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.
medRxiv (Medicine) 2026-06-24

Clinical Evaluation of Automated Self-Operated Transvaginal Ultrasound for Ovarian Stimulation Monitoring

Objective To evaluate the feasibility, safety, patient acceptance, and preliminary clinical relevance of automated self-operated transvaginal ultrasound for ovarian stimulation monitoring. Design Prospective observational pilot study. Subjects Ten women undergoing ovarian stimulation for in vitro fertilization or fertility preservation at a single high-volume private IVF center. Exposure Participants performed investigational self-operated transvaginal ultrasound examinations immediately following standard monitoring visits. Patients inserted and stabilized the ultrasound probe while ovarian and endometrial imaging was acquired through controlled motorized probe rotation without real-time anatomical guidance. Main Outcome Measure(s) The primary outcome was feasibility, defined as the generation of evaluable imaging datasets suitable for ovarian stimulation monitoring. Secondary outcomes included bilateral ovarian visualization, procedural safety, patient-reported outcomes, follicular assessment, and agreement of endometrial thickness measurements with standard transvaginal ultrasound. Result(s) Nineteen investigational scan attempts were performed, yielding 18 evaluable datasets (94.7%). Bilateral ovarian visualization was achieved in 16 of 18 evaluable examinations (88.9%), whereas partial ovarian visualization occurred in 2 examinations (11.1%). No adverse events, adverse device effects, vaginal injury, bleeding, or infection were observed. Patient-reported outcomes demonstrated high procedural acceptability, with all participants expressing willingness to reuse the system. Compared with standard transvaginal ultrasound monitoring, investigational self-operated acquisition significantly improved overall examination experience (Wilcoxon p=0.002). Investigational imaging demonstrated clinically relevant agreement with standard transvaginal ultrasound for follicular categorization and endometrial assessment. Counts of follicles [≥]14 mm correlated strongly with mature oocyte recovery for both investigational and standard ultrasound measurements (Spearman {rho}=0.83 and {rho}=0.80, respectively). Endometrial thickness measurements also demonstrated strong correlation between modalities (Spearman {rho}=0.91). Conclusion(s) This prospective pilot study demonstrates the feasibility of automated self-operated transvaginal ultrasound during ovarian stimulation monitoring. Investigational imaging generated clinically relevant monitoring information without observed safety concerns and was associated with high patient acceptance. These findings support further investigation of patient-operated acquisition strategies and standardized imaging workflows in reproductive medicine.

02.
arXiv (CS.CL) 2026-06-17

HistoRAG: Embedding Historical Methodology in Retrieval-Augmented Generation Through Critical Technical Practice

Retrieval-Augmented Generation (RAG) is the prevailing architecture for grounding language model outputs in external evidence, yet its dominant evaluation paradigms and default configurations remain oriented toward factual question-answering. For interpretive disciplines such as historical studies, RAG embeds assumptions that conflict with scholarly practice. We introduce HistoRAG, a framework that translates historiographical principles into concrete architectural interventions. Separated retrieval and generation decouples source discovery from interpretation, temporal windowing enforces balanced source representation across the research period as a methodological requirement of historical inquiry, and LLM-as-judge evaluation makes relevance judgments transparent and contestable. We evaluate these interventions using SPIEGELragged, applied to 102,189 articles from Der Spiegel (1950-1979). Each intervention addresses a measurable deficiency in standard RAG: era-specific vocabulary retrieves zero chunks from the 1950s when using 1970s terminology, evidence of the temporal skew that motivates windowing; vector similarity and LLM-assessed relevance correlate only weakly (Spearman rho = 0.275), motivating post-retrieval evaluation; and keyword-based and semantic retrieval surface largely disjoint source pools, motivating an architecture in which both operate as complementary retrieval layers under a shared LLM evaluation filter. We also introduce the concept of Zwischentexte (intermediate texts that function as interpretive proposals rather than findings) as a framework for responsible integration of LLM-generated text into scholarly practice. The architecture offers a model for how domain-specific epistemological commitments can be translated into RAG design decisions, and may transfer to other interpretive disciplines working with large corpora.

