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 (math.PR) 2026-06-16

Stein's method for the matrix normal distribution

arXiv:2601.11422v2 Announce Type: replace-cross Abstract: This work presents the first systematic development of Stein's method for matrix distributions. We establish the basic essential ingredients of Stein's method for matrix normal approximation: we derive an extended-generator-based Stein identity from a matrix Ornstein-Uhlenbeck diffusion with two-sided scales, provide an explicit semigroup representation for the solution of the Stein equation, and obtain regularity estimates for the solution. The new methodology is demonstrated in three examples: (i) smooth Wasserstein distance bounds to quantify the matrix central limit theorem (a didactic example), (ii) a Wasserstein distance bound for the matrix normal approximation of the centered matrix $T$ distribution, and (iii) a Stein's method-of-moments approach to estimating the row and column covariance factors of the matrix normal, yielding a flexible class of weighted flip-flop Stein estimators that generalize Dutilleul's classical flip-flop algorithm and naturally accommodate row/column importance weights, systematic missingness, and projection onto structured covariance families. The latter two examples are intrinsically matrix-valued and cannot be treated using naive vectorization.

02.
arXiv (CS.LG) 2026-06-12

Scalable anomaly detection via a univariate Christoffel function

arXiv:2606.12483v1 Announce Type: new Abstract: Anomaly detection plays a critical role in identifying unusual patterns across domains such as fraud detection, network intrusion, and system fault diagnosis. Recently, Christoffel function-based methods, rooted in polynomial optimization, have emerged as promising alternatives to deep learning due to their strong mathematical foundations and computational frugality. However, their practical applicability is hindered by the need to invert a matrix whose size grows exponentially with the data dimension, rendering the method intractable even for moderate-dimensional datasets. This paper addresses the dimensionality limitations of Christoffel function-based anomaly detection while preserving its key theoretical properties, i.e., the on-off support dichotomy behavior and the accurate support shape capture. We introduce UCF, a univariate Christoffel function which is based on the squared distance between the query point and the support points. Extensive experiments on the ADBench benchmark demonstrate that UCF consistently outperforms 14 state-of-the-art baselines in terms of Average Precision. By resolving the scalability bottleneck of the Christoffel Function, this work expands the toolkit of anomaly detection methods with a robust, theoretically grounded, and universally applicable approach.

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

Temporal Straightening for Latent Planning

arXiv:2603.12231v2 Announce Type: replace Abstract: Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to planning and contain information irrelevant – or even detrimental – to planning. Inspired by the perceptual straightening hypothesis in human visual processing, we introduce temporal straightening to improve representation learning for latent planning. Using a curvature regularizer that encourages locally straightened latent trajectories, we jointly learn an encoder and a predictor of a Joint-Embedding Predictive Architecture (JEPA) world model. We show that reducing curvature this way makes the Euclidean distance in latent space a better proxy for the geodesic distance and improves the conditioning of the planning objective. We demonstrate empirically that temporal straightening makes gradient-based planning more stable and yields significantly higher success rates across a suite of goal-reaching tasks. Our code is available at https://agenticlearning.ai/temporal-straightening.

04.
arXiv (CS.LG) 2026-06-18

Protein-Based Fish Species Identification: Dataset, Models, and Insights from Native Bangladeshi Fish

