探索全球前沿学术脉络

01.

Nature (Science) 2026-06-10 DOI: HASH:c78d76b63bcc11f6b3d26bcf8e5e624a

Whole-genome duplication shaped cell-type evolution in the vertebrate brain

作者:

Yuanzhen Zhu↗

The complex brains of vertebrates have more cell types than those of their closest relatives. Whole-genome duplications (WGDs) occurred during early vertebrate evolution1, but it is unclear whether the duplicated genes (ohnologues) facilitated cell-type evolution. Here using brain single-cell transcriptomes from five chordates—human2, mouse3, lizard4, lamprey5 and amphioxus—we report that many cell-type families with conserved core transcription factors in vertebrates do not show one-to-one homology with amphioxus. Moreover, ohnologues, particularly those from the first WGD, were more important than small-scale duplication paralogues for vertebrate cell-type evolution. To explore whether ohnologues are mechanistically important for this process, we predicted ancestral cell-type states and compared them to amphioxus and experimentally investigated macroglia. The findings indicate that ohnologues had a role in early vertebrate cell-type diversification. Moreover, by examining paralogue expression across cell types and species, we show that expression changes were mainly driven by dosage selection and subfunctionalization. We also link ohnologues to cellular diversity at different anatomical and cell-type scales. Our findings demonstrate the importance of WGDs for the evolution of early vertebrate brain complexity and highlight that the resultant ohnologues continued to capacitate cell-type evolution long after they were formed. Analyses of brain single-cell transcriptomes from human, mouse, lizard, lamprey and amphioxus reveal that duplicated genes (ohnologues) played a pivotal part in early vertebrate cell-type diversification.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2605.28591

Models That Know How Evaluations Are Designed Score Safer

作者:

Katharina Deckenbach↗Haritz Puerto↗Jonas Geiping↗Sahar Abdelnabi↗

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or moral dilemmas. Evaluating this fine-tuned model on six safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2604.18109

FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings

作者:

Santosh Kesiraju↗Bolaji Yusuf↗\v{S}imon Sedl\'a\v{c}ek↗Old\v{r}ich Plchot↗Petr Schwarz↗

This paper presents factorized linear projection (FLiP) models for understanding pretrained sentence embedding spaces. We train FLiP models to recover the lexical content from multilingual (LaBSE), multimodal (SONAR) and API-based (Gemini) sentence embedding spaces in several high- and mid-resource languages. We show that FLiP can recall more than 75% of lexical content from the embeddings, significantly outperforming existing non-factorized baselines. Using this as a diagnostic tool, we uncover the modality and language biases across the selected sentence encoders and provide practitioners with intrinsic insights about the encoders without relying on conventional downstream evaluation tasks. Our implementation is public https://github.com/BUTSpeechFIT/FLiP.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12373

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

作者:

Hao Xiang↗Qiaoyu Tang↗Le Yu↗Yaojie Lu↗Xianpei Han↗Ben He↗Le Sun↗Bowen Yu↗Peng Wang↗Hongyu Lin↗Dayiheng Liu↗

Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior research demonstrates that scaling environment quantity improves RL performance, existing manual or individual construction methods suffer from linear scaling limits, thereby hindering scalable reasoning generalization. This paper introduces RACES (Recursive Automated Composition for Environment Scaling), a framework that conceptualizes verifiable environments as composable building blocks that can be recursively assembled. The key insight is that when the codomain (output type) of one environment matches the domain (input type) of another, they can be automatically fused into a new verifiable environment, enabling recursive composition. RACES is implemented with 300 individual environments and defines a set of composition operators (\textsc{SEQUENTIAL}, \textsc{PARALLEL}, \textsc{SORT}, and \textsc{SELECT}) that induce diverse reasoning patterns. Extensive experiments show that RL training on these composite environments consistently enhances reasoning generalization. Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1 on six benchmarks, which are unseen during the construction of training environments. Moreover, RACES achieves performance comparable to training on 300 individual environments using only 50 base environments, demonstrating significant efficiency in environment utilization.