03.
arXiv (CS.AI) 2026-06-11

Can Open-Source LLM Agents Replace Static Application Security Testing Tools? An Empirical Assessment

arXiv:2606.11672v1 Announce Type: cross Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model- (GenAI-) based agent when powered by three different Ollama-hosted general-purpose open source models. We assess each agent's performance using precision, recall, false positive count, and a calculated composite score based upon the interplay of the captured metrics, against the baseline performance of an existing, vetted Static Application Security Testing (SAST) tool, Bandit. Our findings refute the notion that a modern open-source GenAI LLM-based agent is currently suitable for the specialized task of SAST scanning under realistic conditions.

04.
arXiv (CS.LG) 2026-06-19

ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models

arXiv:2606.19919v1 Announce Type: new Abstract: Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost. Existing efficiency-oriented methods attempt to shorten or mix reasoning strategies, yet often degrade reasoning capability. We identify the root cause as sequence-level coupling between efficiency incentives and correctness optimization, which implicitly penalizes long but correct reasoning trajectories. To address this issue, we propose Adaptive Dual-Process Thinking (ADaPT), a token-level dual-process framework that explicitly decouples efficiency and correctness signals during training. ADaPT introduces a mode-selection token to control fast and slow reasoning, applying efficiency-related rewards exclusively to this token to avoid penalizing correct long reasoning while encouraging efficiency when appropriate. Moreover, ADaPT enables precise and continuous control over the efficiency-performance trade-off at inference time: by adjusting the generation probability of the mode-selection token, a single trained model can smoothly move along the efficiency-performance Pareto frontier. Extensive experiments demonstrate that ADaPT significantly reduces inference cost while maintaining strong reasoning performance across multiple benchmarks.

05.
arXiv (CS.CV) 2026-06-17

FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement

Registration of multiview point clouds conventionally relies on extensive pairwise matching to build a pose graph for global synchronization, which is computationally expensive and inherently ill-posed without holistic geometric constraints. This paper proposes FUSER, the first feed-forward multiview registration transformer that jointly processes all scans in a unified, compact latent space to directly predict global poses without any pairwise estimation. To maintain tractability, FUSER encodes each scan into low-resolution superpoint features via a sparse 3D CNN that preserves absolute translation cues, and performs efficient intra- and inter-scan reasoning through a Geometric Alternating Attention module. Particularly, we transfer 2D attention priors from off-the-shelf foundation models to enhance 3D feature interaction and geometric consistency. Building upon FUSER, we further introduce FUSER-DF, an SE(3)$^N$ diffusion refinement framework to correct FUSER's estimates via denoising in the joint SE(3)$^N$ space. FUSER acts as a surrogate multiview registration model to construct the denoiser, and a prior-conditioned SE(3)$^N$ variational lower bound is derived for denoising supervision. Extensive experiments on 3DMatch, ScanNet and ArkitScenes demonstrate that our approach achieves the superior registration accuracy and outstanding computational efficiency.

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

Can Editing 1 Neuron Fix Repetition Loops in LLMs?

