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 (CS.CL) 2026-06-16

SkillWiki: A Living Knowledge Infrastructure for Agent Skills

While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki is a living knowledge infrastructure that supports the organization, grounding, and continuous evolution of agent skills by transforming heterogeneous knowledge into reusable skill assets linked to their originating evidence. Our demonstration presents the complete skill lifecycle, from knowledge ingestion and skill production to provenance-aware exploration, governance, and execution-driven evolution. SkillWiki highlights a future in which knowledge, skills, and execution experience co-evolve within a shared infrastructure. The live demonstration and source code are publicly available at https://github.com/Huangdingcheng/SkillWiki.

02.
arXiv (CS.AI) 2026-06-16

Intrinsic Computational Functionalism and Simulated Consciousness

arXiv:2606.15348v1 Announce Type: cross Abstract: A common objection to artificial or simulated consciousness is that a simulated brain is no more conscious than simulated water is wet. We address this from the perspective of Intrinsic Computational Functionalism (ICF): if consciousness is computationally constituted, it depends not on externally imposed descriptions but on the computational structures a system physically realizes in virtue of its own causal-dynamical organization. In previous work we developed Canonical Functionalism as a mathematically precise special case of this anti-interpretivist program, identifying functional states by their complete future input-output roles under a fixed interface. Here we argue that this input-output construction, though important, is incomplete: as a behavioral boundary case of ICF, it makes lookup tables and unfolded systems that preserve the same boundary behavior canonically equivalent. A consciousness-relevant canonical representation must instead include internal mechanisms, interventions, and joint readouts belonging to the relevant intrinsic organization. We therefore define a mechanism-enriched canonical structure and use it to formulate Intrinsic Causal-Computational Realization (ICCR), a realization relation preserving physical implementation, intrinsic state individuation, transition structure, intervention profiles, and the relevant agent-body-world boundary. The central result is conditional: if conscious properties are invariants of intrinsic causal-computational organization, then any system satisfying ICCR realizes the same consciousness-relevant properties, whether biological, artificial, or simulated. We discuss objections including biological naturalism and integrated information theory. We conclude that to deny consciousness to a simulation, one must identify a consciousness-relevant intrinsic causal-computational structure that the simulation fails to realize.

03.
arXiv (quant-ph) 2026-06-19

Quantum correlations in QBism's reconstruction program

arXiv:2606.07485v2 Announce Type: replace Abstract: QBism recasts quantum theory as a normative framework for an agent's probability assignments, with the Born rule taking the form of a consistency condition known as the Urgleichung. Motivated by this perspective, qplex theories provide a broader class of probabilistic models in which the sets of valid states and measurements are constrained by QBist-inspired geometric conditions. While qplexes have been extensively studied for single systems, their implications for bipartite correlations remain largely unexplored. In this work, we investigate bipartite correlations in qplex theories by expressing joint expectation values as inner products between suitably defined $C$-vectors. This geometric formulation allows Bell-type inequalities to be studied as optimization problems over qplex-compatible probability assignments. We first analyze the CHSH scenario and show that the shared inner-product structure of the $C$-vectors restricts the maximal value to the Tsirelson bound $2\sqrt{2}$. We then turn to the three-outcome CGLMP inequality $I_{2233}$ and find that the same qplex-derived norm and inner-product constraints allow a violation of up to $\leq 2+2\sqrt(3)/3 \approx 3.1547$ versus the quantum maximum of $\approx 2.8729$, thereby exhibiting super-quantum correlations. These results show that qplex geometry captures enough structure to reproduce an important quantum bound in the two-outcome case, but not enough to recover the full set of quantum correlation constraints. The analysis therefore suggests that additional principles are needed to complete the QBist reconstruction of quantum theory.