arXiv:2606.18302v1 Announce Type: cross Abstract: Correct identification of fish species is highly significant for food security, economic development, and climate resilience in Bangladesh. Protein sequences directly reflect functional and evolutionary constraints which are important for species authentication and biodiversity monitoring. Yet there exists no benchmark for native Bangladeshi fish species identification from protein sequence. In this study, we addressed this gap by introducing the first curated dataset for nine native Bangladeshi fish species of 2845 high quality protein sequences. We also established the first protein sequence classification baseline for this domain through a systematic benchmarking of seven architectural paradigms. Moreover, we propose a realistic deployable novel hybrid architecture of MotifCNN and Transformer with Terminal-Aware Positional-Encoding (MotifCNN-Transformer+TA-PE). Our novel architecture achieves 79.80% accuracy with macro-F1 of 0.80. The highest 83.04% accuracy is achieved by finetuned protein language model ProtBERT that has 420M parameters and requires dual 16GB GPUs for inference. According to McNemar's test, ProtBERT's 3.24% accuracy gain over our MotifCNN-Transformer+TA-PE is statistically insignificant (p = 0.1120). Our novel architecture beats it among six of the nine classes in per class identification. Also our MotifCNN-Transformer+TA-PE is approximately 5x faster, 42x smaller, and supports 16x larger batch size than ProtBERT and has GPU free inference, making it more practical for deployment in resources constrained areas such as rural Bangladesh. Beyond this, our foundational work shows effects of phylogenetic relationships on sequence similarity and establishes pathways for fisheries management, food authentication and biodiversity conservation in South Asia's protein dependent economy.

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

Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?

arXiv:2604.14892v3 Announce Type: replace-cross Abstract: Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM Jury, composed of three frontier AI models, for scoring 3334 diagnoses on 300 real-world low- and middle-income country (LMIC) hospital cases. Both LLM- and clinician-generated diagnoses are scored against expert panel diagnoses across four dimensions: diagnosis, differential diagnosis, clinical reasoning, and negative treatment risk. The LLM Jury scores are compared with expert and independent re-scoring panel scores to assess error metrics, inter-rater agreement, severe-risk errors, and the effect of post hoc calibration using isotonic regression. In our data, we find that: (i) the uncalibrated LLM Jury scores preserve ordinal agreement with the expert clinician panel scores, but are systematically lower; (ii) the probability of severe-risk errors is lower for the LLM Jury than the human expert re-score panels; (iii) the LLM Jury combined with LLM diagnoses can be used to identify diagnoses at high risk of error, enabling targeted expert review and improved panel efficiency; (iv) the calibrated LLM Jury scores and rankings of diagnosing agents show excellent agreement with those of the primary expert panels; (v) LLM Jury models show no self-preference bias, they did not score diagnoses generated by their own underlying model or models from the same vendor more (or less) favourably than those generated by other models. Together, these results provide evidence that a calibrated LLM Jury is a trustworthy and reliable proxy for expert clinician evaluation in medical AI benchmarking. Confirming these findings in other clinical settings is an important direction for future work.

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

Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning

arXiv:2606.11767v1 Announce Type: cross Abstract: Blind grasping with a dexterous hand is a crucial manipulation capability. Nevertheless, learning such tactile-only policies for real robots remains challenging due to the tactile sim-to-real gap and the limited expressiveness of sparse tactile signals. To bridge this gap, we propose a framework for tactile-only blind grasping that is deployable on a physical multi-fingered robotic hand. Our approach combines three key components. First, we introduce a Real2Sim tactile calibration pipeline that constructs a contact-calibrated digital-twin simulator capable of reproducing real tactile signals. Second, we improve the expressiveness of sparse tactile observations using a layout-aware tactile encoder, which incorporates sensor-geometry priors through self-supervised pretraining. Third, to improve generalization to unseen objects, we train object-specific reinforcement-learning experts in the calibrated simulator and aggregate their successful grasp trajectories into a tactile-conditioned Diffusion Policy. We evaluate our method on a physical LEAP Hand equipped with distributed tactile sensing across 10 seen and 10 unseen objects. The deployed policy achieves a 27\% real-world grasp success rate across all 20 objects, without real-world grasping demonstrations or visual input. Simulation ablations show that layout-aware tactile pretraining improves grasping performance, while sensing-level evaluations confirm that Real2Sim calibration increases the consistency of tactile contact events between simulation and hardware. Together, these results suggest that contact-event calibration, geometry-aware tactile representation learning, and diffusion-based policy aggregation provide an effective path toward tactile-only blind grasping on real dexterous robotic hands. Project page:Dex-Blind-Grasp.github.io.

