become a standard diagnostic category for trustworthy federated artificial intelligence.

04.
arXiv (CS.CL) 2026-06-12

From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation

Current evaluations of large language models (LLMs) rely heavily on a growing collection of benchmarks and on aggregate benchmark scores, yet it remains unclear what this comparison actually captures, and what these scores reveal about models' underlying capabilities. Here, we propose a new paradigm for LLM evaluation, by asking whether benchmark performance reflects many independent abilities, or rather relies on a small number of shared dimensions. To answer this, we apply Factor Analysis (FA) to a massive performance matrix of LLMs versus benchmarks \((60\times44)\) revealing an intrinsically low-rank structure of that matrix. That is, a small number of latent factors captures most of the structure in the full task space. This low-rank geometry reveals substantial redundancy across existing tasks and explains why many benchmarks appear to be measuring overlapping abilities. We further show that these latent factors correspond to coherent, skill-like, dimensions of LLM behavior. Leveraging this latent skill-space, we deliver three practical tools for LLM evaluation and downstream users: (i)~identifying redundant tasks, (ii)~profiling new models using a small subset of tasks, and (iii)~selecting models aligned with desired skill profiles. Our method provides a solid alternative to the de-facto standard of a single aggregate score, and establishes an interpretable and practical framework for understanding and benchmarking LLM core capabilities.

05.
arXiv (CS.CL) 2026-06-15

Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models

Byte-level tokenization enables language models to handle any Unicode input, but models can generate invalid UTF-8 sequences when encountering rare or unseen characters. We investigate the relationship between training scale and UTF-8 generation reliability with a 355M parameter model trained on 80B tokens from a balanced multilingual corpus of English, Japanese, Korean, and Chinese. We introduce multiple evaluation protocols that isolate UTF-8 structural validity from language modeling. UTF-8 validity convergence lags perplexity by a roughly a factor of two: perplexity stabilizes after 2.1B tokens, but UTF-8 validity requires 4.2B tokens. In context-free generation, rare characters achieve higher structural validity than common characters, suggesting over-specialization of frequent character representations. Through experiments, we observed that reliable UTF-8 generation is a distinct capability requiring evaluation beyond perplexity.

06.
arXiv (CS.LG) 2026-06-11

PAWS: Preference Learning with Advantage-Weighted Segments

arXiv:2606.11982v1 Announce Type: new Abstract: Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods typically train utility functions on trajectory or segment-level preferences while relying on per-step utility estimates during policy optimization. This training and inference mismatch induces a distribution shift that severely degrades temporal credit assignment and limits policy learning. We analyze this issue and propose PAWS, a segment-based preference learning method that performs policy updates directly using segment-level advantage functions. By aligning utility training with policy optimization, PAWS preserves trajectory-level preference information and avoids unreliable per-step learning signals. Experiments on simulated robotic manipulation and locomotion tasks demonstrate that PAWS consistently outperforms existing PbRL approaches, highlighting the importance of distribution-consistent preference learning.

07.
arXiv (CS.CL) 2026-06-15

Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search

Large-scale multi-tenant retrieval systems generate extensive query logs but lack curated relevance labels for effective domain adaptation, resulting in substantial underutilized "dark data." This challenge is compounded by the high cost of model updates, as jointly fine-tuning query and document encoders requires full corpus re-indexing, which is impractical in multi-tenant settings with thousands of isolated indices. We introduce DevRev-Search, a passage retrieval benchmark for technical customer support built via a fully automated pipeline. Candidate generation uses fusion across diverse sparse and dense retrievers, followed by an LLM-as-a-Judge for consistency filtering and relevance labeling. We further study and systematically evaluate index-preserving query-only adaptation strategies that fine-tune only the query-encoder while keeping the document indices fixed. Experiments on DevRev-Search, SciFact, and FiQA-2018 show that parameter-efficient fine-tuning of the query encoder delivers a remarkable quality-efficiency trade-off, enabling scalable and practical enterprise multi-tenant retrieval.