04.
arXiv (CS.CL) 2026-06-16

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas. However, their effectiveness in complex mathematical reasoning involving multi-step FOL deductions is still under-researched. While LLMs perform competitively on established mathematical reasoning benchmarks, they struggle with multi-step FOL tasks, as demonstrated by Deepseek-Prover-V2-7B's low accuracy (4.2%) on our proposed theorem proving dataset. This issue arises from the limited exploration of diverse proof strategies and the potential for early reasoning mistakes to undermine entire proofs. To address these issues, we propose DREAM, a self-adaptive solution that enhances the Diversity and REAsonability of LLMs' generation strategies. DREAM incorporates an Axiom-Driven Strategy Diversification mechanism to promote varied strategic outcomes and a Sub-Proposition Error Feedback to help LLMs reflect on and correct their proofs. Our contributions include pioneering advancements in LLMs' mathematical reasoning through FOL theorem proving, introducing a novel inference stage solution that improves performance by 0.6% to 6.4%, and providing a curated dataset of 447 mathematical theorems in Lean 4 format for evaluation.

05.
arXiv (CS.CL) 2026-06-18

CEO-Bench: Can Agents Play the Long Game?

Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real-world challenges require a combination of sophisticated skills that remain largely untested in agents: (1) navigating long horizons amid uncertainty; (2) acquiring information in noisy environments; (3) adapting to a changing world; (4) orchestrating multiple moving parts toward a coherent goal. We introduce CEO-Bench, which evaluates these capabilities together by simulating a representative real-world task: operating a startup for 500 days. An agent manages pricing, marketing, budgeting, and many other aspects of a fictional company through a programmable Python interface, operating in the same environment and facing the same challenges as a human CEO. Success demands analyzing noisy, interconnected business databases, translating signals into sound strategy, and coordinating many decisions with programming. The strongest agents write sophisticated code that simulates customer cohorts to forecast future cash and mines negotiation history to uncover hidden customer preferences. Even so, most state-of-the-art models struggle in this environment. Only Claude Opus 4.8 and GPT-5.5 finish above the $1M starting balance, and neither consistently turns a profit. CEO-Bench takes a first step toward measuring the intelligence required to drive sustained, adaptive progress over time.

07.
bioRxiv (Bioinfo) 2026-06-18

A unified smoothing framework for protein domain bigram model

Biomolecular sequences can be represented as strings over an alphabet, an analogy that has motivated many applications of computational linguistic techniques to biological problems. However, such methods must be adapted to the characteristic scale and organization of biomolecular data. Here, we consider the problem of bigram smoothing for multidomain protein architectures, where domain bigram frequency data is extremely sparse and differs from textual data in alphabet size, string length distribution, the relationship between bigram and unigram frequencies, tandem repeat lengths, and the distribution of domain adjacencies. Moreover, some domain combinations are unobserved because they are biologically incompatible, others because the data are incomplete. A smoothing method that distinguishes these two cases is required. We propose a unified smoothing framework based on interpolation that can be tuned to accommodate different bigram data characteristics. Within this framework, we design specific model variants suited to protein domain bigram data: these assign low adjusted counts to pairs that are likely incompatible, while making appropriate adjustments for undersampled pairs. We demonstrate empirically that this approach distinguishes the two cases while preserving the characteristic signatures of multidomain data.

08.
arXiv (CS.CL) 2026-06-19

JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines

Current AI-driven game development has made substantial progress in asset generation, gameplay design, and web-based game coding, yet project-level code engineering on professional game engines remains largely unexplored due to the absence of large-scale datasets and deterministic evaluation methods. We present JamSet and JamBench, the first project-level game code framework dataset and benchmark built on a professional game engine. Our key insight is that Game Jam competitions, community events where developers build complete games under tight time constraints, yield thousands of open-source projects suitable for this purpose. Building on the Godot engine's text-based format and headless execution mode, we design a deterministic verification pipeline from file integrity to runtime behavior collection, distilling 8,133 verified projects from over 240,000 repositories. Of these, 300 manually verified projects form JamBench; the rest constitute JamSet. JamBench defines theme-driven generation and code completion tasks, evaluated through a pipeline combining compilation pass rates, Structural Completeness Score (SCS), and Behavioral Alignment Score (BAS). Evaluation of 9 frontier models reveals a capability cliff as project scale increases, with runtime pass rates dropping from 80.4% on small projects to 5.7% on large ones (Task2a). Code Agents improve compilation rates yet yield no gains in runtime behavioral quality, indicating that the bottleneck lies in architectural design rather than syntactic correctness. Experiments validate JamSet as effective training data. All data and code are publicly available.

