// intelligence · research
AI Research Papers
Preprints and publications from arXiv, Berkeley AI Research, MIT, Google Research, and leading academic institutions worldwide.
500 papers · showing 20
MilleMiglia: A realistic instance generator for middle-mile logistics
Algorithms & Theory
A new chapter for MIT Reads
A new focus on fiction and memoir aims to help the MIT community celebrate the power of storytelling and strengthen social connection.
BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research
arXiv:2609.19180v1 Announce Type: cross Abstract: Language models face unique challenges in analyzing interdisciplinary scientific research literature. In biophysics research, faithful answers require grounding observed data in source evidence, interpreting it through a quantitative physics model, and linking it to a biological mechanism. To address this challenge, we introduce BioPhys-Bridge, a novel benchmark dataset for evidence-grounded scientific reasoning over biophysical literature. Each case contains evidence blocks, stable evidence IDs, quantitative values, units, equations, assumptions, mechanisms, and next decisions as grounding targets for question answering (QA) and retrieval-augmented generation (RAG). The initial release contains 500 cases, 1,517 agent-facing tasks, and covers six biological domains and nine physical model families, including three sparse families reserved for future expansion. We enforce strict quality gates for all cases in schema, evidence-integrity, quantitative-grounding, source-license, duplicate, unit-normalization, with domain expert review and annotation for 81 cases. Preliminary evaluations show that DeepSeek-V4-Flash obtain the highest evidence-ID $F_1$ score (0.360), followed by Qwen3.7-Max (0.316) and GPT-4o-mini (0.294). BioPhys-Bridge is an interdisciplinary benchmark for evaluating attribution, faithfulness, hallucination reduction, and biological experiment design with complex, multi-step scientific reasoning. Future works will increase the size and complexity of the dataset and perform comprehensive evaluations. Code and data are available in the GitHub repository and on Hugging Face.
Vertical Attenuation of Thermoremanent Magnetic Anomalies: Implications for Drone-Borne Archaeological and Shallow Geophysical Surveys
arXiv:2609.19349v1 Announce Type: new Abstract: Magnetic surveys are widely used in archaeology to reveal buried features by detecting variations in the Earth's magnetic field caused by past human activities. However, as sensor height increases, magnetic anomalies produced by subsurface sources weaken and broaden, posing challenges for both ground-based and aerial (UAV) surveys. This study quantifies that altitude-dependent loss of signal and spatial definition using a fully synthetic model of a uniformly magnetized circular kiln together with upward continuation of measured fluxgate data from the Storbekken 1 iron-production site in central Norway. The synthetic experiment shows that a 2 m diameter, 1 m thick magnetized cylinder buried 0.3 m below ground retains only about 11% of its near-surface (0.2 m) peak amplitude at 2 m sensor height and about 3% at 4 m. In the hybrid experiment, composite furnace anomalies of several hundred nanoteslas collapse to tens of nanoteslas by 2 to 3 m, while distinct lobes merge into broad, low-contrast features. The results show that UAV-borne magnetometry can remain effective for site detection and delineation at elevations where detailed intra-site morphology is already strongly degraded. For small or subtle archaeological targets, sub-metre to low-metre sensor heights provide substantially greater interpretative detail. Recent field evidence on UAV-system noise further indicates that practical detectability will depend not only on source-distance attenuation but also on platform configuration and acquisition strategy. The resulting attenuation curves and morphological observations provide transferable guidance for planning archaeological and shallow-geophysical UAV magnetic surveys.
Generative Query Suggestion via Intent Coverage and Query-Level Credit Assignment
arXiv:2609.19209v1 Announce Type: new Abstract: Generative query suggestion aims to enhance user engagement by anticipating user intents and recommending relevant follow-up queries. A central challenge is to generate slates whose individual queries are useful while the slate covers distinct intents. We propose an Intent-Driven Query Suggestion Framework with dual-stage optimization. First, intent-aware diversity modeling constructs intent-aligned supervised fine-tuning (SFT) data and uses an Intent-Aware Diversity Reward to optimize intent coverage. Second, query-level credit assignment routes individual quality signals to the corresponding query tokens while sharing a slate-level diversity signal across the slate. Experiments on a large-scale production dataset, including online A/B testing and offline evaluation, show improvements in click-through rate, query quality, and intent coverage.