08.
arXiv (CS.AI) 2026-06-18

Reinforcement Learning Foundation Models Should Already Be A Thing

arXiv:2606.18812v1 Announce Type: cross Abstract: Foundation models for language and vision are powered by internet-scale data, while structured domains (tabular prediction, time-series forecasting, graph learning, reinforcement learning) are not. The substitute is synthetic data, which shifts the burden from collection to prior design. Such priors already exist for many structured tasks: TabPFN and its successors solve tabular classification with a transformer pretrained on a synthetic Bayesian prior. We make two points. First, reinforcement learning is the conspicuous gap: sampling a synthetic MDP is as feasible as sampling a synthetic tabular dataset, yet no in-context RL work treats prior design as a primary objective. Second, MDPs admit a fixed-size sufficient statistic, independent of the episodes observed and tabular in shape, which makes them directly amenable to the attention-based architectures used for tabular foundation models, with a policy head replacing the supervised target. Together these define the agenda for an RL foundation model. As a proof of concept, we train one model entirely on synthetic MDPs and show that, with no task-specific tuning, it solves held-out tabular benchmarks in context, both online and offline: online, in far fewer episodes than UCB-VI and tabular Q-learning, and offline, competitively with VI-LCB.

09.
arXiv (CS.CL) 2026-06-16

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence

While LLMs have substantially advanced text-to-code synthesis, many real programming tasks specify intent through visual artifacts such as screenshots, charts, documents, vector drawings, videos, and interactive states. These tasks require models to connect visual perception to executable programs, because correctness depends not only on syntax but also on layout, geometry, data semantics, editability, interaction behavior, and domain-specific constraints that apply after execution. This survey examines Multimodal Code Intelligence, covering systems that generate, edit, refine, execute, or reason with code under visually grounded inputs and outputs. We first formulate the field by the role that code plays in each task, distinguishing code as a rendered artifact, an editable symbolic structure, a scientific representation, an intermediate reasoning trace, or an executable policy or tool interface. We then organize benchmarks and methods into four domains: Graphical User Interface, Scientific Visualization, Structured Graphics, and Frontier Tasks and Frameworks. This taxonomy connects mature artifact-generation problems to emerging agentic and unified settings and allows us to compare how different tasks treat evidence of correctness. Looking ahead, we argue that future research may benefit from four verification-centered directions. Multi-signal validation can combine complementary evidence of correctness, multi-state verification can test behavior across execution trajectories, cross-task transfer testing can probe reusable visual-code skills, and verifiable agent traces can reveal whether agent actions are grounded in visual evidence. Together, these directions may move multimodal code generation from single-output imitation toward evidence-grounded executable systems.

10.
arXiv (CS.CV) 2026-06-18

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Although Multimodal Large Language Models (MLLMs) demonstrate strong omni-modal perception, their ability to forecast future events from audio-visual cues remains largely unexplored, as existing benchmarks focus mainly on retrospective understanding. To bridge this gap, we introduce FutureOmni, the first benchmark designed to evaluate omni-modal future forecasting from audio-visual environments. The evaluated models are required to perform cross-modal causal and temporal reasoning, as well as effectively leverage internal knowledge to predict future events. FutureOmni is constructed via a scalable LLM-assisted, human-in-the-loop pipeline and contains 919 videos and 1,034 multiple-choice QA pairs across 8 primary domains. Evaluations on 13 omni-modal and 7 video-only models show that current systems struggle with audio-visual future prediction, particularly in speech-heavy scenarios, with the best accuracy of 64.8% achieved by Gemini 3 Flash. To mitigate this limitation, we curate a 7K-sample instruction-tuning dataset and propose an Omni-Modal Future Forecasting (OFF) training strategy. Evaluations on FutureOmni and popular audio-visual and video-only benchmarks demonstrate that OFF enhances future forecasting and generalization. We publicly release all code (https://github.com/OpenMOSS/FutureOmni) and datasets (https://huggingface.co/datasets/OpenMOSS-Team/FutureOmni).

11.
arXiv (CS.AI) 2026-06-12

Benchmarking AI Agents for Addressing Scientific Challenges Across Scales

arXiv:2606.12736v1 Announce Type: new Abstract: AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood. Existing benchmarks for AI agents rarely capture the complexity, heterogeneity, and extended reasoning required by scientific work, whereas benchmarks for scientific tasks often reduce research to static, direct problems and provide limited support for interactive evaluation. Here, we introduce SciAgentArena, a systematic benchmark for evaluating AI agents in real-world scientific research scenarios drawn from emerging needs across multiple domains. SciAgentArena comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents. Using this benchmark, we find that current agents can contribute effectively to well-specified data-analysis workflows, particularly when the task structure and evaluation criteria are clear. However, their performance remains uneven across scientific contexts: agents struggle to generate genuinely novel insights, sustain self-directed exploration, and formulate robust solutions for open-ended research questions. We further characterize common failure modes across agents and identify opportunities for improving their reliability, autonomy, and scientific reasoning. Together, SciAgentArena provides a practical framework for measuring progress in AI agents for science and for guiding the design of future agents capable of addressing complex scientific challenges. Full codes, tasks, and datasets can be accessed via this link: https://sciagentarena.github.io/.