07.
arXiv (CS.AI) 2026-06-17

MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation

arXiv:2606.04513v2 Announce Type: replace Abstract: Lane-level maps are critical infrastructure for autonomous driving and lane-level navigation, yet constructing and maintaining standardized lane networks for hundreds of cities remains highly labor-intensive. Recent end-to-end vectorized mapping methods can predict lane geometry and topology directly from sensor data, but they typically treat mapping specifications and traffic regulations as implicit, dataset-dependent supervision. Moreover, in complex scenes (e.g., worn or missing markings and occlusions), correct lane configurations are often under-determined by visual evidence alone, making specification violations a major source of human post-editing. We propose MapAgent, an industrial-grade agentic architecture that augments a vectorization backbone for specification-compliant lane-map production. Rather than merely adding an agent loop to map prediction, MapAgent couples backbone perception with explicit specification verification, constraint-aware reasoning, and deterministic map editing under a bounded, verification-driven Judge-Planner-Worker loop. A vision-language Judge diagnoses errors by jointly inspecting visual evidence and draft vectors, while a tool-calling Planner generates minimal corrective edits with post-edit re-validation. To remain scalable for city-scale production, MapAgent is selectively triggered only on tiles with low backbone confidence, adding modest overhead while preserving throughput. Experiments on real-world datasets show consistent gains over strong production baselines, especially in complex and long-tail scenarios. Additionally, MapAgent has been integrated into Baidu Maps, supporting lane-level map generation for over 360 cities nationwide and elevating the overall production automation to over 95%, demonstrating MapAgent's practicality and effectiveness for large-scale lane-level map generation.

08.
arXiv (CS.CL) 2026-06-16

DYNA : Dynamic Episodic Memory Networks for Augmenting Large Language Models with Temporal Knowledge Graphs in Continuous Learning

Large Language Models (LLMs) struggle to incorporate new knowledge without forgetting or costly retraining. We propose DYNA, a lightweight framework that augments a frozen LLM with a temporal knowledge graph where events are nodes and temporal relations are directed, timestamped edges. The graph serves as an external, updatable memory. At query time, DYNA retrieves relevant nodes via random walks and centrality measures, then augments the LLM's response. Evaluated on three temporal recall tasks, DYNA reduces catastrophic forgetting by ~7% compared to fine-tuning and improves temporal ordering by ~5% over standard RAG. Higher graph clustering coefficients correlate with better retrieval, showing that graph structure matters. Contributions: (1) episodic memory as temporal KG, (2) retraining-free LLM augmentation, (3) graph properties as predictors of retrieval performance.

09.
arXiv (math.PR) 2026-06-11

Sharp log-Sobolev inequalities on finite cyclic groups

arXiv:2606.02847v2 Announce Type: replace-cross Abstract: Let $\mathbb Z_n$ be the cyclic group equipped with the uniform probability measure $\pi$, and let $A_{\psi_n}$ be the Laplacian with word length \[ \psi_n(k) = \min(k,n-k). \] We prove the sharp log-Sobolev inequality \[ Ent_{\pi}(f^2) \le 2\pi(f A_{\psi_n} f), \qquad f:\mathbb Z_n \to [0,\infty), \] for every $n \ge 4$. The proof is inspired by the recent work of Frank and Ivanisvili[FrankIvanisvili2026] on a sharp log-Sobolev inequality for nearest-neighbor simple random walk. We use their cubic-majorant reduction, which turns the problem into a 3rd moment estimate; the new point is a blockwise 3rd moment estimate adapted to the word-length multiplier. The same 3rd moment argument also recovers the log-Sobolev inequality for Poisson-semigroup on the circle, first proved by Weissler[Weissler1980]. The same sharp inequalities were also obtained recently by Yao[Yao2026] by a different method.