09.
medRxiv (Medicine) 2026-06-22

COVID-19 containment policies and hyperglycemia in pregnancy: correlation with the Stringency Index in a nationwide Belgian cohort

Background During the COVID-19 pandemic, gestational diabetes (GD) prevalence showed variable changes across regions, with most reporting increases and others decreases; however, its association with perinatal outcomes in Belgium remains unknown. We aimed to compare the prevalence of hyperglycemia in pregnancy (HIP) in 2020 versus 2019 and examined the correlation between HIP prevalence and pandemic-related restrictions measured by the Stringency Index (SI) and evaluate neonatal weight percentiles changes. Methods: We included all singleton live births in Belgium in 2019 and 2020 from Belgian birth registry data. We compared monthly proportions of HIP prevalence and Small for gestational age (SGA) and Large for gestional age (LGA) newborns in 2019 and 2020. Crude and adjusted odds ratios (ORs, aORs) were estimated with logistic and multinomial regression. The Spearman correlation coefficient was used to assess the correlation between the monthly average SI and the monthly aORs of HIP. Results: For deliveries from January to June 2020, no significant differences in HIP prevalence were observed compared with 2019. From July to December 2020, there was a significant increase in HIP, with peaks in July (GD screening in April) (aOR 1.41, 1.26-1.58) and November (GD screening in August) (aOR 1.33, 95% CI 1.18-1.49). There was no significant change in neonatal weight percentiles. The Spearman correlation coefficient between the SI and HIP aORs was 0.86 (p = 0.02). Conclusion During the pandemic, we observed an increase in the prevalence of HIP, compared to 2019, without a measurable impact on LGA or SGA newborns. The aOR of HIP in a given month was strongly correlated with the corresponding SI.

10.
arXiv (CS.CL) 2026-06-11

Cross-modal Consistency Guidance for Robust Emotion Control in Auto-Regressive TTS Models

While Text-to-Speech (TTS) systems enable emotional control via natural-language instructions, expressiveness, naturalness, and speech quality degrade when the target emotion conflicts with the textual semantics. We propose a Cross-modal Consistency Guided Classifier-Free Guidance (CCG-CFG) method with dynamic scales based on the degree of inconsistency between the text emotion and the explicit speech emotion, replacing the dropout condition with the text emotion. We also distill the CCG-CFG guidance signal using a hard-sample mining strategy, improving the TTS model's emotional alignment capability. Evaluations on five emotional corpora and two TTS benchmarks show that our approaches applied to CosyVoice2 achieve up to a 12% absolute improvement in emotion-recognition accuracy and a 10% relative improvement in subjective scores, outperforming baselines including HierSpeech++, Qwen3-TTS, and original CosyVoice2, while preserving intelligibility, naturalness, and high speech quality.

11.
arXiv (CS.CV) 2026-06-19

LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation

Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentation. The immense computational requirements of backbones often necessitate distillation into smaller architectures for edge deployment. Feature-based knowledge distillation (KD) often suffers from the teacher-student gap; the student struggles to imitate teacher's complex feature map due to its limited capacity. To mitigate this bottleneck, we propose LEAP: Layer-skipping Efficiency via Adaptive Progression, a training curriculum for ViT feature-based knowledge distillation. By utilizing the teacher's intermediate feature maps as a sequence of progressively more difficult targets, our curriculum allows the student to build a foundational representation before tackling higher-level abstractions. Our results demonstrate that this paradigm significantly accelerates convergence through adaptive difficulty selection across various student model sizes and dataset scales. With our curriculum, the LEAP-distilled ViT-S achieves 90.1% accuracy on ImageNet-100, a +12.24% improvement compared with baseline. On ImageNet-1K, LEAP achieves +3.84% and +7.75% improvement for the instance retrieval task on the Oxford and Paris datasets, respectively. Furthermore, the curriculum enables 25.1% savings in training FLOPs and 21% savings in training time on ImageNet-100 by implementing early-stopping for teacher inference during the initial stages of training. Code is available at https://github.com/KevinZ0217/LEAP