arXiv:2606.13705v1 Announce Type: cross Abstract: Yes. Can it cure doom loops? Probably not. The Gemma 4 instruction-tuned models share a reproducible failure: on long factual enumeration prompts, such as listing every episode of a TV series, the 88 IAU constellations, or the 151 original Pokemon, they collapse into repetition, either a tight verbatim loop or a list whose entries decay onto a single answer. These loops occur at rates as high as 95% and survive prompt rewording, inference-engine changes, and most sampling adjustments. In this paper we explore whether this behavior is localized enough to remove by weight edits. To localize the cause, we use per-layer ablation and per-neuron attribution, then confirm the strongest candidates with full-generation sweeps. The loops trace to a small set of MLP neurons (or, in the 26B-A4B Mixture-of-Experts model, a few routed experts) which we suppress with static weight edits. These "surgeries" can be as small as a single sign-inverted neuron (in the E2B model). The size of the effective edits grows with model scale, but in all cases, the loop patterns can be addressed at normal generation budgets while preserving general-purpose benchmark scores. However, the edits do not solve everything: we also study longer thinking budgets, where the two larger models most visibly enter doom looping, i.e. a non-convergent regime in which the model self-corrects in circles over a fact it cannot recall, exhausting the budget without committing to a final answer. We show this residual failure is reduced but not eliminated by the same edits, and argue it is fundamentally a knowledge-precision problem rather than a removable circuit; weight surgery can delete a loop, but it cannot supply a missing fact. Our results are both a feasibility demonstration, that is, evidence that a concrete generation pathology can be localized to a few parameters and edited out, and a delineation of where that approach stops.

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

LiAuto-GeoX: Efficient Grounded Driving Transformer

Dense 3D reconstruction has demonstrated immense potential for spatial understanding, yet its viability as a real-time, onboard representation for autonomous driving remains an open challenge. Existing large-scale visual geometry models typically require substantial computational resources and lack the long-range geometric fidelity, surround-view consistency, and real-time efficiency demanded by dynamic driving environments. To bridge this gap, we present LiAuto-GeoX, an efficient grounded driving transformer designed for deployable, ego-centric 3D scene understanding. Our approach begins by learning a high-capacity driving geometry model from large-scale surround-view data, utilizing sparse LiDAR priors to provide robust geometric grounding in distant, ambiguous, or structure-sparse regions. We then instantiate this capability into a highly compact 155M-parameter onboard model through a novel geometry-preserving distillation framework. This framework employs mask-guided depth-aware distillation to retain fine-grained metric structures by emphasizing geometrically informative regions, and relative-pose relational distillation to enforce cross-view spatial consistency through pose-induced geometric relations. Extensive evaluations reveal that LiAuto-GeoX runs at 220 FPS on KITTI while maintaining high-fidelity dense reconstruction, enabling real-time deployment. The learned geometry transfers seamlessly to downstream autonomy tasks, achieving 90.6 PDMS in trajectory prediction, 24.63 mIoU in occupancy prediction, and 47.67 IoU in future-frame prediction. These all demonstrate that efficient dense 3D reconstruction can transcend its traditional role as a perception target to serve as a scalable, foundational geometric representation for next-generation autonomous driving.

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

Size Doesn't Matter: Cosine-Scored Sparse Autoencoders

arXiv:2606.15054v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's norm. Under BatchTopK, high-norm tokens inflate all pre-activations simultaneously, claiming dictionary slots regardless of content alignment. This matters because sublayer normalization has already discarded the magnitude the score measures, so the encoder detects a quantity the model does not read. We replace the score with a learned blend of cosine similarity and input magnitude, letting the optimizer choose how much norm to use; a per-feature extension lets each feature decide independently. In both regimes, training is free to recover inner product but never does, with no feature ever choosing more than half-magnitude dependence. At matched reconstruction, the cosine encoder learns features that align with human-recognizable concepts far more often than standard, filling dictionary slots that inner product wastes on norm detectors. Loss reweighting that equalizes gradients barely closes the gap, confirming forward-pass score geometry as the lever. The advantage is not universal across tasks or depths, but we believe cosine scoring should be the default for dictionary learning on normalized representations.

