Explore the Frontier of Global Academia

01.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2605.30208

Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency

Authors:

Chris Adams↗Arjun Singh Banga↗Parveen Bansal↗Souvik Bhattacharya↗Payal Bhuptani↗Rujin Cao↗Pedro Canahuati↗Nate Cook↗Brian Ellis↗Prabhakar Goyal↗Gurinder Grewal↗Tianyu He↗…

arXiv:2605.30208v2 Announce Type: replace-cross Abstract: AI-assisted coding tools have altered software production. At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and per-developer diff volume rose 51%, with agentic AI responsible for over 80% of that growth. Meanwhile, the share of diffs receiving timely review has declined, exposing a widening gap between code supply and reviewer bandwidth. We ask three questions that progress from feasibility through calibration to impact: (1) can risk-stratified automation operate at scale across diverse organizations, (2) how does tuning the risk threshold affect the trade-off between automation yield and safety, and (3) to what extent does automated review reduce end-to-end latency for AI-generated changes? We deployed RADAR (Risk Aware Diff Auto Review), a multi-stage funnel that classifies each diff by authorship and source type, applies eligibility gates, static heuristics, a machine-learned Diff Risk Score, LLM-based Automated Code Review, and deterministic validation before landing qualifying changes. We evaluate RADAR through telemetry covering 535K+ RADAR-reviewed diffs, observational before-after comparisons for policy changes, and difference-in-differences analysis of efficiency outcomes. RADAR has reviewed 535K+ diffs and landed 331K+. Relaxing the Diff Risk Score threshold from the 25th to the 50th percentile increased the approve rate to 60.31%. The revert rate for RADAR-reviewed diffs is 1/3 that of non-RADAR diffs, and the Production Incident rate is 1/50 that of non-RADAR diffs. RADAR reduces median time to close by over 330% and median diff review wall time by 35%. Risk-aware layered automation can materially reduce review bottlenecks created by AI-driven code growth without compromising production safety.

Read & Discuss → View Source →

02.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2604.10389

BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection

Authors:

Saukun Thika You↗Nguyen Anh Khoa Tran↗Wesley K. Marizane↗Hanshu Rao↗Qiunan Zhang↗Xiaolei Huang↗

Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two domain expert agents distinct knowledge bases to produce independent analyses; when the experts disagree, a structured counter-argumentation round and cross-source adjudication resolve the conflict, followed by a cascading safety layer that filters common false-positive patterns. We evaluate BLUEmed on a clinical terminology substitution detection benchmark under both zero-shot and few-shot prompting with multiple backbone models spanning proprietary and open-source families. Experimental results show that BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines. Further analyses across six backbone models and two prompting strategies confirm that retrieval augmentation and structured debate are complementary, and that the framework benefits most from models with sufficient instruction-following and clinical language understanding.

Read & Discuss → View Source →

03.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13608

AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility

Authors:

Xiaoyuan Liu↗Jianhong Tu↗Yuqi Chen↗Siyuan Xie↗Sihan Ren↗Tianneng Shi↗Gal Gantar↗Evan Sandoval↗Donghyun Lee↗Daniel Miao↗Peter J. Gilbert↗Nick Hynes↗…

arXiv:2606.13608v1 Announce Type: new Abstract: Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate interfaces, one for the benchmark and one for the agent, while AAA only needs one; this yields a generic, unified framework that separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and reproducibility. To evaluate our design at scale, we conduct two studies: a five-month open competition that drew 298 judge agents across 12 categories together with 467 subject agents from independent participants, showing that AAA applies across a heterogeneous range of benchmarks; and a case study on coding agents that confirms agentified evaluation preserves fidelity with the public record while surfacing previously missing head-to-head results, yielding research insights about agent design. Combining a community-scale field study and a controlled coding case study, we verify that AAA delivers coverage, practicality, and fidelity across heterogeneous scenarios at scale. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.