阅读与讨论 → 访问原文 →

05.

arXiv (quant-ph) 2026-06-24 DOI: arXiv:2606.23727

Certifying Quantum Optimization and Circuit Cutting by Using Quantum-Classical Moment Duality

作者:

Ammar Daskin↗

arXiv:2606.23727v1 Announce Type: new Abstract: We establish a direct quantum-classical duality based on the degree-$2$ Sum-of-Squares (SoS) semidefinite programming cone: the matrix of two-qubit Pauli-$Z$ correlation functions obtained from any quantum state $\rho$ is automatically a feasible point of the classical Goemans-Williamson (GW) relaxation. This observation provides a universal ``safety net'' for quantum optimization algorithms: applying GW random hyperplane rounding to the quantum-driven moment matrix yields a certified expected cut value $\mathbb{E}[\mathrm{Cut}] \ge \alpha_{\mathrm{GW}}\langle\mathcal{H}\rangle_\rho$, valid for every state produced by variational algorithms such as QAOA or the Variational Quantum Power Method (VQPM), regardless of convergence quality. We further show that the same moment matrix reveals the tensor-product structure of the underlying unitary circuit, enabling a polynomial-time, correlation-based circuit cutting procedure with rigorous error bounds. The framework is validated numerically on Max-Cut instances for variational quantum algorithms and on random states for circuit cutting, demonstrating that the cheap two-point correlation data are sufficient to locate near-optimal bipartitions and that the theoretical error bounds hold in practice.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12186

A Resource for Enthymeme Detection in Controversial Political Discourse

作者:

Martial Pastor↗Nelleke Oostdijk↗

Enthymemes, arguments with unstated premises or conclusions, are pervasive in persuasive discourse, yet their annotation remains notoriously subjective. We present a resource of 1,482 tweets from politically controversial discourse, annotated by five annotators for the presence of enthymemes and their argument structure, designed to study label variation. We first revisit the definition of enthymemes and propose annotation guidelines anchored in Walton's argumentation schemes, offering a structured and constrained approach that nonetheless preserves room for the interpretive nature of the task. This contrasts with past resources, which tend to eliminate disagreement, obscuring its sources and preventing investigation of its potential benefits for model performance. We further propose a complexity analysis of the task, identifying where annotation imposes high cognitive load and may give rise to inconsistent annotation. Our preliminary experiments show that models trained on annotator disagreement outperform models trained on hard majority-vote labels. We close by reflecting on how structural openness in enthymeme definitions and guidelines enables the study of variation in subjective inferential processes for future resources and downstream NLP applications concerned with human inference.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2508.21380

The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network

作者:

Elias Sandmann↗Sebastian Lapuschkin↗Wojciech Samek↗

arXiv:2508.21380v3 Announce Type: replace-cross Abstract: Recent mechanistic work has uncovered learned algorithms within neural networks, from modular arithmetic to search and planning in game-playing agents. But does algorithmic structure guarantee algorithmic behavior? We investigate this in Leela Chess Zero, the strongest neural chess engine, where prior work identified learned look-ahead. By extending the logit lens to its move-selecting policy network, we discover that correct puzzle solutions-including immediate checkmates-often appear in intermediate layers but are systematically overridden in the final output, a phenomenon we term "forgotten puzzles". Replicating prior analyses on these positions, we find that look-ahead operates normally-future moves of the correct continuation are represented, causally important, and linearly decodable-ruling out a failure of the algorithm itself. Instead, late layers increasingly shift toward prioritizing safe play over aggression. To test whether this shift drives the override, we steer the model against these preferences and recover 61.7% of forgotten puzzles, providing causal evidence that safety priors override algorithmically computed solutions. These findings demonstrate that algorithmic structure does not guarantee algorithmic behavior: a model can internally solve a problem and still output the wrong answer.