13.
arXiv (CS.AI) 2026-06-25

Agent-as-a-Router: Agentic Model Routing for Coding Tasks

arXiv:2606.22902v2 Announce Type: replace Abstract: Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Consequently, routing each task to the most suitable model becomes critical for both performance and cost. Existing routers treat this as a static, one-off classification problem. However, we identify the performance bottleneck for these routers as information deficit: simply augmenting a vanilla LLM router with performance statistics at the task-dimension level yields a 15.3% relative gain, surpassing a heuristic router built on the same dimension-level priors. Motivated by this finding, we propose Agent-as-a-Router, a framework that formalizes routing as a C-A-F loop (Context->Action->Feedback->Context). It closes the information gap by accumulating execution-grounded experience during deployment. We instantiate this framework as ACRouter, composed of an Orchestrator, a Verifier, a Memory module, and introduce CodeRouterBench, an evaluation environment comprising ~10K task instances with verified scores from 8 frontier LLMs, enabling regret-based router comparison on streaming tasks. Experiments show that ACRouter achieves the lowest cumulative regret on in-distribution tasks and generalizes to out-of-distribution agentic-programming tasks, demonstrating that our routing framework actively closes the information gap. Codes and benchmarks are released at https://github.com/LanceZPF/agent-as-a-router.

14.
arXiv (CS.AI) 2026-06-12

An Explainable AI Assistant for Introductory Programming Education: Improving Feedback Reliability with Instructor-AI Collaboration

arXiv:2606.12425v1 Announce Type: cross Abstract: Active learning is widely recognized as an effective approach for improving learning outcomes in introductory programming courses. However, insufficient instructional support often limits students' access to timely, personalized feedback, which is crucial for mastering foundational programming concepts. Although recent advances in AI, particularly large language models, offer scalable opportunities for feedback, concerns about explainability and reliability remain. In this paper, we present an AI-driven classroom assistant that leverages an explainable AI model to analyze student code, map logical errors to instructor-identified misconceptions, and deliver instructor-authored feedback, thereby grounding reliability in instructor-defined pedagogical knowledge. To evaluate the effectiveness of our framework, we conducted an expert evaluation to examine its alignment with instructor-verified feedback and deployed the system in a classroom setting to assess students' perceptions of its usability. Results indicate that the assistant can provide accurate, instructor-verified feedback to students while fostering a positive experience.

15.
arXiv (CS.CL) 2026-06-25

Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval

Foundation-model agents in multi-step, open-ended environments frequently suffer from compounding errors, where early mistakes contaminate long-horizon trajectories. While Multi-Agent Debate (MAD) succeeds in deterministic domains, agents in subjective tasks like persuasion experience severe problem drift and sycophantic conformity. We identify semantic leakage in standard Retrieval-Augmented Generation (RAG) as a reproducible trigger for these failures, as standard RAG prioritizes vocabulary overlap over logical necessity. To eliminate this leakage, we introduce Taxonomic Strategy RAG (TS-RAG), a systems intervention that routes strategies through a discrete categorical bottleneck to decouple argumentative structure from topical content. Zero-shot, cross-domain evaluations demonstrate that TS-RAG significantly improves the transfer of abstract logic where standard semantic retrieval collapses. Crucially, TS-RAG acts as a "capability bridge" in asymmetric deployments, empowering lightweight persuaders to consistently defeat parametrically superior opponents (improving win rates from 70.5 to 78.5) and accelerating argumentative efficiency. Finally, we introduce trace-level diagnostics via a turn-by-turn Debate State Representation (DSR), demonstrating the necessity of strict constraints to prevent evaluation collapse via default agentic sycophancy.