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

Towards Understanding What State Space Models Learn About Code

arXiv:2602.06774v2 Announce Type: replace Abstract: State Space Models (SSMs) have emerged as an efficient alternative to the Transformer architecture. Prior work shows that, when trained under comparable conditions, SSMs can match or surpass Transformers on code understanding tasks. However, their internal mechanisms remain a black box. We present the first systematic analysis of what SSM-based code models learn along with the direct comparison between SSM and Transformer models in this domain. Our analysis shows that SSMs capture syntactic and semantic structure more effectively than Transformers during pretraining but forgets certain relations during fine-tuning on some tasks. To investigate this behavior, we introduce SSM-Interpret, a frequency-domain framework that exposes a spectral shift toward short-range dependencies during fine-tuning. Guided by these findings, we propose architectural modifications that significantly improve the performance of SSM-based code model by upto +6 MRR on NLCodeSearch. This demonstrates that our analysis not only explains model behavior but also leads directly to better designs.

11.
arXiv (CS.CL) 2026-06-25

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems. The book covers the full stack from first principles to production deployment, organized around a central thesis: building great agentic systems requires understanding every layer of the pipeline, not just one. The book opens with the LLM substrate – transformer architecture, GPU systems, training and fine-tuning (SFT,LoRA, MoE), model compression, and inference optimization – treated as essential foundations rather than the primary focus. It then develops the alignment and reasoning layer: reinforcement learning from human feedback (RLHF), PPO, DPO and its variants, GRPO, reward modeling, and RL for large reasoning models including chain-of-thought and test-time scaling. The second half is devoted to agentic AI proper. Topics include agentic training and trajectory-based RL, retrieval-augmented generation (RAG and Agentic RAG), memory systems (in-context, external, episodic, and semantic), agent harness design and context management, and a taxonomy of agent design patterns. Inter-agent coordination is covered in depth: the Model Context Protocol (MCP), agent skills and tool use, the Agent-to-Agent (A2A) communication protocol, and multi-agent architectures spanning centralized, decentralized, and hierarchical topologies. The book concludes with agent development frameworks, agentic UI design, evaluation methodology for agentic tasks, and production deployment. Each chapter pairs rigorous theoretical foundations with implementation guidance, code examples, and references to the primary literature.

12.
arXiv (CS.CV) 2026-06-24

Ingredient-Level Food Image Segmentation for Nutrition Awareness

Food images often contain several visible ingredients, so assigning one dish label to an entire image hides important visual structure. This work studies ingredient-level semantic segmentation on FoodSeg103, where the model predicts an ingredient class for each pixel. Two SegFormer variants were fine-tuned and evaluated under a controlled setup: SegFormer-B0 as the smaller baseline model and SegFormer-B1 as the larger final model. Both models use ImageNet-pretrained MiT backbones with newly initialized 104-class output layers. On the held-out FoodSeg103 test split of 2,135 images, B0 achieved 0.7709 pixel accuracy and 0.2521 mean IoU, while B1 achieved 0.7929 pixel accuracy and 0.3204 mean IoU. B1 improved every saved test metric, including a +0.0683 absolute gain in mean IoU. The system also converts predicted masks into visible ingredient-area percentages, giving a simple visual composition summary of the predicted meal. This summary can serve as a first-pass nutrition-awareness cue by providing a visual alternative to detailed food tracking similar to plate-based meal guidance, but it is not a direct estimate of calories, macronutrients, food mass, volume, density, or true portion size.