阅读与讨论 → 访问原文 →

08.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2606.18035

Approximately Decoding the Colour Code

作者:

Mark Walters↗

arXiv:2606.18035v1 Announce Type: new Abstract: Recently we showed that minimum weight decoding in the (6.6.6 planar) colour code is NP-hard. However, it remained an open question as to whether it was possible to approximate the minimum weight decoding arbitrarily closely in polynomial time. In this paper we prove that it is possible: for any $\varepsilon>0$ there is an polynomial time algorithm that, given a syndrome, can find an error-set generating that syndrome whose weight is at most $1+\varepsilon$ times the weight of the minimum weight decoding. As a consequence we see that, for any $\varepsilon>0$, there is a polynomial time algorithm that can correct all errors of weight up to $(1-\varepsilon)d/2$ in the distance $d$ colour code (so almost up to the theoretical $d/2$ limit). The polynomial we give is impractically large, but it does open the door for sensible polynomial time algorithms that approximate minimum weight decoding and, in particular, shows that approximate decoding is not NP-hard.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15701

Robust Transformer-Based One-Step Stock Index Forecasting via Shifted Data Augmentation

作者:

Tien Thanh Thach↗

arXiv:2606.15701v1 Announce Type: new Abstract: Transformers have shown remarkable success in sequence modeling, yet their direct application to financial time series remains challenging due to noisy signals, short-memory dynamics, and distributional shifts. This paper proposes a modified Transformer architecture for one-step stock index forecasting, combined with advanced learning-rate scheduling and a novel Shifted Data Augmentation (SDA) technique. We evaluate the proposed framework on two benchmark stock index datasets, VN30 and S&P 500. Experimental results demonstrate that cosine annealing with warmup consistently improves forecasting accuracy over the generalized inverse-power scheduler. Furthermore, SDA substantially reduces forecasting errors and run-to-run variability while improving robustness to hyperparameter selection. The combination of cosine annealing scheduling and SDA achieved the best performance on both datasets, indicating that data augmentation can play a more important role than increasing model complexity in Transformer-based financial forecasting. These findings provide a practical and computationally efficient approach for robust stock index forecasting in noisy financial environments.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17819

A Framework for Evaluating Agentic Skills at Scale

作者:

Maksim Shaposhnikov↗Nicolas Fortuin↗Simon Stipcich↗Maria I. Gorinova↗Amy Heineike↗Rob Willoughby↗

Agent skills – structured, reusable knowledge artifacts that augment LLM agent capabilities – have been rapidly adopted in industry, yet their cross-domain impact and use across commercial and open-source models remain under-studied, and no reusable methodology exists for evaluating an individual skill. In this work, we present an evaluation framework that lets a skill author construct realistic tasks to rigorously assess the aspects of a skill that matter most to them, and that estimates skill utility by solving those tasks. Further, we apply our evaluation approach at scale to 500 real-world skills, generating 1,000 tasks derived from the skills' content, along with instruction-following and goal-completion scoring rubrics. Using these metrics, we evaluate how 19 agent-model configurations, both proprietary and open-source, perform on the tasks. Our results show that models vary widely in how closely they adhere to the instructions encoded in skills, leading to substantial differences in their performance gains. Furthermore, we show that access to a skill significantly changes model behavior compared to the no-skill setup, providing an essential mechanism for encoding opinionated workflows into LLM agents. We release our evaluation dataset to support future work on agent skills.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.19204

ROSA-TFormer: A Radar-Optical Sensor-Aware Temporal Transformer for Pinus sylvestris Plantation Classification in Northern Shaanxi Using GEE-Derived Sentinel-1/2 Time Series

作者:

Nengbo Zhang↗Chang sheng↗

Accurate identification of Pinus sylvestris var. mongolica plantations is important for monitoring afforestation quality and ecological restoration in northern Shaanxi. This paper proposes ROSA-TFormer, a radar-optical sensor-aware temporal Transformer for P. sylvestris classification using Sentinel-1/2 time-series data generated on Google Earth Engine. The model integrates separate SAR and optical embedding branches, a sensor-aware gate, and temporal attention pooling to capture multi-source seasonal features. Experiments on monthly and half-month point-level datasets show that ROSA-TFormer achieves strong classification performance, with 99.67% overall accuracy, 99.56% macro F1, and 98.91% P. sylvestris F1 on the HalfMonth-dataBig dataset. Spatial block validation and ablation results further indicate the effectiveness of radar-optical temporal fusion and sensor-aware modeling. The results demonstrate the potential of ROSA-TFormer for point-level P. sylvestris plantation classification, while broader wall-to-wall validation remains necessary.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2508.04424