16.
arXiv (CS.CV) 2026-06-19

Cinematic Compositing Using Character-Environment-Harmonized Video Generation Models

Cinematic compositing aims to integrate green-screen characters into novel environments while maintaining physical and photometric realism. Previous methods often fail to capture the complex bidirectional interactions between characters and their surroundings, which we characterize as Character-to-Environment (C2E) physical interaction and Environment-to-Character (E2C) lighting harmonization. To address this, we propose an end-to-end video diffusion framework that jointly models C2E and E2C interactions, specifically handling the challenges of interactive props. Our approach introduces a tri-mask-guided architecture with RGB-D joint denoising to ensure physically consistent interactions among the character, props, and environment. We further develop an efficient prior-driven data curation pipeline to construct high-quality relighting pairs without expensive rendering. Finally, a reference-conditioned mechanism enables controllable environment synthesis and precise prop replacement. Extensive experiments demonstrate that our framework significantly outperforms existing methods in cinematic-quality dynamic video compositing.

17.
arXiv (CS.LG) 2026-06-11

Fourier Features Let Agents Learn High Precision Policies with Imitation Learning

arXiv:2606.12334v1 Announce Type: new Abstract: High-precision robotic manipulation requires fine-grained spatial reasoning that is often difficult to achieve with RGB-only policies due to depth ambiguity and perspective scale issues. Policies that leverage 3D information directly, such as those based on point clouds, offer a stronger geometric prior over purely image-based ones, yet their performance remains highly task-dependent. We hypothesize that this discrepancy may be due to the spectral bias of neural networks towards learning low frequency functions, which especially affects architectures conditioned on slow-moving Cartesian features. We thus propose to map point clouds from Cartesian space into high-dimensional Fourier space, effectively equipping the point cloud encoder with direct access to high-frequency features. We experimentally validate the use of Fourier features on challenging manipulation tasks from the RoboCasa and ManiSkill3 benchmarks and on a real robot setup. Despite their simplicity, we find that Fourier features provide significant benefits across diverse encoder architectures and benchmarks and are robust across hyperparameters. Our results indicate that Fourier features let policies leverage geometric details more effectively than Cartesian features, showing their potential as a general-purpose tool for point cloud-based imitation learning. We provide source code and videos on our project page: https://fourier-il.github.io/fourier-il

18.
medRxiv (Medicine) 2026-06-22

Accounting for uncertainty in the expected treatment effect substantially increases the sample size required for randomised trials: implications for the feasibility of clinical trials in anaesthesia and critical care

Background Multicentre trials in anaesthesia and critical care report low rates of statistically significant differences. This finding may partly reflect conventional sample size methods, which assume a fixed treatment effect. Assurance methods use a design prior to represent uncertainty in the expected treatment effect, which may provide a more realistic way of estimating sample sizes. Methods We calculated power curves across a range of effect sizes, design priors, and sample sizes using frequentist and Bayesian assurance methods and compared the sample sizes required to achieve 80% and 90% power to the conventional method. We standardised the design priors across effect sizes using the coefficient of variation. We derived a theoretical limit for achievable power. We validated a normal approximation to the Bayesian posterior distribution. Results Frequentist and Bayesian assurance methods produced similar power curves across all scenarios. At a coefficient of variation of 0.5 - reflecting realistic prior uncertainty in the expected effect size - both methods required sample sizes that were approximately 1.5 to 3.5 times larger than the conventional method. The theoretical power limit depends only on the coefficient of variation of the design prior and holds true across all effect sizes. The normal approximation to the Bayesian posterior distribution matched the results obtained from Markov chain Monte Carlo sampling. Conclusions Incorporating clinical uncertainty in the expected effect size substantially increases the sample size required to achieve adequate power, which has important implications for the feasibility of randomised trials in anaesthesia and critical care.

19.
arXiv (CS.CL) 2026-06-16

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning

Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks. In practice, SFT on a full dataset is computationally expensive and sometimes suffers from overfitting or bias amplification. This facilitates the rise of data curation in SFT, which prioritizes the most valuable data to optimze. This work studies the online batch selection family that dynamically scores and filters samples during the training process. However, existing popular methods often (i) rely merely on the utility of data to select a subset while neglecting other crucial factors like diversity, (ii) rely on external resources such as reference models or validation sets, and (iii) incur extra training time over full-dataset training. To address these limitations, this work develops UDS (Utility-Diversity Sampling), a framework for efficient online batch selection in SFT. UDS leverages the nuclear norm of the logits matrix to capture both data utility and intra-sample diversity, while estimating inter-sample diversity through efficient low-dimensional embedding comparisons with a lightweight memory buffer of historical samples. Such a design eliminates the need for external resources and unnecessary backpropagation, securing computational efficiency. Experiments on multiple benchmarks demonstrate that UDS consistently outperforms state-of-the-art online batch selection methods under varying data budgets, and significantly reduces training time compared to full-dataset fine-tuning. Code is available at https://github.com/gfyddha/UDS.