12.
arXiv (CS.LG) 2026-06-16

A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to Adapt

arXiv:2606.15569v1 Announce Type: new Abstract: Test-time training (TTT) adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts. Yet, its performance often suffers from instability and sensitivity to hyperparameters such as update steps and subspace. We explain this behavior through a decision-theoretic lens, treating TTT as implicit Bayesian inference in the kernel regime. Under a Gaussian process benchmark, we show that TTT reduces prediction error when updates are spectrally matched to the prompt's signal-to-noise ratio and aligned with query-relevant eigen-directions. This perspective underpins the following results: (1) we show when fixed update steps and subspaces fail under distribution shifts, motivating adaptive strategies; (2) we prove that selecting update steps via prompt evidence admits a PAC-Bayes guarantee against overfitting; and (3) we characterize the Bayes-optimal update subspace under a linear-Gaussian correction model, yielding a scoring rule for selecting Transformer blocks and heads. Our theory helps explain the empirical instability of TTT, taking a step toward principled guidance for when, how far, and which directions to adapt.

13.
arXiv (CS.CL) 2026-06-17

Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond

Large language models (LLMs) are widely used to fulfill users' information needs; users ask LLMs about the weather, pose educational questions, and consult them for legal assistance. One particularly understudied area is digital security and privacy (S&P), where users may seek LLMs' help on how to secure their online accounts or protect their computers from cyber attacks. To the best of our knowledge, no prior study has collected or analyzed the S&P questions users ask LLMs; prior research on LLM response quality relied on expert-authored S&P misconceptions or FAQs rather than user queries. Drawing from WildChat, a dataset of 3.2M user-LLM conversations collected in the wild, our study identifies 14,727 S&P prompts and categorizes them into nine categories covering a wide range of S&P topics. From the S&P prompts, we sampled 450 and performed a thematic analysis to characterize the S&P questions users ask LLMs. Separate from the thematic analysis, we curated 270 advice-seeking S&P prompts, where users ask for recommendations, guidance, or specific S&P information. We measured LLM response quality and consistency when posing the prompt to LLMs 10 times. We found that commercial LLMs outperform open-weight models (GPT 5.5 provided "good enough" responses on 98% of prompts; Llama 4 on 47%). However, among prompts that received high-quality responses on average, commercial models sometimes produce contradictory responses across runs, risking confusing or misleading users.

14.
arXiv (CS.CV) 2026-06-17

Flux-Guard: Facial Identity Protection using diffusion models

The widespread deployment of face recognition (FR) systems exposes personal images shared on social media and public platforms to identity linkage and privacy risks. Existing adversarial privacy protection methods can degrade unauthorized FR performance but are not compatible with generative face editing. Artificial intelligence-driven face editing tools are gaining popularity, which has significantly increased user demand for personalized portrait generation and social sharing. However, current editing methods often preserve identity features, making the edited images still susceptible to tracking by malicious FR systems. Thus, this paper proposes Flux-Guard, a privacy-preserving face editing framework based on adversarial attacks, which integrates face editing and privacy protection within a unified generative process. Specifically, we design a flow trajectory control method to align semantic manipulations with the generative process and introduce latent-space adversarial optimization with an adaptive perceptual-loss-driven weighting strategy, dynamically adjusting adversarial strength to maximize attack effectiveness while preserving visual quality. Extensive experiments demonstrate that Flux-Guard supports face editing while significantly improving attack success rates against cross-domain face recognition models on the CelebA-HQ and LADN datasets. Furthermore, evaluation results for commercial APIs have confirmed its effectiveness in real-world applications. The code is released at https://github.com/JLMWang/Flux-Guard.

15.
arXiv (CS.CL) 2026-06-12

When Similar Means Different: Evaluating LLMs on Arabic–Hebrew Cognates

Arabic and Hebrew, as closely related Semitic languages, share a substantial lexicon of true cognates, misleading false friends, and modern loanwords. This overlap poses a challenge for cross-lingual semantic understanding in large language models (LLMs). To evaluate this capability, we introduce SemCog Bench, a curated benchmark of 1,858 Arabic–Hebrew word pairs with sentence-level annotations for cognate identification and semantic disambiguation. We evaluate open-source and commercial LLMs across multiple input representations (raw, diacritized, Romanized, and phonetic) and reveal a critical gap in cross-lingual reasoning. While models achieve high accuracy on true cognates, performance drops sharply on false friends and loanwords, reflecting a strong reliance on surface-form similarity. Furthermore, sentence-level context yields only modest improvements, suggesting that contextual cues alone are insufficient to overcome misleading form-based signals. These findings reveal a fundamental limitation of current LLMs in resolving cross-lingual form–meaning conflicts and establish SemCog Bench as a rigorous benchmark for multilingual semantic reasoning. Our code and data are publicly available.