Composed Object Retrieval: Object-level Retrieval via Composed Expressions

作者:

Tong Wang↗Guanyu Yang↗Nian Liu↗Zongyan Han↗Jinxing Zhou↗Salman Khan↗Fahad Shahbaz Khan↗

Retrieving fine-grained visual content based on user intent remains a challenge in multimodal systems. Although current Composed Image Retrieval (CIR) methods combine reference images with retrieval texts, they are constrained to image-level matching and cannot localize specific objects. To this end, we propose Composed Object Retrieval (COR), a new object-level retrieval task that retrieves target object(s) from candidate objects in a target image and grounds the retrieved result with pixel-level masks. Given a reference object, its mask, a target image, and a retrieval text describing the desired modification, COR requires models to perform composed visual-textual reasoning rather than relying on explicit category names. This setting introduces several challenges, including fine-grained compositional matching, negative-object filtering under visually similar distractors, and flexible single- or multi-object retrieval. We construct COR125K, the first large-scale COR benchmark, containing 125,541 retrieval triplets across 408 categories with base/novel splits for evaluating category-level generalization. We also present CORE, a unified end-to-end model that integrates reference region encoding, adaptive vision-text interaction, and region-level contrastive learning to align composed representations with target objects while suppressing background and distractors. Extensive experiments demonstrate that CORE significantly outperforms existing CIR-based pipelines and strong baselines in both base and novel categories, establishing a simple and effective foundation for fine-grained object-level multimodal retrieval. Code will be released publicly at https://github.com/wangtong627/COR.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2507.11366

Characterizing Nash Equilibria in Zero-Sum Games: A Physics-Inspired, Parallelizable Approach with a Linear Number of Gradient Queries

作者:

Taemin Kim↗James P. Bailey↗

arXiv:2507.11366v2 Announce Type: replace-cross Abstract: We study online optimization methods for zero-sum games, a fundamental problem in adversarial learning in machine learning, economics, and many other domains. Traditional methods approximate Nash equilibria (NE) using either regret-based methods (time-average convergence) or contraction-map-based methods (last-iterate convergence). We propose a new method based on Hamiltonian dynamics in physics and prove that it can characterize the set of NE in a finite (linear) number of iterations of alternating gradient descent in the unbounded setting, modulo degeneracy, a first in online optimization. Unlike standard methods for computing NE, our proposed approach can be parallelized and works with arbitrary learning rates, both firsts in algorithmic game theory. Experimentally, we support our results by showing our approach drastically outperforms standard methods.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19251

Acceleration of an algebraic multigrid pressure solver using graph neural networks

作者:

Eric Chill\'on↗Artur K. Lidtke↗Nguyen Anh Khoa Doan↗Bernat Font↗

arXiv:2606.19251v1 Announce Type: cross Abstract: Solving the pressure-Poisson equation remains the primary computational bottleneck in incompressible unstructured flow solvers primarily due to the inherent sensitivity of traditional linear solvers to mesh irregularities. This work introduces a data-driven algebraic multigrid (AMG) smoother that uses a modified graph convolutional isomorphism network (GCIN). The graph neural network predicts optimal polynomial coefficients to construct a sparse pseudo-inverse operator across diverse grid topologies. The coefficients are optimized to reduce the residual after each V-cycle iteration. By directly capturing the algebraic structure of the system from the sparse coefficient matrix, the proposed method maintains the solver's linearity while adapting to local anisotropies in unstructured grids. Our framework demonstrates significant performance gains by reducing the number of V-cycles required for a given tolerance and delivering wall-clock speedups from 4% to 37% across diverse benchmarks. Notably, the model exhibits robust generalization by maintaining efficiency on meshes up to 128 times larger than those seen in training, and by accelerating the solver's convergence on unseen industry-relevant problems such as the AirfRANS dataset.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-24 DOI: arXiv:2602.02899