09.
arXiv (CS.CV) 2026-06-11

Mitigating Content Shift and Hallucination in GenAI Image Editing via Structural Refinement

Generative AI (GenAI) image editors, such as Nano Banana, produce visually compelling results for retouching tasks, enabling non-experts to edit images through text prompts alone. However, the generative nature of these models often introduces spatial misalignment, texture distortion, and content hallucination, all of which are detrimental to downstream workflows that require pixel-level fidelity. We identify a problem setting we call "structure-preserving GenAI fusion" for black-box GenAI image retouching: retain the perceptual enhancements of a GenAI output while enforcing structural faithfulness to the original input image. To address this problem, we propose a post-processing framework that fuses an input image with its GenAI-enhanced counterpart by first establishing coarse spatial and photometric correspondences, then performing a fusion stage that transfers desired enhancements while suppressing hallucinated content. In the absence of direct prior work in this setting, we evaluate our framework against representative methods from photorealistic style transfer and image fusion. Our experiments demonstrate that our method better preserves aesthetic quality while maintaining pixel-level structural consistency and the input resolution.

10.
arXiv (CS.LG) 2026-06-16

Peak-Based Nuclide Identification in HPGe $\gamma$-Spectrometry with Machine Learning and SHAP

arXiv:2606.14874v1 Announce Type: cross Abstract: High-purity germanium gamma spectra often require time-consuming analyses from subject matter experts. Photopeaks within these spectra are carefully fitted and numerical methods are employed to assist with nuclide identification (NID) and quantification. Amending the list of nuclides identified by analysis software can be nontrivial. When many samples need to be analyzed, it is therefore challenging to make timely and correct decisions. Supervised machine-learning-based NID can serve as an expert-informed, automated tool to improve the initial set of radionuclides suggested to an analyst and more effectively drive subsequent quantification. To that end, we implemented machine learning models that map photopeaks carefully fitted by analysts to NID results for experimental spectra containing various isotopic combinations drawn from a set of 65 isotopes. The best model achieved an F1 score of 0.97, markedly surpassing the F1 score of 0.84 achieved by traditional software when compared using a nuclide library comprising the same 65 isotopes assessed by the models. Finally, we illustrated the most important input features for model predictions using Shapley Additive Explanations. These explanations revealed that the models use physically relevant photopeaks when making predictions for the isotopes in our nuclide library.

12.
bioRxiv (Bioinfo) 2026-06-11

DivQuant: Estimation of Species Richness and Entropy from Small Samples

Estimating diversity properties of discrete distributions from a small observed sample is a fundamental problem in algorithmic statistics that has applications in many fields, in particular bioinformatics, but also in ecology or linguistics. The two most common diversity measures are the number of distinct elements in a multiset, also referred to as species richness in ecology or alpha diversity in microbial analysis, and the Shannon entropy, also referred to as evenness. Estimating these properties from a small sample is particularly challenging for distributions with many rare elements. Thus, many estimators have been proposed in the past that, in practice, work well for different types of distributions. We present DivQuant, an optimization-based, extrapolating richness and entropy estimator with three contributions. First, we formulate the upsampling problem as a convex quadratic program with a Neyman {chi}2 objective. Unlike the linear program of its predecessor RichnEst, DivQuant admits confidence intervals via {chi}2 test inversion that are empirically well-calibrated. Second, we replace RichnEst's fixed-threshold fingerprint truncation with the rare/abundant fingerprint split of Valiant and Valiant, which strongly reduces problem size and preserves enough degrees of freedom for the confidence-interval program to remain valid and feasible. Third, we plug the optimal population fingerprint returned by the program into Shannon's entropy formula to obtain an entropy estimate. DivQuant attains close-to-nominal 95% confidence intervals in essentially all tested regimes, including six simulated distribution families, Tara Oceans microbiome data, and 10X Genomics scRNA-seq data, while competing state-of-the-art methods (RichnEst, iNext, PreSeq) miss the true richness in up to 80% of instances, well above the nominal 5%. In addition, DivQuant outperforms classical asymptotic entropy estimators (Miller-Madow, CAE) and the extrapolating iNext estimator. Running times remain competitive, with DivQuant typically completing in seconds. DivQuant is available as a command-line tool at https://gitlab.com/rahmannlab/divquant.