Read & Discuss → View Source →

04.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.12120

A Riemannian Approach to Low-Rank Optimal Transport

Authors:

Pratik Jawanpuria↗Bamdev Mishra↗

arXiv:2606.12120v1 Announce Type: new Abstract: Low-rank optimal transport (OT) mitigates the quadratic scaling of classical solvers, yet existing approaches rely heavily on first-order mirror-descent updates that require careful hyperparameter tuning and ignore the optimization landscape's curvature. To address these limitations, we propose a unified Riemannian geometric framework for low-rank OT, modeling balanced and unbalanced rank-$r$ positive factored couplings as novel smooth embedded submanifolds of the positive orthant. By equipping these manifolds with the Fisher-Rao product metric, we derive tractable formulations for Riemannian projectors, retractions, and Hessian-vector products. Our cost-agnostic framework seamlessly extends to linear OT, Gromov-Wasserstein (GW), fused GW, and their unbalanced counterparts. For balanced OT, our geometric ingredients are computed via efficient conjugate-gradient and iterative Bregman updates. For the unbalanced OT, our operations elegantly reduce to closed-form scalings, completely eliminating inner iterative loops. In both regimes, per-iteration complexity scales linearly with dataset size, and we provide a rank-sufficiency certificate for global optimality verification. Extensive experiments across a range of problem sizes demonstrate that our regularization-free first- and second-order solvers achieve faster convergence and superior performance over existing state-of-the-art low-rank OT solvers.

Read & Discuss → View Source →

05.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15881

Biarchetype analysis for univariate functional data. An application to macroeconomic financial time series

Authors:

Aleix Alcacer↗Rafael Benitez↗Vicente J. Bolos↗Irene Epifanio↗

arXiv:2606.15881v1 Announce Type: cross Abstract: We introduce biarchetype analysis for the first time in the context of univariate functional data. This unsupervised methodology extends archetype analysis by simultaneously identifying archetypal structures across both the cases (countries, in our application) and the temporal argument. Both cases and time points are expressed as mixtures of biarchetypes, yielding a concise and highly interpretable representation of complex functional observations. Although biarchetype analysis is not intended as a clustering technique, it offers superior interpretability compared with biclustering approaches, as it is based on extreme, representative patterns rather than average centroids, thereby enhancing human comprehension. We apply the proposed method to 10-year government bond yields of European countries over the period 2001-2025. The results identify three distinct time regimes (the pre-crisis period, the euro-area sovereign debt crisis, and the post-crisis period), and reveal Germany, Greece, and Hungary as country archetypes.

Read & Discuss → View Source →

06.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20373

AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning

Authors:

Zepeng Li↗Jie Ren↗Zhanyong Tang↗Jie Zheng↗Zheng Wang↗

arXiv:2606.20373v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a multi-agent framework for compiler performance tuning that uses compiler and runtime evidence to guide LLM-generated optimization decisions. Rather than treating the compiler as a black box like prior auto-tuning schemes, AutoPass opens up the compiler to the LLM, enabling it to query compiler-internal optimization states and analyze the intermediate representation to orchestrate compiler options. The search process iteratively refines optimization configurations using measured runtime feedback to diagnose regressions and guide latency-improving edits. AutoPass operates in an inference-only, training-free setting and requires no offline training or task-specific fine-tuning, making it readily applicable to new benchmarks and platforms. We implement AutoPass on the LLVM compiler and evaluate it on server-grade x86-64 and embedded ARM64 systems. AutoPass outperforms expert-tuned heuristics and classical autotuning methods, achieving geometric-mean speedups of 1.043x and 1.117x over LLVM -O3 on x86-64 and ARM64, respectively.

Read & Discuss → View Source →

07.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13643

Recursive Agent Harnesses

Authors:

Elias Lumer↗Sahil Sen↗Kevin Paul↗Vamse Kumar Subbiah↗

Recursive language models (RLMs) showed that recursion over model calls is an effective strategy for long-context reasoning, and production coding agents have begun to write code that spawns subagents at scale, most recently in Anthropic's dynamic workflows. We name and study the pattern between these two lines of work, where the recursive unit is a full agent harness with filesystem tools, code execution, and planning rather than a model call with no tools. We call this the Recursive Agent Harness (RAH) and frame it as harness recursion, the code-first extension to the model recursion of RLMs. A parent agent generates and runs an executable script that spawns subagent harnesses in parallel for fine-grained workloads and uses structured function calls for small subtasks. We provide a controlled evaluation on long-context reasoning. With the backbone held fixed at GPT-5 to match the published Codex and RLM baselines, RAH improves the Codex coding-agent baseline from 71.75% to 81.36% on Oolong-Synthetic (199 samples, 13 context-length buckets up to 4M tokens), a gain attributable to the harness rather than the model. With a stronger backbone, Claude Sonnet 4.5, the same design reaches 89.77%.