20.
arXiv (CS.LG) 2026-06-11

From inverse problems to neural operators: prediction, mechanism, and generalization of data-driven models

作者:

arXiv:2606.08956v2 Announce Type: replace Abstract: Scientists have historically relied on mathematical models based on differential equations to relate system inputs – forces, fluxes, or heat sources – to outputs, such as displacement, velocity, concentration, and temperature. These models rely on deep domain knowledge to determine the form of the governing differential equation, which is then calibrated with data by solving an inverse problem. In recent years, the field of Scientific Machine Learning has introduced a variety of alternative modeling strategies for physical systems. A method called Sparse Identification of Nonlinear Dynamics learns the governing equation as a sparse linear combination of terms in a user-defined library. Neural Ordinary Differential Equations construct the governing equation by taking in the state and its derivatives at the input layer of a neural network. Entirely foregoing the modeling framework of differential equations, neural operators directly learn a non-linear mapping between the system inputs and outputs. From inverse problems to neural operators, all of these modeling strategies can be conceptualized as data-driven machinery to predict a system's response over a range of inputs. It is then natural to wonder how exactly these various strategies relate to each other, and whether they can be neatly taxonomized. Drawing from the philosophical literature on scientific models, we argue that many model types have a common structure, differing only in the assumed model class of the input-output relation they define. Connecting to philosophical ideas on mechanism, and arguing that data from physical systems arises from solutions to parsimonious differential equations, we propose that only certain models are capable of mechanism discovery, and thus generalization. Our analysis is intended to unite apparently disparate modeling strategies and provide insight into their appropriate use cases.

21.
arXiv (CS.CL) 2026-06-18

GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents

With data-driven development now widely adopted, online A/B testing is an established method for measuring the effects of new technologies. However, deploying online experiments demands resources for design, implementation, and deployment, and may negatively impact users (e.g., unsafe or unethical outcomes) while requiring weeks of data collection. To address this, the growing research area of off-policy evaluation (OPE), or offline A/B testing, assesses new technologies offline using previously collected logged data. OPE is also a fundamental problem in reinforcement learning and is important where online testing is expensive or risky, such as healthcare, recommender systems, education, and robotics. Despite advances in code-generation large language models (LLMs) and agentic workflows, little is known about whether and how LLMs and LLM-based agents can automatically optimize OPE implementations. We propose GrowthHacker, a benchmark that evaluates baseline LLMs and LLM-based agents on large-scale public datasets. GrowthHacker autonomously and iteratively modifies code, runs OPE, and uses the metrics to guide subsequent optimization. We evaluate methods on Open Bandit Pipeline (OBP) and Scope-RL, and develop a two_agent framework that addresses limitations of existing frameworks while reducing complexity. Across both libraries, two_agent shows the highest reliability (98.1%-100% success rate) and positive-outcome rate (78%), with a median improvement of 4.4% among positive outcomes; CrewAI achieves the highest average improvement (37.9%) and is the only framework with zero extreme-value failures. AutoGen and Default each reach 65% positive-outcome rates. These results establish the feasibility of using LLM-based agents as automated "growth hackers" to continuously improve OPE systems, with implications for scaling data-driven decision-making where manual optimization is expensive.

22.
arXiv (CS.AI) 2026-06-15

A Multi-Agent AI System for Automated High School Transcript Processing: Collaborative Document Analysis at Scale

arXiv:2606.13916v1 Announce Type: new Abstract: Each year, college admissions offices face an overwhelming challenge: processing millions of high school transcripts, each with unique formats, grading systems, and layouts. This manual process creates operational bottlenecks that delay admissions decisions and consume valuable resources. We present a transformative solution through a multi-agent AI system where specialized agents collaborate to automatically process diverse transcript formats through intelligent coordination and communication. Our multi-agent architecture consists of three specialized agents-a Pattern Recognition Agent for format-specific parsing, a Semantic Analysis Agent for natural language understanding, and a Vision Intelligence Agent for multimodal document analysis-coordinated by an Orchestration Agent that manages agent communication and result reconciliation. Our key innovation lies in agent-based quality control using GPA extraction as a coordination signal, ensuring reliable agent collaboration and preventing critical information loss. When evaluated on 40 real world transcripts from high schools across 13 U.S. states, our agent system successfully processed every document, achieving 96.7% accuracy compared to expert manual review while maintaining practical processing speeds of 45 seconds per transcript. This work demonstrates how multi-agent coordination can solve complex document processing challenges, offering institutions a scalable, collaborative AI solution that preserves accuracy while dramatically reducing processing time.