13.
arXiv (CS.CV) 2026-06-12

MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics

To study the ability to infer physical dynamics from videos and extrapolate them forward in time, we assemble a dataset of 2D Material Point Method (MPM) physical simulations covering rich physical phenomena such as deformable objects, fluids, kinetic objects, and emitters. We study code generation and video diffusion approaches on this dataset, identifying their strengths and weaknesses by varying the amount of physically relevant side information. The code generation model, beyond giving a working demonstration of automatic synthesis of MPM simulations, reveals that such an approach struggles with inferring physical parameters from visual input, but relative to video diffusion, produces physically and temporally stable extrapolations forward in time, while the video diffusion model more strongly identifies geometric properties from visual input but produces physically implausible extrapolations.

14.
bioRxiv (Bioinfo) 2026-06-13

MoE-Bind: Guiding De Novo Protein Binder Generation with Sparse Experts

作者:

De novo protein binder design has been dominated by structure-based pipelines that require known three-dimensional target conformations and consume substantial compute and generation time per design, limiting their throughput and accessibility for routine large-scale binder exploration. Sequence-only generative models promise a faster and lighter alternative, yet existing systems remain uniformly dense and frequently reintroduce structural computation at inference, undermining the core advantages they were intended to deliver. Across the broader language modelling community, transformers have meanwhile transitioned from fully dense designs to sparse Mixture-of-Experts architectures that decouple capacity from per-token compute, a shift that has yet to reach sequence-only protein binder generation. We present MoE-Bind, an autoregressive protein binder generator that, for the first time in this domain, combines Multi-head Latent Attention with a sparse Mixture-of-Experts feed-forward network and is evaluated under two independent structure predictors, Boltz-2 and AlphaFold2-Multimer. Despite activating less than half the per-token parameters of compute-matched dense baselines, MoE-Bind matches or exceeds them on full-length receptor-conditioned binder generation on a leakage-free Docking Benchmark 5.0 evaluation, transfers without peptide-specific training to short-peptide design, and reduces training and inference compute by a large margin. Routing analysis on generated binders reveals interpretable expert specialization at both the individual amino acid and biochemical group level, a structured expert-token alignment not previously reported for natural-language MoE models. These results show that sparse architectural design, rather than scale, can deliver fast, structure-free, and interpretable protein binder generation.

15.
arXiv (CS.AI) 2026-06-17

Riemann-Bench: A Benchmark for Moonshot Mathematics

arXiv:2604.06802v2 Announce Type: replace Abstract: Recent AI systems have achieved gold-medal-level performance on the International Mathematical Olympiad, demonstrating remarkable proficiency at competition-style problem solving. However, competition mathematics represents only a narrow slice of mathematical reasoning: problems are drawn from limited domains, require minimal advanced machinery, and can often reward insightful tricks over deep theoretical knowledge. We introduce Riemann-Bench, a private benchmark of expert-curated problems designed to evaluate AI systems on research-level mathematics that goes far beyond the olympiad frontier. Problems are authored by Ivy League mathematics professors, graduate students, and PhD-holding IMO medalists, and routinely took their authors weeks to solve independently. Each problem undergoes double-blind verification by two independent domain experts who must solve the problem from scratch, and yields a unique, closed-form solution assessed by programmatic verifiers. We evaluate frontier models as unconstrained research agents, with full access to coding tools, search, and open-ended reasoning, using an unbiased statistical estimator computed over 100 independent runs per problem. Our results reveal that all frontier models currently score below 10%, exposing a substantial gap between olympiad-level problem solving and genuine research-level mathematical reasoning. By keeping the benchmark fully private, we ensure that measured performance reflects authentic mathematical capability rather than memorization of training data.