Read & Discuss → View Source →

08.

Nature (Science) 2026-06-17 DOI: HASH:3e86c94c31c859aecb93ee5d133f1aa7

Lethal plague outbreaks in Lake Baikal hunter-gatherers 5,500 years ago

Authors:

Ruairidh Macleod↗

Plague is among the most devastating diseases in human history1. However, early strains of the plague-causing bacterium Yersinia pestis lacked virulence factors that are required for the bubonic form until around 3,800 years ago2,3. Consequently, the morbidity and mortality of early plague strains remain unclear. Here we describe early plague strains that are associated with two phases of outbreaks among mid-Holocene hunter-gatherers near Lake Baikal in southeast Siberia, beginning from about 5,500 years ago. These outbreaks occur across four hunter-gatherer cemeteries, with a 39% detection rate for plague infection. By reconstructing kinship pedigrees, we show that small familial groups were affected, consistent with human-to-human spread of disease, and that the first outbreak occurred within a single generation. The infections appear to have resulted in acute mortality, especially among children (aged 8 to 11 years). We further note functional differences, including in the ypm superantigen locus, which is also present in present day Yersinia pseudotuberculosis. The new strains diverge ancestrally to known Y. pestis and constrain the timing of its emergence, indicating that this happened before approximately 5,700 years ago. These findings show that plague outbreaks happened earlier than previously thought and were indeed lethal. We contend that the occurrence of outbreaks among mid-Holocene hunter-gatherer communities well outside the sphere of Late Neolithic Europe challenges the notion that higher population densities and lifestyle changes during the Neolithic agricultural transition were prerequisites for plague epidemics. Analyses of ancient DNA from hunter-gatherers near Lake Baikal in southeast Siberia around 5,500 years ago indicate that highly virulent Yersinia pestis emerged earlier than previously estimated, far from the next known cases of infection in Late Neolithic Europe.

Read & Discuss → View Source →

09.

medRxiv (Medicine) 2026-06-15 DOI: HASH:266b3d0161a06b994fc62243b3890604

Wellbeing After Stroke-2 (WAterS-2): a feasibility study with process evaluation exploring inclusive, accessible, online psychological support after stroke

Authors:

Longley↗Woodward-Nutt↗Cotterill↗Chouliaria↗Thomas↗Bamford↗Bowen↗Patchwood↗

Objectives: Explore feasibility and acceptability of upskilling a workforce to deliver a co-developed intervention, based on Acceptance and Commitment Therapy (ACT), to support psychological adjustment post-stroke targeting underserved groups. Design: Multi-site, single-arm feasibility study with embedded mixed-methods process evaluation (ISRCTN17628580). Setting: Four NHS community stroke services across England. Participants: 1. Stroke survivors [≥]18 years of age, [≥]4 months post-stroke, reporting psychological difficulties adjusting to stroke, able to consent and access remote group sessions in English; 2. Group facilitators from NHS stroke services, not ACT specialists. Intervention: WAterS-2: an eight-session, remotely-delivered ACT-informed group intervention. Outcome measures: Recruitment, fidelity, safety, acceptability and perceived value were assessed using fidelity checklists, post-intervention surveys and semi-structured interviews with stroke survivors and facilitators. Clinical outcomes including mood (HADS), wellbeing (ONS4), psychological flexibility (AAQ-ABI), measured post-group and three-months later. Results: Nineteen stroke survivors recruited (mean 9.6 months post-stroke; n=5 (26%) minoritised ethnicities; n=10 (52%) with aphasia). Thirteen facilitators - including two peer support workers - delivered the intervention with fidelity following structured training across four services. Drop-out was low (2/19; 11%); with 15 (79%) attending [≥]5/8 sessions. Remote data collection was feasible (79% follow-up completion), with no adverse events recorded. Acceptability was high: survivors valued peer connection, grounding and mindfulness practices. ACT metaphors were helpful for some but challenging for others, including some with aphasia. Online delivery was suitable but limited informal connection. Facilitators reported increased capability, incorporating ACT skills into routine care. NHS workforce pressures and geographically-constrained referral pathways limited recruitment reach. Conclusions: WAterS-2 is feasible, safe, acceptable and inclusive. A mixed workforce, including NHS peer support workers, can be upskilled to deliver with fidelity. Inclusion of underserved groups is achievable but requires active strategies beyond standard NHS referral routes. Findings inform a provisional logic model and a future pragmatic trial.