13.
arXiv (quant-ph) 2026-06-25

Finite-Shot Sensitivity for Moment Estimation in Quantum Metrology

arXiv:2606.25920v1 Announce Type: new Abstract: The quantum Cramér-Rao bound can be saturated only asymptotically and does not specify how many measurements are needed for a concrete estimator to approach it. We develop a finite-measurement theory for method-of-moments estimation, where the parameter is inferred from the sample mean of a calibrating observable rather than from the full likelihood. For general quantum statistical models, the expansion is written in terms of the calibration curve and the central moments of the measured observable. Nonlinear calibration curves make the usual moment estimator biased at finite measurement number; we construct a bias-corrected estimator with bias $O(\nu^{-3})$. This gives sensitivity corrections beyond the leading error-propagation term of the chosen moment protocol. We identify a general density-matrix condition under which the full $1/\nu^2$ correction vanishes. In unitary examples, the leading residual correction appears at order $1/\nu^3$, is governed by calibration curvature, and can be reduced or cancelled by higher-rank components of the same measured observable. The resulting thresholds quantify how many measurements are needed before the asymptotic sensitivity of a moment-estimation protocol is operationally visible.

14.
arXiv (CS.LG) 2026-06-15

FlowMo-WM: A World Model with Object Momentum and Hidden Ambient Drift

arXiv:2606.13817v1 Announce Type: cross Abstract: World models in robot learning predict future states from visual observations and actions, enabling agents to reason about the consequences of their controls. However, many action-conditioned models are evaluated in settings where motion is dominated by immediate control, whereas aquatic surface vehicles and other real-world objects continue moving under inertia and are displaced by hidden ambient drift, such as water currents or wind. We propose FlowMo-WM, an end-to-end trainable visual world model that infers object-centric motion state and a predictive long-history context associated with hidden drift from image-action histories without direct supervision of flow fields. FlowMo-WM factorizes image-action history into a short-history latent state, trained to summarize object-centric motion, and a longer-history context, trained to summarize slowly varying exogenous influences. A zero-context residual transition separates action-conditioned base dynamics from context-dependent drift effects during latent rollout. In simulated aquatic surface-vehicle environments with diverse hidden flows, disturbances, and randomized vehicle dynamics, FlowMo-WM improves long-horizon rollout accuracy over representative action-conditioned latent world models. Prediction-time context ablations, in which the inferred context is zeroed or shuffled during rollout, show that the ambient context is important for stable prediction under hidden drift, while frozen linear probes characterize information encoded in the learned factors.

15.
arXiv (CS.LG) 2026-06-18

Spatiotemporal downscaling and nowcasting of urban land surface temperatures with deep neural networks

arXiv:2605.13566v2 Announce Type: replace Abstract: Land Surface Temperature (LST) is a key variable for various applications, such as urban climate and ecology studies. Yet, existing satellite-derived LST products provide either high spatial or high temporal resolution, resulting in a fundamental trade-off between the two. To address this trade-off, we combine observations from a geostationary and a polar orbiting satellite and provide LST fields at high spatial and high temporal resolution (1 km at 15-min intervals). We demonstrate their application for intraday forecasting of LSTs. To estimate LST fields at high spatiotemporal resolution, a U-Net model is trained to map LST fields from SEVIRI/MSG (3 km and 15 min resolution) to LST fields from Terra/Aqua MODIS (1 km, 4 overpasses per day) that are collocated in space and time. The presented model has been trained on LSTs across large European cities with a population exceeding 1 million inhabitants, and achieves an RMSE = $1.92${\deg}C and near-zero bias MBE = $0.01${\deg}C on the hold-out test set. As a second step, we present an LST nowcasting model based on ConvLSTM architecture, trained across downscaled LST fields with forecast lead times of 15 to 75 minutes. The nowcasting model outperforms a persistence and a Climatological Rolling Median benchmarks, with RMSEs of $0.57$ to $1.15${\deg}C for the considered lead times and biases ranging from $-0.1$ to $0.14${\deg}C. An additional validation conducted against independent MODIS overpasses confirms robust performance. Our LST forecast model at high spatiotemporal resolution is directly applicable to operational satellite-based LST monitoring.