16.
arXiv (CS.CL) 2026-06-18

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training. We conduct a first-order gradient analysis of token-level entropy dynamics under GRPO and identify a token-level credit assignment mismatch: the per-token entropy variation decomposes into the product of the trajectory-level advantage and an entropy sensitivity function over the next-token distribution, yielding an advantage-surprisal four-quadrant structure and a near-criticality property. Motivated by it, we propose STARE (Surprisal-guided Token-level Advantage Reweighting for policy Entropy stability), which identifies entropy-critical token subsets via batch-internal surprisal quantiles, selectively reweights their effective advantages, and incorporates a target-entropy closed-loop gate for stable entropy regulation. Across model scales from 1.5B to 32B and three task families (Short CoT, Long CoT, and Multi-Turn Tool Use), STARE sustains stable RL training over thousands of steps while maintaining policy entropy within the target band. On AIME24 and AIME25, STARE outperforms DAPO and other competitive baselines by 4%-8% in average accuracy, with reflection tokens and response length growing in tandem, indicating sustained exploration-exploitation balance that further unlocks RL training potential.Code is available at https://github.com/hp-luo/STARE.

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

RePAIR: Predictive Self-Supervised Representation Learning in Chess

arXiv:2606.11860v1 Announce Type: new Abstract: In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT). We demonstrate how it can be used to encode objects in sequential data like consecutive chess positions into compact yet meaningful representations. The basic principle of the architecture is to mask large portions of a sequence of latent states, similar to BERT and MAE. Then, we apply a lightweight Predictor to the latent representations that repairs gaps in the sequence in a lower-dimensional embedding space akin to JEPA. Our experiments in the domain of chess show that the Encoder refines the board representations such that meaningful chess concepts emerge clustered in the latent space. Furthermore, reconstructions of the masked board states show that the model is able to reason about the piece movements without relying on costly reinforcement learning methods. Lastly, we find that the resulting representation space allows for quick and intuitive dissections of chess games by observing the game path trajectories in this semantically rich space.

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

AI-Driven Assessment of Human Tutors: Linking Training Performance to Real-Life Practice

arXiv:2606.18617v1 Announce Type: cross Abstract: There exist numerous tutor training platforms. However, few provide AI-driven training and evaluation for human tutors based on real-life performance. We present an AI-driven system that assesses both open responses during training and authentic real-life tutoring. Unlike platforms that only assess learning through online training or simulations, our system utilizes Generative AI (Gemini-2.5-pro) to analyze transcriptions of authentic tutoring, measuring the transfer of tutor skills to real-life application. Human tutors instructing students remotely in math (N=86) completed six scenario-based lessons, averaging a significant 7.4% learning gain. Using mixed-effects models across 405 session-to-lesson pairs, we found that training performance significantly predicted real-life transcript scores with an effect size of 0.25 SD. Model comparison (AIC/BIC) indicated averaging open response and multiple choice performance during training predicted real-life tutor performance best, although open responses were comparatively more predictive. Exploratory analysis showed that after training, tutors were significantly more likely to encounter pedagogical opportunities to apply their skills (61.1% to 68.9%) and demonstrated higher execution quality within those opportunities (65.5% to 68.1%). Interrupted time series analysis suggested that these tutor improvements were part of a gradual trend over time rather than an immediate intervention effect of training. We illustrate an AI-driven method to link tutor training with real-life assessment. In doing so, we contribute open datasets, AI prompts, and scoring rubrics to support transparency and reproducibility.

19.
arXiv (CS.AI) 2026-06-12

Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage

arXiv:2606.12767v1 Announce Type: new Abstract: Evaluating procedural reasoning in AI-supported learning systems requires question-answer datasets that are both learner-like and grounded in the instructional knowledge the system is expected to use. We study how TMK-based question generation strategies affect dataset quality for procedural and multi-hop reasoning. We compare three strategies: strict generation from Task-Method-Knowledge (TMK) models, transcript-first generation with post-hoc TMK filtering, and TMK-aware generation that combines transcripts with structured guidance. To evaluate generated items, we introduce a grounding validation framework based on closed-set evidence units extracted from TMK models. The framework measures whether answers are supported by the underlying representation, whether questions are self-contained, and whether they target multi-hop procedural reasoning. Across 23 instructional topics and 690 generated question-answer pairs, strict TMK generation achieves the strongest overall quality, with 96.5% grounded questions and 92.6% usable questions. Transcript-first generation produces more learner-like questions but more context-dependent or weakly grounded items, while TMK-aware generation yields high raw multi-hop coverage but lower grounding. These results show that procedural richness and natural phrasing do not guarantee representational grounding, motivating explicit representation-aware validation for evaluation datasets in AI-supported learning.