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

Deep Temporal Modeling and Ensemble Fusion for Multimodal Emotion Recognition from Physiological Signals

Physiological stress and emotion recognition are important for health monitoring and affective computing. In this work, we present a comprehensive evaluation of deep learning models such as Long Short-Term Memory (LSTM), Temporal Convolutional Networks (TCN), and Transformer on the WESAD dataset for multimodal affect recognition using wrist and chest sensor signals. We perform ablation studies to assess the individual contributions of each modality by training models on wrist-only and chest-only inputs. In addition, we implement a late-fusion ensemble strategy that combines predictions from all three architectures trained on multimodal input. We also employ early fusion at the sensor level by concatenating wrist and chest signals before feeding them into each model. Our results show that Transformer models consistently achieve the highest accuracy in multimodal settings, while TCN models perform best in the wrist-only configuration. The ensemble method yields the highest overall accuracy (98.91 +/- 0.13%) and macro-F1 score (98.56 +/- 0.17%). These findings demonstrate the effectiveness of sensor fusion and ensemble-based fusion in developing robust systems for physiological emotion recognition.

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

Finsler Geometry, Graph Neural Networks, and You

arXiv:2606.17185v1 Announce Type: new Abstract: Graph neural network architectures based on the graph Laplacian approximate the Laplace-Beltrami operator, thus limiting their application to isotropic operators. As a nonlinear alternative to the Laplace-Beltrami operator, we consider estimates of the Finsler Laplacian on point clouds sampled from a manifold. We prove that these discrete estimates converge to the true operator on the manifold as the number of point samples grows. Moreover, we show that this operator can be expressed as a graph neural network layer, which we use to define a family of Finslerian graph neural networks constrained to express Finsler geometry. We show that Finslerian graph neural networks recover the geometry underlying nonlinear diffusion equations in practice.

18.
arXiv (CS.AI) 2026-06-11

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

arXiv:2605.23243v2 Announce Type: replace-cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM-R, across C/Java/Python) and black-box web application security testing (five production-style applications with 118 ground-truth vulnerabilities across 20+ CWE families, which we will open-source). We test six frontier models (GPT-5.4, Codex~5.3, Claude Opus~4.6, Sonnet~4.6, Gemini~3.1~Pro and Gemini~3~Flash) and two domain-specialized models across four testing paradigms. Our findings are sobering: (1)~every frontier model produces 10-50% false positive rates in white-box detection, systematically over-predicting vulnerabilities; (2)~in black-box testing, frontier models achieve only 4-8% ground-truth coverage, improving to just 10-19% even with external security tools (Playwright MCP, Burp Suite MCP); (3)~structured penetration-testing methodology encoded in domain-specialized agents raises per-family detection above 50%, demonstrating that methodology, not scale, is the primary lever; and (4)~a domain-specialized defense model achieves the highest precision (0.904) and lowest false positive rate (9.7%) among all models, on a single GPU. We identify the absence of structured security testing traces end-to-end request/response sequences, failure-heavy data, and multi-step attack chains as the fundamental training data bottleneck, and propose self-play security testing as a data generation strategy. Our results make the case for vertical foundation models purpose-built for cybersecurity.