16.
arXiv (CS.AI) 2026-06-24

Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications

arXiv:2606.23858v1 Announce Type: cross Abstract: A primary challenge in AI safety is the existence of adversarial examples – slightly distorted inputs that cause a neural network (NN) to misclassify. To mitigate this problem, recent research focuses on the computation of robustness certifications, which, for a given input, determine the largest distortion the input may receive without breaking the network's prediction. Robustness certifications can be interpreted as an axis-aligned hyper-rectangle (multi-dimensional intervals). Most existing approaches focus on maximizing the certification's volume, but recent intractability results prohibit the computation of volume-optimal certifications in reasonable time. We introduce the apothem measure and show how to compute apothem-optimal certifications in a linear number of calls to a NN verifier (oracle) w.r.t. the input domain's diameter. Moreover, we prove that we cannot have a volume-optimal, oracle-based algorithm, even if we discard the oracle costs. Also, we introduce dual certifications – an interval including all instances of a class – thus providing apothem-minimum upper bounds to a robustness certification. Further, we present the ParallelepipedoNN system, which we evaluate on the standard MNIST and Fashion MNIST benchmarks. A preliminary comparison with existing work on the same datasets reveals at least two-fold improvement w.r.t. the minimum edge length.

17.
arXiv (CS.LG) 2026-06-16

When Does q-error Predict Plan Regret? Three Regimes of Cardinality-Estimation Error

arXiv:2606.15600v1 Announce Type: cross Abstract: Cardinality-estimation (CE) research ranks estimators by q-error, yet it is well known that q-error is an imperfect proxy for query-plan quality. We give a measurement-driven account of when it is a good proxy and when it is not, and why. Modeling plan selection as an argmin over a piecewise-linear cost landscape, we find that plan regret (the cost of the chosen plan relative to the optimal, under true cardinalities) is governed by plan-cost geometry in a regime-dependent way. (i) For small errors, a true-point condition number kappa predicts regret and out-predicts q-error; its predictive power decays to zero as error grows, as a local linearization must. (ii) For large errors – where deployed learned estimators operate – an estimator-independent average-case sub-optimality measure ACS-infinity predicts which queries are regret-prone (Spearman rho ~ 0.54 on STATS-CEB), while q-error is nearly uninformative at the query level (rho ~ 0.05). (iii) The worst case is Haritsa's maximum sub-optimality (MSO). The three are one cost-ratio spectrum under three weightings. We prove a limit law ACS-infinity = sum_k r_k pi_k with cardinality-independent combinatorial weights, and validate every claim on STATS-CEB and JOB-light with four released estimators under pre-registered decision rules, and confirm on real PostgreSQL runtime that ACS-infinity predicts regret where q-error does not. The contribution is conceptual and empirical – an average-case companion to worst-case robust query optimization, and a characterization of when an accuracy metric tracks plan quality – rather than a new estimator. Code and the full pre-registration are public.

18.
arXiv (CS.CL) 2026-06-17

FeedEval: Pedagogically Aligned Evaluation of LLM-Generated Essay Feedback

Going beyond the prediction of numerical scores, recent research in automated essay scoring has increasingly emphasized the generation of high-quality feedback that provides justification and actionable guidance. To mitigate the high cost of expert annotation, prior work has commonly relied on LLM-generated feedback to train essay assessment models. However, such feedback is often incorporated without explicit quality validation, resulting in the propagation of noise in downstream applications. To address this limitation, we propose FeedEval, an LLM-based framework for evaluating LLM-generated essay feedback along three pedagogically grounded dimensions: specificity, helpfulness, and validity. FeedEval employs dimension-specialized LLM evaluators trained on datasets curated in this study to assess multiple feedback candidates and select high-quality feedback for downstream use. Experiments on the ASAP++ benchmark show that FeedEval closely aligns with human expert judgments and that essay scoring models trained with FeedEval-filtered high-quality feedback achieve superior scoring performance. Furthermore, revision experiments using small LLMs show that the high-quality feedback identified by FeedEval leads to more effective essay revisions. We release our code and curated datasets at: https://github.com/BBeeChu/FeedEval.git.