Read & Discuss → View Source →

10.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.18032

INI-VPINN: A Variational Physics-Informed Neural Network with Implicit Neumann and Interface Handling for Multi-Material Domains with Geometric Singularities

Authors:

Shayan Dodge↗Alessandro Formisano↗Sami Barmada↗

arXiv:2606.18032v1 Announce Type: cross Abstract: We propose a new weak-form Physics-Informed Neural Network approach (named INI-VPINN). INI-VPINN naturally incorporates Neumann boundary and interface conditions into the variational formulation. It removes the need for additional loss terms or multiple subdomain networks. This framework employs compact support weighting functions and integration by parts to implicitly impose flux and continuity constraints. In this way, it implicitly ensures physical consistency across material boundaries. The proposed method is tested on Poisson and Laplace problems with sharp interfaces and complex geometries. Results show that, compared with several other Physics Informed Neural Networks-based formulations, the INI-VPINN consistently achieves higher accuracy, smoother and faster convergence. The proposed framework provides a general approach for solving multimaterial problems with complex geometries and mixed Neumann-Dirichlet boundary conditions using neural networks. The implementation is publicly available in a GitHub repository.

Read & Discuss → View Source →

11.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15837

Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation

Authors:

Jimut B. Pal↗Suyash P. Awate↗

Deep neural networks (DNNs) frequently fail to generalize to out-of-distribution (OOD) medical images because of variations in scanners and acquisition protocols. Retraining DNN models to address these distribution shifts is often impractical due to the high cost of acquiring and annotating new medical datasets. To address this, we introduce VarDeepPCA, a novel lightweight variational DNN framework designed to restore/refine degraded segmentation maps by leveraging intrinsic geometric priors. Unlike existing approaches that require target-domain data or extensive pre-training, our VarDeepPCA explicitly learns a distribution of valid anatomical geometries using only small in-distribution (ID) datasets. Theoretically, our novel variational learning framework leverages a reinterpretation of the softmax mapping to implicitly perform exact distribution modeling, thereby enabling computationally efficient, sampling-free learning and inference. This also enables VarDeepPCA to provide uncertainty estimates associated with its restored segmentation maps. We empirically validate our framework across 4 distinct clinical applications, using 14 publicly available datasets, involving segmentation of the myocardium, neuroretinal rim, prostate, and fetal head. Comparisons against 15 existing methods demonstrate that VarDeepPCA consistently restores segmentation maps produced by the existing methods on OOD data to (i) significantly improve anatomical plausibility of geometries and clinical utility of the segmentations, and (ii) significantly reduce errors, without needing any more training data than that used by existing methods.

Read & Discuss → View Source →

12.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17639

ERQA-Plus: A Diagnostic Benchmark for Reasoning in Embodied AI

Authors:

Hong Yang↗Basura Fernando↗

Generalist embodied agents require more than object recognition: they must reason about spatial relations, actions, procedures, human intentions, environmental constraints, and commonsense consequences from situated visual observations. Yet existing visual and embodied question answering benchmarks often provide limited control over the reasoning dependencies being tested, making it difficult to distinguish grounded embodied reasoning from shortcut-driven visual or linguistic pattern matching. We present ERQA-Plus, a diagnostic benchmark for reasoning in embodied AI. ERQA-Plus contains 1,766 question-answer instances grounded in 711 robot-centric images and organized according to a structured taxonomy spanning perceptual, action-centric, social-interaction, navigation-environmental, and contextual commonsense reasoning. The dataset is constructed using a multi-stage generation and validation pipeline that combines taxonomy-guided question generation, automatic quality judging, iterative revision, and human assessment to improve visual grounding, answer validity, and reasoning quality. We benchmark representative general-purpose vision-language models and embodied models, including LLaVA-NeXT-8B, Prismatic-7B, MiniCPM-V-4.5-8B, Qwen3-VL, RoboRefer-8B, and RoboBrain2.5-8B. Although the strongest model, Qwen3-VL-32B, achieves 83.4% overall accuracy and 61.4 SBERT score, category-level results reveal persistent weaknesses in spatial reasoning, procedural reasoning, event prediction, and intention inference. ERQA-Plus therefore provides a fine-grained evaluation framework for measuring not only whether embodied agents answer correctly, but also which forms of embodied reasoning they can and cannot perform reliably. The dataset is available https://huggingface.co/datasets/huggingdas/erqa-plus and the project page at https://github.com/LUNAProject22/erqa-plus.