Decentralized SGD with Controlled Disagreement Finds Flatter Minima

作者:

Zesen Wang↗Mikael Johansson↗

arXiv:2602.02899v2 Announce Type: replace Abstract: Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization. This work challenges this view by introducing decentralized SGD with Adaptive Consensus (DSGD-AC), which uses a time-dependent scaling mechanism to maintain consensus errors throughout the training. We show that adaptive consensus changes the stationary variance of disagreement modes by balancing two effects: it preserves consensus-error magnitude through weaker graph damping while still allowing curvature-dependent damping to shape the disagreement directions. This balance can produce a stronger Hessian-weighted loss-envelope penalty around the deployed model, even when normalized Hessian alignment is weaker than in standard DSGD. Empirical results on image classification show that DSGD-AC reaches flatter solutions and higher test accuracy than standard DSGD and even centralized SGD. Together, these results support consensus errors as a useful implicit regularizer and open a new perspective on the design of decentralized learning algorithms.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.10683

UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data

作者:

Dong Fang↗Youjun Wu↗Yuanxin Zhong↗Rui Zhang↗Yunlong Wang↗Xiaosong Jia↗Yu-Gang Jiang↗

Dexterous hands are essential for fine-grained manipulation, but their hardware designs vary substantially across embodiments. Differences in kinematics, joint definitions, and degrees of freedom make it difficult to define a shared state representation compared with parallel grippers. As a result, dexterous-hand data remains fragmented and difficult to use for joint training. In this work, we propose the Unified Dexterous Hand Model (UDHM), which maps human and robot hand states into a shared 22-DoF semantic interface. Based on UDHM, we introduce UniDexTok, a retargeting-free state tokenizer that learns embodiment-conditioned discrete tokens from standardized real joint states. UniDexTok provides a unified representation for heterogeneous dexterous hands without relying on retargeting or simulation data. Compared with the recent baseline UniHM, UniDexTok reduces MPJAE from 15.63 degrees to 0.16 degrees and MPJPE from 18.51 mm to 0.18 mm, corresponding to error reductions of 98.98% and 99.03%, respectively. These results improve reconstruction from centimeter-scale to sub-millimeter accuracy. Experiments further show that data from other embodiments improves target-embodiment reconstruction accuracy, demonstrating the benefit of cross-embodiment tokenization. UniDexTok also shows strong zero-shot and few-shot reconstruction ability when new dexterous hands are introduced.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18257

From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions

作者:

Xiaolong Wang↗Zhe Zhao↗Song Lai↗Chaoli Zhang↗Zijie Geng↗Yu Tong↗Ye Wei↗Qingsong Wen↗

arXiv:2606.18257v1 Announce Type: cross Abstract: While LLMs show promise in automating educational content creation, their ability to generate questions that stimulate higher-order thinking remains understudied. This work evaluates six widely-used LLMs through a Bloom's Taxonomy lens, focusing on their capacity to transcend rote memorization and achieve cognitive leaps. Using a hybrid human–AI evaluation protocol, we generate and analyze 20{,}700 questions across computer science, K–12 math, and social-science domains. Key contributions include: (1) a fine-grained prompting strategy that reduces question repetitiveness by 24.45\% for Qwen2.5-7B-Instruct, and increases the proportion of higher-order cognitive level outputs by 11.53\% for InternLM3-8B-Instruct; (2) quantitative metrics for cognitive shift intensity (CogShift) and category drift, revealing InternLM3's superior performance in multi-level transitions; (3) an interpretability analysis revealing metric-level correlations that enhance the transparency of Chain-of-Thought prompting. Our findings highlight the importance of cognitive-aware prompt design and provide benchmarks for deploying LLMs in personalized learning systems.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17619

RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation

作者:

Qiwei Yan↗Zhiqiang Yuan↗Chongyang Li↗Jiapei Zhang↗Ying Deng↗Jinchao Zhang↗Jie Zhou↗

Reference-driven image generation has made rapid progress on identity preservation, but reliable viewpoint control across different subjects remains poorly understood. The difficulty is not merely generating a new image of the target subject: the model must infer the implicit viewpoint of one subject and transfer it to another subject using only image-level evidence, without camera poses, depth, or ray-based conditions. In this setting, existing generators conditioned on multiple image references often rely on spurious semantic correlations, which lead to viewpoint drift, part-level structural mismatches, and missing or unsupported target-specific content. We formulate this challenge as cross-subject viewpoint alignment and propose RAVA, a retrieval-augmented framework that supplies explicit geometric evidence before generation. RAVA first learns a cross-instance viewpoint embedding that retrieves target-subject images aligned with the anchor viewpoint, then applies a LogDet-based subset selection strategy to retain a compact reference set that is both view-consistent and structurally complementary. The selected references are finally consumed by a fine-tuned multi-reference image generator. Experiments show that generic semantic embeddings are nearly random for this task, while the proposed retriever substantially improves viewpoint retrieval quality. On cross-subject generation, RAVA consistently outperforms zero-shot baselines and stronger retrieval alternatives under the same generation backbone. These results indicate that cross-subject viewpoint alignment benefits from retrieval-augmented geometric grounding rather than relying on end-to-end generation alone.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2605.27864

FundaPod: A Multi-Persona Agent Pod Platform with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research

作者:

Di Zhu↗Lei Nico Zheng↗Zihan Chen↗

arXiv:2605.27864v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered on prediction. Institutional fundamental research, by contrast, requires human analysts or AI agents to gather evidence, identify business drivers, compare competing viewpoints, and generate investment memos. Its broader goal is not merely to predict outcomes, but to produce investment plans that are transparent, reusable, and verifiable, while contributing to the cumulative development of investment knowledge. We present FundaPod, a multi-persona agent platform for AI-assisted fundamental investment research. We argue that fundamental research is a human-centric decision-support task that is qualitatively distinct from trading-signal generation, and is therefore better served by an independence-preserving architecture. In FundaPod, AI agents with different personas, such as value investors or macro strategists, conduct research independently under a shared provenance contract. Their disagreements are then surfaced post hoc for adjudication by the human portfolio manager (PM) through a knowledge-graph memory system. This paper contributes five design principles for human-AI hybrid systems supporting fundamental research, grounded in design-science practice and theories of cognitive isolation and human-machine coordination. It also describes four architectural mechanisms: a persona distillation pipeline that turns public investor materials into deployable agents; a declarative skill registry that lets the planner derive typed task graphs; a grounded evidence model that links memo claims to verifiable sources; and a knowledge-graph "second brain" that connects tickers, memos, analysts, and themes. We demonstrate the architecture through a complete case study and a persona-based memo comparison.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2601.16713

A Human-in-the-Loop Label Error Detection Framework Applied to Arabic-Script HTR Datasets

作者:

Sana Al-azzawi↗Elisa Barney↗Marcus Liwicki↗

Despite recent advances, Handwritten Text Recognition (HTR) for Arabic-script languages still lags behind Latin-script HTR. Part of the problem is dataset quality. To help closing this gap, we propose a two-stage framework (CER-HV) for detecting label errors. Stage 1 (CER) is a Character-Error-Rate-based noise detector built on a Convolutional Recurrent Neural Network (CRNN) architecture. Stage 2 (HV) is the Human-In-The-Loop (HITL) Verification of noisy samples detected by the first stage. Applying the CER-HV framework on multiple Arabic-script datasets can identify samples with label errors including transcription, segmentation, orientation, and non-text content errors that can markedly affect HTR performance. These errors were identified by the first stage of the framework with up to 90percent (top-50) precision. We also show that our CRNN achieves state-of-the-art performance across five of the six evaluated datasets, reaching 8.46 percent Character Error Rate (CER) on KHATT (Arabic), 8.22 percent on PHTI (Pashto), 10.59 percent on Ajami, and 10.11% on Muharaf (Arabic), all without any data cleaning. We establish a new baseline of 11.3 percent CER on the PHTD (Persian) dataset. Applying CER-HV improves evaluation CER by up to 1.8 percentage points after dataset cleaning and retraining. Although our experiments focus on documents written in an Arabic-script language, the framework is general and can be applied to other text recognition datasets