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

Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View

arXiv:2603.05573v2 Announce Type: replace Abstract: Scalable sequence models, such as Transformer variants and structured state-space models, often trade expressivity power for sequence-level parallelism, which enables efficient training. Here we examine the bounds on error and how error scales when models operate outside of their expressivity regimes using a Lie-algebraic control perspective. Our theory formulates a correspondence between the depth of a sequence model and the tower of Lie algebra extensions. Echoing recent theoretical studies, we characterize the Lie-algebraic class of constant-depth sequence models and their corresponding expressivity bounds. Furthermore, we analytically derive an approximation error bound and show that error diminishes exponentially as the depth increases, consistent with the strong empirical performance of these models. We validate our theoretical predictions using experiments on symbolic word and continuous-valued state-tracking problems.

21.
arXiv (CS.CL) 2026-06-16

Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations

In-context learning (ICL) is the standard method for low-resource classification, yet its efficacy in specialized domains remains largely unexplored. We address the challenge of classifying semantically complex, multi-party B2B conversations, where traditional ICL encounters significant limitations, especially as context length increases due to the concatenation of multiple few-shot examples. We introduce the \texttt{Call Playbook} dataset, featuring five classification tasks derived from real-world B2B conversations targeting core sales concepts. To bridge the gap between performance and practical utility, we propose novel knowledge extraction methods that distill verbose examples into compact, interpretable representations of structured classification criteria and precise task descriptions. Our approach achieves a 99\% reduction in token usage and improves macro-averaged AUC by up to 7\% over traditional ICL. Notably, it remains robust as context grows, unlike advanced token compression baselines which degrade by over 9 F1 points. Importantly, our framework enables direct refinement of classification logic, addressing critical needs for transparency, efficiency, and user interaction in real-world NLP applications.

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

Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks

arXiv:2606.19741v1 Announce Type: new Abstract: Neural Combinatorial Optimization (NCO) achieves strong performance, yet its black-box nature remains a key roadblock to deployment and scientific diagnosis. Standard interpretability tools, such as Concept Bottleneck Models (CBMs), are ill-equipped for NCO, whose decisions are dynamic, state-dependent, and lack proper concept vocabulary definition. To close this gap, we introduce Evolving Programmatic Bottlenecks (EPB), to our knowledge, the first framework for interpreting NCO policies by distilling black-box NCO models into human-readable program portfolios. EPB employs an LLM to autonomously evolve a bank of programs, where each program's per-step action distribution serves as the bottleneck. EPB works through an iterative framework: Block I fixes program bank capacity and introduces a hybrid textual-numerical gradient descent scheme that couples numerical gradients for student router updates and textual gradients for LLM-based program revision; Block II dynamically adapts bank capacity via fault-targeted expansion and redundancy pruning. Extensive experiments demonstrate EPB's effectiveness and broad applicability, where the distilled program portfolios largely match original performance. EPB also reveals that NCO behavior shifts across optimization stages and can be approximated as a composition of classic heuristic variants. Our work advances interpretable NCO and establishes EPB as a promising tool for interpreting sequential decision-making models.