Read & Discuss → View Source →

13.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15497

Towards End-to-End Automation of AI Research

Authors:

Yutaro Yamada↗Robert Tjarko Lange↗Cong Lu↗Chris Lu↗Shengran Hu↗Jakob Foerster↗David Ha↗Jeff Clune↗

arXiv:2606.15497v1 Announce Type: new Abstract: The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific process, a system that autonomously navigates the entire research lifecycle – from conception to publication – has remained out of reach. Here, we present the strongest demonstration to date toward automating the entire process end-to-end. We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyzes data, writes the entire scientific manuscript and performs its own peer review. Its ideas, execution, and presentation are of sufficient quality to produce a manuscript generated by an AI system that passes the first round of peer review at a major machine learning conference workshop. The workshop has an acceptance rate of 70 percent. Our system leverages modern foundation models within a complex agentic system. We evaluate The AI Scientist in two settings: a focused mode using human-provided code templates as an initial scaffold to conduct research on a specific topic, and a template-free, open-ended mode that leverages agentic search for wider scientific exploration. Both settings produce diverse ideas and automatically test, report on, and evaluate them. This achievement demonstrates AI's growing capacity for scientific contribution and signifies a potential paradigm shift in how research is conducted. As with any impactful new technology, there could be significant risks, including taxing overwhelmed review systems and adding noise to scientific literature. However, if developed responsibly, such autonomous systems could greatly accelerate scientific discovery.

Read & Discuss → View Source →

14.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.10813

RedAct: Redacting Agent Capability Traces for Procedural Skill Protection

Authors:

Shuwen Xu↗Zhitao He↗Yi R. Fung↗

Users rely on execution traces to observe agent behavior, diagnose failures, and ensure accountability. These traces contain rich procedural detail, including tool invocations, intermediate decisions, and error-recovery logic. Yet this detail can expose private procedural skills, allowing downstream methods to recover key formulas, thresholds, and strategies without access to model weights or skill files. To quantify this risk and evaluate protection, we construct \textsc{CapTraceBench}, a benchmark of 75 specialized long-horizon tasks and 154 curated skills across seven domains. We also introduce \textsc{RedAct} https://github.com/XuShuwenn/RedAct, a protected trace release framework that localizes protected key information, rewrites traces while preserving verifier-critical evidence, and embeds behavioral watermarks for downstream provenance analysis. Across representative trace reuse methods, \textsc{RedAct} reduces normalized skill transfer (NST) from 44.7–67.1\% on raw traces to below the no-skill baseline, while preserving audit evidence. Its standalone behavioral watermarks reach 93.6–100.0\% true detection with a false alarm rate of at most 1.9\%. These results frame public agent traces as security interfaces and show that selective redaction can reduce procedural capability leakage without removing audit evidence.

Read & Discuss → View Source →

15.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13529

Ride, Track, and Recover: Pilot Randomized Trial of a Wearable Digital Self-Management Intervention During a Veteran Endurance-Cycling Program

Authors:

Alan Ta↗Nilsu Salgin↗Caleb Armstrong↗Kala Phillips Reindel↗Farzan Sasangohar↗

arXiv:2606.13529v1 Announce Type: cross Abstract: Post-traumatic stress disorder (PTSD) in veterans is characterized by persistent hyperarousal and comorbid anxiety and depressive symptoms that are difficult to monitor and manage outside clinical settings. Thirteen veterans participating in a Project Hero cycling event in Texas were randomized by computer-generated sequence in a naturalistic setting to two arms: (1) digital intervention plus physical activity, or (2) physical activity only, plus a third at-home monitoring control cohort consisting of 7 veterans selected from the broader Project Hero veteran community. Continuous smartwatch sensing combined heart rate and accelerometer features to detect hyperarousal events, which were confirmed in real time by participants. Weekly self-report measures of anxiety, depression, and PTSD severity were collected. Generalized additive mixed models characterized nonlinear trajectories over time. Baseline-normalized hyperarousal trajectories differed significantly across conditions, with the digital intervention group (n=7) showing structured stabilization compared to late-study escalation in the physical-only group (n=3). Both cycling groups exhibited acute symptom improvements during the endurance event; however, the digital intervention group demonstrated a higher overall maintenance of gains. The at-home control group (n=4) showed gradual symptom declines. Perceived precision of ML detections varied substantially across individuals and was positively associated with symptom severity, with higher-severity participants confirming a greater proportion of detected events. These results suggest that coupling wearable detection with digital self-management tools may support stabilization of hyperarousal and symptom improvement while emphasizing the importance of personalization and human-centered design in wearable mental health systems.

Read & Discuss → View Source →

16.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11456

AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable

Authors:

Meysam Alizadeh↗Fabrizio Gilardi↗Mohsen Mosleh↗Enkelejda Kasneci↗

The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may amplify the analytic flexibility through which researchers reach motivated conclusions. We argue these worries target two empirically separable layers: a design layer of methodological choices, and a verdict layer in which a decision rule maps estimates to a substantive claim. We test both by running 20 independent executions of Claude Code and Codex on a prominent immigration and social-policy against a many-analysts human baseline. At the design layer, Codex matches human methodological diversity and Claude Code produces nearly three times as many specifications; both agents' effect estimates remain broadly aligned with the human consensus, and no agent model exactly matches any human model. A prompt-induced anti-immigration researcher prior reorganizes each agent's methodological decisions but, unlike for biased human analysts in the same data, does not shift aggregate estimates or final verdicts; nor do agents reroute along the methodological axes humans use to bias their estimates. At the verdict layer, an explicit confirmatory prompt flips Claude Code's verdicts from 10% to 90% support while leaving its coefficient distribution essentially unchanged, operating through rule omission rather than rule softening. AI agents can rival or exceed human methodological diversity at the design layer while remaining vulnerable at the verdict layer. In our setting, the locus of AI bias is not estimation but interpretation.

Read & Discuss → View Source →

17.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19212

Generalised Eigenvalue Geometry of Semantic Adversarial Attacks

Authors:

Martin Anthony↗Kaveh Salehzadeh Nobari↗

arXiv:2606.19212v1 Announce Type: cross Abstract: Recent empirical work shows that semantically equivalent paraphrases can fool financial sentiment classifiers: although a paraphrase remains close to the original under a strong reference embedding, it may shift the target model's representation enough to change the predicted class. Existing robustness theory either assumes a single-model threat model or focuses mainly on empirical attack algorithms. We develop a continuous local model of semantic paraphrase perturbations that captures this two-model structure. We show that the worst-case local displacement of the target representation, subject to a proxy-model budget, is governed by the largest generalised eigenvalue of a matrix pencil $(A,B)$ constructed from the Jacobians of the two embedding maps. The resulting attackability index $\lambda^*(x)$ is intrinsic to the local paraphrase geometry and the chosen embedders, yields a closed-form prediction-flip condition for affine readouts, and supports conservative population and finite-sample attackability certificates. For uniform control over classes of affine readouts, we derive a distribution-free VC bound for binary attackability indicators and a scale-sensitive margin bound based on an attackability-adjusted margin that subtracts a local geometric penalty from the standard classifier margin. We also connect the continuous theory to discrete paraphrase search, identify an asymmetry between successful and unsuccessful finite searches, and give a covering condition under which the discrete and continuous settings agree. Finally, we propose an empirical verification framework using soft-token relaxations and generated paraphrase sets to assess the local eigenvalue geometry, prediction-flip condition, and finite-search approximation on a deployed financial-text classifier.