阅读与讨论 → 访问原文 →

21.

medRxiv (Medicine) 2026-06-17 DOI: HASH:41b14a18730ba3405e6cbfa259dfbd35

The interaction between chronic hepatitis B (CHB) and Metabolic dysfunction-associated steatotic liver disease (MASLD) in a diverse central London population

作者:

Martyn↗Mullender↗Ogunnaike↗Kemper↗Ghosh↗Peppa↗Tsochatzis↗Gilson↗Flanagan↗Copas↗MacDonald↗Arenas-Pinto↗…

Introduction: The overlap between chronic hepatitis B (CHB) and metabolic dysfunction-associated steatotic liver disease (MASLD) is an emerging global health challenge. We investigated the impact of MASLD and metabolic comorbidity in a diverse London viral hepatitis clinic. Methods: This retrospective cross-sectional study (May 2018-Feb 2024) included adults with CHB having controlled attenuation parameter (CAP) measurements. MASLD was defined as CAP >264 dB/m plus [≥]1 cardiometabolic factor (CMF). We used univariable and multivariable models to examine MASLD's relationship with liver stiffness and hepatitis B viral load (HBV VL). Results: Among 323 individuals (67% male, median age 36), most were from Black (35%) or non-white British/Irish (29%) backgrounds. Overall, 64% had [≥]1 CMF, and 20% had MASLD. The CHB/MASLD group was significantly older (median 43 vs 35 years, p

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2605.00665

Prediction of Alzheimer's Disease Risk Factors from Retinal Images via Deep Learning: Development and Validation of Biologically Relevant Morphological Associations in the UK Biobank

作者:

Seowung Leem↗Yunchao Yang↗Adam J. Woods↗Ruogu Fang↗

The systemic, metabolic, lifestyle factors have established associations with Alzheimer's Disease (AD) through epidemiologic and AD-specific biomarker studies. Whether colored fundus photography (CFP) contains retinal structural signatures corresponding to these AD-related risk domains remains unclear. To determine whether deep learning (DL) models can predict 12 AD-related risk factors from CFP and to characterize the retinal structures underlying these predictions, thereby assessing whether CFP reflects pathways to AD vulnerability. Using 62,876 CFPs from 44,501 unique participants from the UK Biobank, DL models were trained to predict 12 factors linked to AD incidence: 6 categorical (sex, smoking, sleeplessness, economic status, alcohol use, depression) and 6 continuous (age, age at completing education, BMI, systolic, diastolic blood pressure, HbA1c). Model performance, model saliency, and saliency-derived scores (CAM-Score) were evaluated and compared to retinal morphometry. The scores were also compared between incident-AD cases (average 8.55 years before onset) and matched controls. Performance of DL ranged from AUROC= 0.5654-0.9480 for categorical and R2=-0.0291-0.7620 for continuous factors, outperforming most of the morphometry-machine learning models. Saliency-based score consistently highlighted biologically meaningful regions, particularly the optic nerve head and retinal vasculature. It also aligned with present morphometric variations. Several saliency-based scores differed significantly between incident AD and matched controls, suggesting potential overlap between retinal correlates of risk factors and preclinical AD-associated changes. CFP encodes retinal signatures linked to AD risk factors. Although not diagnostic, DL-derived retinal representations may uncover biologically meaningful risk-related structural changes mirroring the potential AD vulnerability.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17454

Dissecting model behavior through agent trajectories

作者:

Gaurav Gupta↗Vatshank Chaturvedi↗Jun Huan↗Anoop Deoras↗

arXiv:2606.17454v1 Announce Type: new Abstract: AI agent performance is not just a modeling problem, it is fundamentally a systems problem. The advanced capabilities of models are realized through agent harnesses. Therefore, a gap between model assumptions and harness behavior can easily prevent the model's full capabilities from translating into agent performance. We formalize this as the `intent-execution' gap: the mismatch between what the model intends and what the harness executes, and vice versa. We argue that minimizing this intent-execution gap is as important as other aspects of harness design such as tools and execution loops. To illustrate the impact of this harness-model alignment, we develop a simple and customizable harness called `Simple Strands Agent' (SSA). SSA aims to find the bulk of common patterns which generalize across different model families (such as Claude, Gemini, GPT, Grok, Qwen), as well as a small number of model-specific preferences. We make two contributions: (i) we $reproduce or improve on the pass@1$ performance reported by diverse model-provider families on popular agentic benchmarks (SWE-Pro, SWE-Verified and Terminal-Bench-2), and (ii) building on an $analysis of 138k trajectories generated by SSA$, we look beyond the $\texttt{pass@1}$ numbers which tend to be relatively even across frontier models. By representing agent trajectories in code state-spaces, we observe model-level differences in problem-solving behavior. Finer-grained metrics such as edit frequency, testing activity, and phase-transitions reveal how individual models allocate effort across different stages of autonomous problem solving.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18686

ForecastBench-Sim: A Simulated-World Forecasting Benchmark

作者:

Jaeho Lee↗Nick Merrill↗Ezra Karger↗

Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly, tail events are rare, and counterfactual questions are difficult to score. We introduce ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, a turn-based strategy game modelled on the Civilization series. Forecasters receive a fixed world report (a structured snapshot of the current game state) and answer questions about hidden future states; the benchmark then continues the simulation and scores forecasts. Because the world is simulated, the same setup can generate continuous or binary forecasting questions at arbitrary time horizons, paired intervention worlds for conditional or causal questions, and resolved examples of rare or disruptive outcomes. We describe the benchmark pipeline, question families, scoring protocol, and release artifacts, and report validation slices from model evaluations and an anonymized human pilot. ForecastBench-Sim is intended to complement real-world forecasting benchmarks by providing controlled, immediately resolvable tasks for studying probabilistic reasoning under dynamic world states.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13188

Transformer-Guided Graph Attention for Direct Cardiac Mesh Reconstruction: A Structural Digital Twin Framework

作者:

Abhishek H S↗Akash Ganamukhi↗Abhimanyu Suresh↗Aditya G Hiremath↗Prasad B Honnavalli↗Adithya Balasubramanyam↗

Building patient-specific cardiac models sits at the heart of precision cardiology, yet getting those models into clinical use keeps running into the same wall: mesh generation is slow, messy, and frustrating. The standard workflow – segmenting the image, running Marching Cubes, and then manually cleaning up the result – is time-consuming, inconsistent across operators, and demands specialist knowledge most clinical teams do not have. We take a fundamentally different approach. Instead of treating segmentation and mesh generation as two separate problems, we train a single end-to-end network that goes directly from a raw 3D medical image to a smooth, simulation-ready cardiac surface mesh. The core is a 3D Swin Transformer encoder-decoder that extracts volumetric features from CT or MRI volumes, paired with a Graph Attention Network (GAT) head that iteratively deforms a template mesh to fit the patient's cardiac boundary. We tested on the MM-WHS 2017 benchmark using both CT and MRI. Segmentation scores were competitive (Dice of 0.84 on CT, 0.83 on MRI), but the primary focus is mesh quality: mean Chamfer distance of 1.8 mm, with 95th-percentile surface distance below 5 mm. Every mesh is produced in a single forward pass – no Marching Cubes, no smoothing filters, no manual cleanup. We argue that for cardiac digital twin pipelines, geometric fidelity and topological correctness matter more than pixel-level Dice scores. By removing the post-processing bottleneck, this approach makes patient-specific cardiac simulation substantially more accessible for clinical use.

阅读与讨论 → 访问原文 →