23.
arXiv (CS.CV) 2026-06-15

Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editing

Inversion-based image editing offers flexible and training-free control but still struggles with inversion accuracy and the trade-off between editing fidelity and background preservation. While recent methods improve inversion formulations or attention interactions, the role of textual conditioning in shaping diffusion dynamics and editing behavior remains underexplored. We show both empirically and theoretically that the precision of textual conditioning influences inversion stability by modulating the geometry of the diffusion velocity field, while also affecting the consistency of cross-branch attention during editing. These effects directly impact background preservation and semantic fidelity. Building on this analysis, we propose SimEdit, a conditioning-aware framework with two complementary components: (a) conditioning refinement, which constructs conditioning signals with improved semantic precision and structural alignment to facilitate stable inversion and consistent attention manipulation, and (b) token-wise cross-branch attention control, which separates edit-relevant and structure-preserving components and modulates them asymmetrically during attention manipulation. Extensive experiments on PIE-Bench demonstrate that SimEdit consistently improves both inversion reconstruction quality and editing performance over previous attention-manipulation approaches. Our code is available at https://github.com/zju-pi/SimEdit.

24.
arXiv (CS.LG) 2026-06-24

Evaluation Metrics as Averaged Outcomes of Fair Gambles

arXiv:2401.14483v4 Announce Type: replace Abstract: In the current practices of machine learning, the evaluation of forecasts has become a cornerstone of scientific progress. A multitude of evaluation metrics have been suggested and used to qualify "good" forecasts. What do those metrics share? How are they related? In this work, we use a protocol borrowed from game-theoretic probability to show that a large part of evaluation metrics can be viewed as averaged outcomes of fair gambles. Intuitively, a fair gambler is one which a forecaster would expect to fail. Hence, the gambler's ability to gain disproves the quality of the forecast. Standard evaluation metrics are then variants of choices of such fair gambles. In particular, this choice is structured along two dimensions, one of which separates calibration-type and regret-type metrics. In particular, this framework sheds light on the relationship of calibration and regret showing a theoretical equivalence in their ability to evaluate when being scaled appropriately, but the incomparability of obtained scores.

25.
medRxiv (Medicine) 2026-06-11

PCRAgent: A Multi-Agent Framework for Transforming Noisy clinical conversations into Structured Pre-Consultation Medical Records and Reusable Clinical Data Resources

In primary care and outpatient settings, clinically important patient information is often embedded in fragmented, ambiguous, repetitive, and noisy communication between physicians and patients. This limits physicians ability to obtain a clear preconsultation overview of symptoms, history of present illness, and visit intent, while also preventing real world clinical dialogues from being reused in hospital information systems and medical artificial intelligence applications. To address this challenge, we developed PCRAgent, a centrally coordinated multi agent framework for preconsultation clinical information organization. Guided by physician inquiry logic, PCRAgent identifies, extracts, corrects, and standardizes patient-reported information from noisy consultations. Its coordinated modules including error detection, semantic editing, output control, contextual memory, and intent recognition enable robust parallel handling of spelling errors, repetitions, grammatical inconsistencies, medical ambiguities, and non-medical interference. A traceable edit list records intermediate corrections and context, allowing iterative refinement without redundant modifications. PCRAgent generates two complementary outputs. One is a PreConsultation Clinical Report for rapid physician review. The other is a Structured Clinical Conversation Dataset for hospital data construction and downstream AI applications. In evaluations using 220000 strongly perturbed consultations, PCRAgent maintained high robustness, achieving a clinical information accuracy of 4.99 out of 5 and key element completeness of 5 out of 5, outperforming GPT4o. Expert review of Chinese and English dialogues confirmed high clinical accuracy of 4.85 out of 5 and high safety of 4.79 out of 5. Multicenter validation in real-world outpatient workflows further demonstrated practical utility. These findings indicate that PCRAgent can efficiently transform noisy and unstructured consultations into physician ready reports and AI ready structured data, improving outpatient efficiency, reducing cognitive burden, ensuring information completeness, supporting precise decision-making, and enabling high-quality reuse of clinical data.