Read & Discuss → View Source →

18.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13035

TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment

Authors:

Yu Meng↗Xiangyang Luo↗Letian Li↗Wenyuan Jiang↗Chen Gao↗Xinlei Chen↗Yong Li↗Xiao-Ping Zhang↗

Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift. In this paper, we propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation. TetherCache organizes the cache into sink, memory, and recent regions, and introduces two complementary mechanisms. First, GRAB (Gated Recall with Attention-Diversity Balancing) selects long-range memory frames using a gated score that combines attention-based relevance with temporal diversity, preserving informative yet diverse historical context under a fixed cache budget. Second, TAME (Trusted Alignment via Memory Editing) lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution, reducing the pollution caused by drifted historical features. Built on Self-Forcing, TetherCache consistently improves long-video generation quality on VBench-Long across 30s, 60s, and 240s settings. In particular, for 240s generation, it substantially improves overall and semantic scores while reducing quality drift from 7.84 to 1.33, demonstrating its effectiveness for stable long-horizon autoregressive video diffusion.

Read & Discuss → View Source →

19.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11386

Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering

Authors:

Cheng-Kuang Chang↗Kai-Wei Chang↗Alexander H. Liu↗James Glass↗

Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored. We analyze the predictive behavior encoded in FD-SLM hidden representations and find that they exhibit stream-specific predictive patterns: during listening, they preferentially predict the incoming user stream, whereas during speaking, they preferentially predict the model output stream. Building on this observation, we show that FD-SLMs dynamically modulate their internal predictive focus between two states: a generative state aligned with model output generation and a perceptive state aligned with incoming user input. However, this modulation can lag behind abrupt changes in conversational context. During user interruptions, the model remains transiently biased toward the generative state before transitioning into the perceptive state, causing it to miss the beginning of the incoming input. We term this delayed internal transition state inertia. To quantify its downstream impact, we introduce the Zero-Buffer Benchmark (ZBB), a diagnostic benchmark for evaluating immediate interruption comprehension when user speech begins abruptly. We evaluate this setting using response correctness and initial-word occurrence rate (IWOR). Finally, we mitigate state inertia through activation steering with a perception vector, a training-free intervention with little additional computational overhead. Across multiple state-of-the-art FD-SLMs, activation steering substantially improves interruption handling; for example, on PersonaPlex, it improves correctness from 28% to 45% and IWOR from 40% to 72% without any fine-tuning.

Read & Discuss → View Source →

20.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.12353

Gate-tunable spin-valley transport via carrier velocity in monolayer WSe$_2$

Authors:

Otman Bouladiane↗Hocine Bahlouli↗Clarence Cortes↗David Laroze↗Ahmed Jellal↗

arXiv:2606.12353v1 Announce Type: cross Abstract: We theoretically investigate spin- and valley-resolved quantum transport in monolayer tungsten diselenide (WSe$_2$) described by an effective massive Dirac Hamiltonian. Particular attention is devoted to a finite barrier region characterized by simultaneously modulated Fermi velocity and scalar potential. The barrier velocity $v_2$ is related to the external velocity $v_1$ through a velocity ratio $\xi=v_2/v_1$, motivated by an optical analogy with the Snell-Descartes law. The exact refraction condition depends on the full spin- and valley-resolved dispersion, and the simple ratio $\xi=v_2/v_1$ is recovered only in the massless, symmetric limit. The interplay of intrinsic spin-orbit coupling in the conduction and valence bands, quantified by $\lambda_c$ and $\lambda_v$, with spin- and valley-dependent Zeeman fields, $M_s$ and $M_v$, gives rise to substantial changes in the quasiparticle dispersion, leading to pronounced modifications of the transport characteristics. By solving the Dirac equation and enforcing current-conserving matching conditions at the interfaces, we compute the spin- and valley-dependent transmission probability and conductance. Our results demonstrate that the barrier velocity, scalar potential, incidence angle, incident energy, and barrier width serve as effective control parameters for transport, giving rise to strong anisotropy and resonant tunneling features. Furthermore, we show that both the magnitude and orientation of spin- and valley-polarized currents can be continuously tuned via velocity and potential modulation. These findings establish combined velocity and potential engineering as a powerful theoretical framework for controlling spin-valley physics in two-dimensional transition-metal dichalcogenides.