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

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces additional weights between the LLM layers, Soft Prompting introduces additional fine-tuning-specific raw tokens to an LLM input. However, both require modification to the computational graphs of precompiled, preoptimized LLMs. As a result, neither is fully supported in high-throughput engines like vLLM. We propose fine-tuning with ART (Art-based Reinforcement Training). The method injects information into a frozen Multimodal Large Language Model (MLLM) by optimizing only its raw visual input, thus enabling the soft-token approach on pre-compiled computational graphs. It relies on backpropagation of gradients back into a plain pixel array and thus supports any fine-tuning objective. Moreover, the optimized visual input can be stylized as task-relevant computational artworks. The approach's effectiveness is confirmed for different sizes of a popular open Qwen architecture and for several textual benchmarks. Specifically, ART reaches accuracy competitive with LoRA across mathematics and structured-tool-use benchmarks.

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

GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge

Large language model (LLM) reasoning is ephemeral: chains of thought vanish with the context window, pruned search branches leave no record, and memory buffers cannot be diffed, merged, or audited. Every other complex software process (code, infrastructure, data, experiments) is version-controlled; reasoning is not. We introduce GitOfThoughts, which stores an agent's reasoning tree as a git repository: every scored thought is a commit, scores are notes, outcomes are tags, and retrieval is "git log" over the agent's own history. This makes reasoning replayable, auditable, and mergeable across agents at near-zero engineering cost. We then ask the harder question: does memory, in any substrate, actually improve accuracy? Across five substrates (none, markdown, vector, graph, git), two benchmarks, two model scales, and pre-registered replications, the answer for novel problems is no. No memory format reliably helps, and a promising early result collapsed under its own pre-registered replication. Memory pays only above what we call the copyability threshold: when the retrieved case is a near-duplicate of the current problem (similarity >~ 0.8), accuracy jumps sharply; below it, nothing. The gain is answer retrieval, not method transfer: a 4.5x larger model doubles the near-duplicate payoff yet still cannot extract a transferable method from a worked example. The only general lever we find is test-time sampling. The case for git-as-substrate is therefore auditability, provenance, and mergeability at accuracy parity. We document a retracted result and a refuted hypothesis to model the evaluation standard we hold ourselves to.

21.
medRxiv (Medicine) 2026-06-22

The Protective Role of Belonging and Socioeconomic Status in Dropout Intent Among Minority Ethnic Students: A Mixed Methods Study

Improving minority ethnic student retention is a global higher education priority. This mixed-methods study investigated how institutional belonging and socioeconomic status interact to shape dropout intentions among minority university students in the UK (N = 182). Quantitative results revealed that perceived course difficulty and lower subjective socioeconomic status were the strongest predictors of dropout intent. While the interaction between socioeconomic status and difficulty was non-significant, qualitative accounts showed distinct structural vulnerabilities. Financial strain restricted social integration, turning socioeconomic disparities into campus isolation. Conversely, representative curricula, diverse peer networks, and stable cultural in-groups (e.g., religious affiliations, living in the parental home) functioned as essential psychological buffers against academic exhaustion and alienation. Universities must shift from transactional models to sustained structural equity to protect vulnerable student groups.

22.
arXiv (CS.LG) 2026-06-19

UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

arXiv:2606.04101v3 Announce Type: replace-cross Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes. Existing balancers redistribute experts periodically based on historical load, which becomes unreliable for production deployments with non-stationary load patterns. We present UltraEP, the first exact-load, real-time balancer for large-EP MoE training and serving prefill on rack-scale nodes (RSNs). Leveraging the extended scale-up connectivity among dozens of GPUs within RSNs, UltraEP rebalances every microbatch and layer on critical paths, which requires nontrivial co-design of plan solving and expert replication communication to minimize exposed overhead. To this end, UltraEP eagerly reacts to post-gating load with an efficient quota-driven planner, and executes the resulting irregular expert-state transfers with RSN-native persistent tile streaming and relay-based fan-out mitigation. We evaluate UltraEP in a multi-RSN deployment of up to 256 GPUs, using cutting-edge MoE models from 106B to 671B parameters. Averaged across training and serving, UltraEP achieves 94.3% of the force-balanced ideal throughput, delivering 1.49$\times$ improvement over no-balancing, while reducing the final inter-rank imbalance from 1.30$-$4.01 to 1.01$-$1.04.