19.
arXiv (quant-ph) 2026-06-17

Robust Spin Splitting and Strain-Controlled Optical Response in Monolayer CrC2N4 for Valleytronic and Optoelectronic Applications

arXiv:2606.17329v1 Announce Type: cross Abstract: Monolayer CrC2N4 recently emerged as a promising two-dimensional semiconductor, yet its spin-orbit-coupled (SOC) physics and strain-tunable optical response remained largely unexplored. Here, we investigated the electronic, valley, charge-transfer, and optical properties of pristine and biaxially strained monolayer CrC2N4 using first-principles calculations. The monolayer exhibited a direct band gap at the K/K' valleys. SOC produced valley contrasting out-of-plane spin polarization, yielding a moderate valence band spin splitting of 51.9 meV and a small conduction band spin splitting of 1.7 meV. Orbital-resolved analysis showed that the edge states were mainly governed by Cr-d and N-p hybridization, while Bader analysis indicated polar-covalent bonding through charge transfer toward N atoms. Biaxial strain in the range of -4% to +4% tuned the band gap from 1.987 to 1.421 eV and drove an indirect-to-direct gap transition near -1% strain. Tensile strain enhanced the Berry curvature and red-shifted the optical response toward the visible-near-infrared region. These results suggested monolayer CrC2N4 as a promising platform for strain-engineered valleytronic and optoelectronic device applications.

20.
arXiv (CS.CV) 2026-06-15

Temporal Backtracking Search for Test-time Generative Video Reasoning

While test-time scaling has revolutionized reasoning in large language models, generative video reasoning remains bottlenecked by a single-shot paradigm. We demonstrate that searching over denoising steps cannot rescue logically flawed rollouts because spatial trajectories commit early in the diffusion process. Root-level Best-of-N (BoN) sampling is similarly inefficient: reasoning errors cluster early in the temporal axis, and resampling blindly discards verified upstream progress. To unlock effective test-time scaling for video models, we introduce Temporal Backtracking Search (TBS), which shifts the search space to the temporal axis. TBS transforms video generation into an iterative generate-verify-restart loop via three core mechanisms: (1) variable-K conditioning to resume generation from arbitrary clean prefixes; (2) temporal process verification to localize failures and extract valid restart anchors; and (3) prefix-based search to reallocate compute toward extending correct trajectories rather than root resampling. Across algorithmic, navigation, and robotics domains, TBS Pareto-dominates matched-budget BoN. In a strict out-of-distribution setting where one-shot generation collapses (0.7% for BoN), TBS achieves 22.7%, with every solved episode stemming from a restarted branch. Ultimately, TBS reveals that the local reasoning competence of video models far exceeds what single-shot rollouts indicate, providing a scalable test-time framework to unlock it.

21.
arXiv (CS.CL) 2026-06-11

BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language

作者:

We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources. The corpus contains 10,060 validated utterances in native Nastaliq script, derived from Mozilla Common Voice recordings. Fine-tuning OpenAI Whisper-small yields a Word Error Rate (WER) of 26.74% and a Character Error Rate (CER) of 8.67% on a 538-utterance speaker-disjoint validation set, down from a zero-shot baseline of 159.19% WER and 152.52% CER. A Whisper-base fine-tuned on the same data achieves 44.54% WER and 15.61% CER, confirming that model capacity matters for this low-resource setting. The dataset, fine-tuned model, and a live transcription demo are publicly available on HuggingFace.

22.
arXiv (CS.CL) 2026-06-12

SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents

Language model agents are increasingly effective in solving realistic tasks through multi-turn tool use. However, training reliable tool-using agents remains challenging in practice. While reinforcement learning provides an on-policy paradigm for improving agents from their own environment interactions, its effectiveness depends heavily on the training task distribution. When tasks are fixed before training, the task distribution can become increasingly mismatched with the policy's evolving capabilities, causing many rollouts to be spent on uninformative tasks. We propose SENTINEL, a failure-driven reinforcement learning framework that turns the Solver's rollout failures into targeted training tasks. SENTINEL follows a Controller–Proposer–Solver loop: the Controller analyzes failed trajectories and summarizes recurring error patterns, the Proposer generates executable tasks that stress these weaknesses, and the Solver is trained on the targeted tasks. On Tau2-Bench Retail with Qwen3-4B-Thinking-2507, SENTINEL improves Pass\^{}1 from 66.4 to 74.9 and outperforms RL on general synthetic tasks across Pass\^{}k metrics. These results demonstrate that model failures provide an effective and scalable source of targeted training signal for improving tool-using language model agents.