Read & Discuss → View Source →

21.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2601.16407

Jacobian Scopes: token-level causal attributions in LLMs

Authors:

Toni J. B. Liu↗Baran Zadeo\u{g}lu↗Nicolas Boull\'e↗Rapha\"el Sarfati↗Gurbir Arora↗Christopher J. Earls↗

Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the proliferation of layers and attention heads in modern architectures. We propose Jacobian Scopes, a suite of gradient-based, token-level causal attribution methods for interpreting LLM predictions. Grounded in perturbation theory and information geometry, Jacobian Scopes quantify how input tokens influence various aspects of a model's prediction, such as specific logits, the full predictive distribution, and model uncertainty (effective temperature). Through case studies spanning instruction understanding, translation, and in-context learning (ICL), we demonstrate how Jacobian Scopes reveal implicit political biases, uncover word- and phrase-level translation strategies, and shed light on recently debated mechanisms underlying in-context time-series forecasting. To facilitate exploration of Jacobian Scopes on custom text, we open-source our implementations and provide a cloud-hosted interactive demo at https://huggingface.co/spaces/Typony/JacobianScopes.

Read & Discuss → View Source →

22.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2505.08413

Improved delta-kick cooling with multiple nonideal kicks

Authors:

Harshil Neeraj↗David C. Spierings↗Joseph McGowan IV↗Nicholas Mantella↗Aephraim M. Steinberg↗

arXiv:2505.08413v2 Announce Type: replace Abstract: Delta-kick cooling is a technique employed to achieve low kinetic temperatures by decreasing momentum width at the cost of increased position width. In an ideal implementation, this method uses a harmonic potential to deliver a single near-instantaneous momentum kick. In practice, potentials that are approximately harmonic near their center are commonly used. As a result, the breakdown of the harmonic approximation far from the center limits the cooling performance. Inspired by aberration cancellation in optics, we propose to use compound matter-wave lens systems for $\delta-$kick cooling with Gaussian potentials. By strategically combining attractive and repulsive kicks, we show that it is possible to mimic the effect of a harmonic potential. For a test case with reasonable experimental parameters, our method suggests a reduction in kinetic temperature by a factor of $2.5$ using a 2-pulse sequence and by a factor of $3.2$ using a 3-pulse sequence.

Read & Discuss → View Source →

23.

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 →

24.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14728

FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty

Authors:

Harry Zhang↗Luca Carlone↗

Vision-language models (VLMs) are playing an increasingly important role across multiple domains. In many applications, such as robotics, it is crucial to quantify the uncertainty in the output of these models. } We develop FUSE, a probabilistic framework for capturing two complementary sources of uncertainty in vision-language modeling: (i) aleatoric embedding-level uncertainty derived from input data vision-language ambiguity, and (ii) epistemic model-level uncertainty estimated from the semantic response diversity of VLMs. Our approach formulates a Bayesian fusion mechanism that analytically combines these uncertainty sources to produce a scalar measure of uncertainty. This measure can be used to reliably predict the model's output correctness for downstream applications. We demonstrate that our method outperforms baselines and achieves SOTA uncertainty calibration.

Read & Discuss → View Source →

25.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15078

Cognitive Debt: AI as Intellectual Leverage and the Dynamics of Systemic Fragility

Authors:

Shuchen Meng↗

arXiv:2606.15078v1 Announce Type: new Abstract: We develop a formal theory of cognitive debt: the stock of unverified reasoning obligations that accumulates when individuals use AI as a substitute rather than a complement for first-principles cognition. The model features two state variables per agent, cognitive capital and cognitive debt, and a multiplicative production technology in which cognitive capital functions as collateral that determines the return to AI adoption. We establish six propositions. Rational agents incur positive cognitive debt because the costs are deferred, partially external, and masked by short-run productivity gains. Tranquil periods lower subjective risk assessments, raise AI substitution intensity, and compound leverage, generating a cognitive Minsky moment in which subjective risk falls while true systemic fragility rises. Expected crisis losses are convex in aggregate leverage. Post-crisis, output-target pressure can produce a false-correction loop in which agents patch AI failures with more AI. The decentralised equilibrium over-adopts substitutive AI relative to the social optimum because of systemic risk, cognitive public goods, and arms-race externalities. In a two-type heterogeneous-agent economy, high-cognitive-capital agents adopt AI more intensively and may eventually erode their unaided cognitive capital below that of initially lower-skilled agents.

Read & Discuss → View Source →