23.
arXiv (CS.CL) 2026-06-11

Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical judgment while patients increasingly use them for health advice. We show this assumption is fragile: when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer. We call the ability to maintain correct judgment under adversarial context epistemic resilience, and introduce MedMisBench to measure it. MedMisBench contains 10,932 medical question items and 48,889 misleading context-option pairs spanning medical reasoning, agentic capability, and patient-journey evaluation. Across 11 model configurations, mean accuracy falls from 71.1% on original questions to 38.0% under focused misleading context, with 51.5% attack success. The most damaging injections are formal, rule-like fabrications: authority-framed falsehoods reach 69.5% attack success and exception-poisoning claims reach 64.1%. A 14-member clinical panel from 7 countries identified serious potential harm in 38.2% of reviewed cases. MedMisBench exposes a structural blind spot in LLM evaluation in medical settings: existing benchmarks measure what models know, but not whether they preserve correct medical judgment under misleading context.

24.
arXiv (CS.AI) 2026-06-16

Hybrid NARX-LLM for Greenland Iceberg Discharge: Prompt-Driven Residual Correction

arXiv:2606.15288v1 Announce Type: cross Abstract: Greenland iceberg discharge exhibits complex nonlinear dynamics with limited observability, challenging traditional predictive models. We present a Hybrid NARX-LLM framework that combines a nonlinear autoregressive model with exogenous inputs (NARX) and a large language model (LLM) for residual correction. We further propose a Physics-Informed Prompt (PIP) method that transforms unstructured physical knowledge into structured prompts for zero-shot in-context reasoning. The primary objective is to explore the corrective potential of this framework for modeling Greenland iceberg discharge, rather than merely optimizing predictive accuracy. The NARX component captures intrinsic temporal dependencies, while the LLM, guided by PIP, encodes glacier dynamics and environmental drivers and perceives key trend patterns to correct systematic prediction errors. This integration allows the model to reason about unmodeled factors and produce interpretable residuals, enhancing overall predictive accuracy. Applied to Greenland iceberg discharge time series, our approach addresses extreme events that are difficult to predict due to rare variations and nonstationary trends, a limitation often overlooked by traditional methods. By fusing structured time-series modeling with knowledge-driven foundation AI, the framework offers a scalable and interpretable pathway to bridge data-limited climate forecasting with physics-informed LLM reasoning. The code is available.

25.
arXiv (CS.CL) 2026-06-11

Context-Driven Incremental Compression for Multi-Turn Dialogue Generation

Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length. Naive truncation or summarization degrades fidelity, while existing context compressors lack cross-turn memory sharing or revision, causing information loss and compounding errors in long dialogues. We revisit the context compression under conversational dynamics and empirically present its fragility. To improve both efficiency and robustness, we introduce Context-Driven Incremental Compression (C-DIC), which treats a conversation as interleaved contextual threads and stores revisable per-thread compression states in a single, compact dialogue memory. At each turn, a lightweight retrieve, revise, and write-back loop shares information across turns and updates stale memories, stabilizing long-horizon behavior. In addition, we adapt truncated backpropagation-through-time (TBPTT) to our multi-turn setting, learning cross-turn dependencies without full-history backpropagation. Extensive experiments on long-form dialogue benchmarks demonstrate superior performance and efficiency of C-DIC; notably, C-DIC shows stable inference latency and perplexity over hundreds of dialogue turns, supporting a scalable path to high-quality dialogue modeling.