23.
medRxiv (Medicine) 2026-06-12

The Clinical Characteristics and mortality outcomes of Atrial fibrillation complicating Heart failure with reduced ejection fraction: A prospective study from South Africa

Background: A growing burden of cardiovascular risk factors has raised cardiovascular disease-related mortality in Sub-Saharan Africa (SSA), driving higher prevalence of heart failure with reduced ejection fraction (HFrEF) and its complication with atrial fibrillation (AF). No prospective study has examined AF's clinical impact on HFrEF in SSA. Aim: To determine AF prevalence in HFrEF, describe HFrEF-AF clinical characteristics, and determine AF's impact on mortality. Methods: In this prospective observational study at a tertiary hospital in Johannesburg, 136 HFrEF patients were enrolled and categorised as HFrEF- SR (sinus rhythm) or HFrEF-AF. Baseline clinical characteristics and biochemistry were recorded. Comprehensive echocardiography including left atrial strain by 2D speckle-tracking was performed. Median follow-up was 30.6 months. Results: AF was present in 28 patients (21%). The mean age was 58.7 {+/-} 14.9 years (52.9% male) and differed between groups (p < 0.001). Hypertensive heart disease was the leading cause of HFrEF (36%). Compared with SR, HFrEF-AF patients had poorer health status (KCCQ 27 [16-43] vs 45 [32-60], p < 0.001) and lower left atrial strain (26.2 {+/-} 11.3%, p < 0.001). Guideline-directed medical therapy was suboptimal in the AF group: anticoagulation use was higher than SR (60% vs 9.5%, p < 0.001) but overall inadequate; HFrEF-AF patients received lower median doses of carvedilol (15.6 mg vs 25 mg, p = 0.002) and enalapril (10 mg vs 20 mg, p = 0.004), and fewer received spironolactone (50% vs 75.3%, p = 0.013). Survival was significantly lower in HFrEF-AF (0.41 [0.22-0.61]) versus SR (0.73 [0.61-0.82], p < 0.001). Independent predictors of mortality included prior stroke, lower TAPSE and KCCQ, and higher E/e' and heart rate. Conclusion: AF is common among HFrEF patients in this SSA cohort (though lower than in high-income countries) and associates with worse clinical status, suboptimal therapy, and higher mortality.

24.
arXiv (CS.CL) 2026-06-17

MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task

This work describes the participation of the MLLP-VRAIN research group in the shared task of the IWSLT 2026 Simultaneous Speech Translation track. Our submission utilizes the recently released Parakeet and Qwen 3.5 models to create a robust, cascaded solution for long-form SimulST through the use of adaptive "black-box" policies. We explore relaxations of these policies to achieve better quality-latency trade-offs. Compared to last year, we participate on all language directions. In addition to this, for the En$\rightarrow${De, It, Zh} directions we also participate in this year's new context track employing a combination of ASR word-boosting and a RAG mechanism of offline pre-translated exemplars to guide generation and enrich our system with domain-specific context. Finally, we provide a detailed latency analysis of our system. Compared to last year, results on the MCIF En$\rightarrow$De test set shows a substantial quality improvement of +5.82 XCOMET-XL. Our context track processing further improves performance by +1.03.

25.
arXiv (CS.CV) 2026-06-12

Emerging Flexible Designs for Geospatial Multimodal Foundation Models

Foundation models are rapidly transforming Earth observation by enabling scalable pretraining across diverse unlabeled geospatial modalities. However, their architectural diversity ranging from encoder-only to encoder-decoder and masked autoencoding paradigms makes it challenging to assess performance trade offs in a consistent manner. In this work, we present an apples-to-apples comparison of leading FM architectures designed for geospatial multimodal reasoning, with a particular focus on flexibility across varied spectral band configurations. We standardize pretraining using identical self supervised learning objectives and training datasets, and evaluate all models under consistent parameterization on the GEOBench benchmark across classification and segmentation tasks. Our results offer new insights into the design trade-offs between model flexibility, modality alignment, and downstream task performance. By highlighting architectural strengths and limitations under controlled conditions, this study provides practical guidance for building next generation geospatial foundation models capable of robust multimodal reasoning.