23.
arXiv (CS.AI) 2026-06-17

Small Initialization Matters for Large Language Models

arXiv:2606.17945v1 Announce Type: new Abstract: Large language models provide a tractable system for asking how intelligence itself emerges, rather than only how LLMs can be engineered. Although progress is usually attributed to scale, data and architecture, we show that parameter initialization is a gene-like determinant of training and, in particular, of model capacity. Reducing the initialization scale consistently improves pretraining, with the largest gains on reasoning-demanding tasks. We identify two widely used empirical settings that restrain the advantage of small initialization, and show how relaxing them restores favorable scaling. We further uncover a critical initialization that balances the reasoning and training. Mechanistically, small initialization drives a distinct developmental trajectory: parameters first condense into low-complexity structures and later expand into richer representations, giving concrete form to the idea that compression is intelligence. Token-level analyses show that the gains concentrate on non-trivial, context-constrained predictions rather than all tokens uniformly. These results motivate a simple $\gamma$-initialization rule: expose initialization rage as an explicit knob and use small initialization by default, an almost cost-free intervention that improves pretraining and strengthens reasoning across model scales.

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

LearnOpt: Recovering the Latent Cognitive Structure of Standardized Examinations via Knowledge Graphs and Constrained Optimization

arXiv:2606.15349v1 Announce Type: cross Abstract: Standardized examinations are typically treated as uniform syllabus coverage problems. We argue they are better understood as adversarial systems with stable latent cognitive structures diverging systematically from official syllabi. We introduce LearnOpt, which recovers this structure from historical question papers and generates personalized, time-bounded study plans. Applied to nine years of NEET questions (2016-2024, n=1,496), LearnOpt builds an exam knowledge graph from LLM-tagged questions, extracts a five-category latent skill distribution, and formulates study planning as a knapsack-variant optimization over prerequisite-aware subgraphs with Bayesian Knowledge Tracing. Central finding: NEET's latent skill distribution is stable within a syllabus regime (consecutive-year KL divergence 0.004-0.032 for 2016-2021, non-significant under permutation testing) but shifts significantly with NCERT's 2023 syllabus rationalization: pooling 2016-2021 (n=1,072) vs 2023-2024 (n=392) gives KL=0.040 (p=0.0005), with Elimination/Negation questions rising from ~20-29% to ~31-35%. Latent structure, while not permanently stationary, is piecewise stable, with shifts detectable and attributable to curricular events. Within either regime, subject predicts skill profile more strongly than year. An optimization evaluation, using one real and two synthetic mastery profiles, shows the skill-weighted objective produces a modest but real reordering of recommended topics over a mastery-conditioned frequency baseline. Applying the pipeline to JEE Advanced reveals a profile dominated by Multi-concept Integration (80.9% vs. 33.3% for NEET), with a JEE-vs-NEET divergence (KL=0.505) exceeding NEET's largest cross-subject divergence: exam tier shapes latent cognitive structure more than subject, which shapes it more than time within a regime. Code, knowledge graph, and annotated dataset are released publicly.

25.
arXiv (CS.AI) 2026-06-24

BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents

arXiv:2605.06177v2 Announce Type: replace Abstract: Reproducing and comparing deep research agents today is hard: the same backbone evaluated on the same benchmark can report different accuracies across papers because the harness and tool registry differ, and integrating a new model into a comparable evaluation surface costs weeks of model-specific engineering. These are symptoms of a broader reproducibility problem in deep research agent research. Here, we introduce BioMedArena, an open-source toolkit that addresses this reproducibility gap and provides an arena for comparing deep research agents under a shared evaluation environment. BioMedArena decouples six layers of biomedical agent evaluation – benchmark loading, tool exposure, tool selection, harness mode, context management, and scoring – and exposes 166 biomedical benchmarks and 75 biomedical tools across 9 functional families. Adding a new model, benchmark, or tool can be accomplished with a few-line provider adapter. Beyond evaluation infrastructure, BioMedArena ships a library of high-quality reference components: 6 agent harnesses (including our proposed Mutual-Evolve) and 6 context-management strategies, any of which can be equipped on any backbone. Equipping these components substantially improves all 12 backbones; on each of 8 representative biomedical benchmarks, the best equipped backbone surpasses prior state-of-the-art (SOTA), by 15.01 percentage points on average. The toolkit, configurations, and per-task traces are available at https://github.com/AI-in-Health/BioMedArena.