Bounded curvature manifolds without Euclidean isometric immersions of bounded mean curvature
arXiv:2609.19168v1 Announce Type: new Abstract: For every integer $n\ge2$, we construct a smooth complete Riemannian metric $G_n$ on $\mathbb{R}^n$ with full curvature norm at most one and injectivity radius at least one for which no $C^2$ isometric immersion into a finite-dimensional Euclidean space has bounded mean curvature. In dimension two, bounded second fundamental form would give uniformly controlled finite Jacobian representations of the Laplacian of the conformal factor. We construct disjoint conformal blocks for which the curvature remains bounded while the finite Jacobian representation cost tends to infinity. Taking Euclidean products gives all higher dimensions. The result answers Yau's Problem~52 negatively under the stronger assumption of bounded full curvature.
Enhanced Emission and Two-Photon Interference of Lead-Vacancy Centers in Diamond Solid Immersion Lenses
arXiv:2609.19220v1 Announce Type: new Abstract: A negatively charged lead-vacancy (PbV-) center in diamond is a novel quantum system which can be operated at a high temperature above 4 K owing to its large ground state splitting. To unlock the quantum properties of the PbV- center, the enhancement of the fluorescence intensity is a key issue. Here, we demonstrate enhanced emission from PbV- centers by a factor of approximately 10 using solid immersion lenses (SILs) fabricated on rough diamond surface caused by high-temperature anneal over 2000{\deg}C. Resonant excitation reveals the narrow emission close to the transform-limited linewidth. Furthermore, we demonstrate two-photon interference using one single PbV- center in an SIL. This enhanced emission and indistinguishability will lead to further development of the PbV- center towards quantum network node applications.
Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes
arXiv:2609.19170v1 Announce Type: new Abstract: Emphatic temporal-difference learning (ETD) stabilizes the expected off-policy TD update and changes its projection geometry, but neither property determines constant-stepsize sampled dynamics. We construct an ergodic two-state counterexample in which the ETD mean map contracts while the sampled product has a positive top Lyapunov exponent. Regenerative-cycle analysis separates this sign from the infinite variance of the follow-on trace. We introduce regularized emphatic TD (RETD), a normalized first-order post-shock repair that leaves the trace and importance ratios unchanged, stores the emphatic TD signal in a leaky scalar state, and releases a delayed correction. RETD's raw equilibrium is an affine shift of the ETD equilibrium; single- and two-regularization readouts recover the ETD fixed point exactly. We prove almost-sure convergence for harmonic diminishing stepsizes and a conditional constant-stepsize moment-contraction result from a Markovian random-product bound. RETD has certified negative exponents on the two-state construction and one Baird point, whereas the positive Baird ETD sign remains numerical. Paired 10,000-run experiments validate both separations, fixed-point recovery, a nonmonotone stability region, and task dependence. RETD changes post-shock dynamics; it does not reduce the shared follow-on-trace variance.
Personalized Federated Hierarchical Gaussian Processes for Privacy-Preserving Modeling of Heterogeneous Distributed Systems
arXiv:2609.19337v1 Announce Type: new Abstract: We present Personalized Federated Hierarchical Gaussian Processes (pFedHGP) for probabilistic regression and classification when data are distributed across heterogeneous clients. Each client's latent function decomposes into (i) a shared global component, (ii) a client-specific deviation that shares the global kernel structure, and (iii) a flexible local residual. Sparse inducing-variable approximations and federated variational inference keep raw data local while the server synchronizes only low-dimensional statistics for the shared component. Full predictive distributions support uncertainty-aware decisions. In application studies, pFedHGP attains perfect fault classification in press tonnage monitoring using 13.77% of labeled cycles and recovers geographic zones in federated air-quality modeling without centralizing station-level time series. An Instantaneous Linear Mixing Model viewpoint links the hierarchy to multi-output Gaussian processes for correlated sensors.
Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data
arXiv:2609.19153v1 Announce Type: new Abstract: Empirical legal scholarship increasingly treats judicial text as data, and much of it still runs on sparse, interpretable pipelines -- TF-IDF features and linear classifiers -- because the textual feature is often the object of study, not merely a means to a prediction. Yet these pipelines inherit a chain of preprocessing defaults from mid-century information retrieval that were never validated against classification accuracy, the most entrenched being stopword removal. This study introduces an exhaustive single-word ablation that measures a preprocessing step's effect directly against the downstream objective, and applies it to stopword removal as the hardest case to dislodge. Matching Supreme Court Database labels to Caselaw Access Project opinion texts, it examines two binary tasks that bracket F1 headroom, ideological direction (no-removal baseline F1 ~ 0.68) and constitutional versus non-constitutional law type (~ 0.92), across 7,668 and 7,001 opinions. For each task the analysis approximates the best stoplist any expert could build, removing each of roughly 18,500 candidate words and measuring the effect directly. Three findings follow: generic stoplists in common use fall below the no-removal baseline in every test; even optimized stoplists are statistically indistinguishable from removing nothing; and meta-models trained on word-level features cannot predict which removals help, so list curation has nothing to target. The method generalizes to any inherited preprocessing default, and the result is a caution specific to interpretable legal text-as-data: a step that silently reshapes which features a model sees can distort the very doctrinal and ideological signal such research exists to recover. Leaving stopwords in place is a question of measurement validity.
4D Radar Perception Algorithms for Autonomous Driving: A Review
arXiv:2609.19216v1 Announce Type: new Abstract: Research on 4D millimeter-wave radar perception algorithms has flourished in recent years, extending from signal processing and object detection to semantic segmentation, motion estimation, occupancy prediction, and dynamic scene reconstruction. This review organizes the field according to the evolution of perception tasks and algorithms. It first introduces radar fundamentals, data representations, and quality-enhancement methods, and then reviews object-level perception, motion and localization, local and dense spatial perception, and dynamic scene understanding. Across these directions, we compare radar-only learning, multimodal fusion, and cross-modal supervision and knowledge distillation. Particular attention is paid to how elevation, Doppler measurements, and radar physical priors are exploited across tasks. We further summarize the task coverage, input data, annotations, and evaluation protocols of existing datasets, clarifying the empirical support for different research directions. Finally, we discuss the common challenges and future directions of 4D radar perception for autonomous driving. This review provides a task-oriented perspective on the transition from sparse object perception to dynamic spatial understanding.
Grasping by interconnection: robust closing motions from coarse object templates
arXiv:2609.19228v1 Announce Type: new Abstract: Dexterous robot hands must often grasp objects whose shape, size, and pose are known only approximately. Grasp planners typically require accurate object models or correct errors with feedback, but how much inaccuracy a closing motion can tolerate on its own remains unclear. To address this question, we designed a motion planner based on four principles: a coarse template of the object, human grasp types, an object-centric interaction, and compliant, sliding contacts instead of prescribed contact points. This paper presents the planner, implemented through virtual model control, and its evaluation on a Shadow Dexterous Hand. Without feedback, the planned closing motions tolerated size errors of about 1cm and pose errors of several centimeters and tens of degrees, a wider range than a state-of-the-art data-driven planner in 25 of 27 tested conditions. They also grasped 82.5% of 80 everyday objects and succeeded within an autonomous pipeline. Robustness can thus be designed into the closing motion itself, rather than left only to feedback. This planner opens a path toward reliable manipulation in uncertain settings, which we will pursue by combining it with adaptive feedback control on the physical hand.
What Do We Expect from LLMs? Mapping the Design of LLM Benchmarks
arXiv:2609.19182v1 Announce Type: new Abstract: Benchmarks are central to how progress in large language models (LLMs) is assessed and communicated. Yet model rankings alone reveal little about how evaluation requirements themselves are changing. The expanding variety of benchmarks offers another perspective: what researchers expect LLMs to do, and what they count as successful performance. We systematically map 14,767 papers introducing or updating evaluation resources from arXiv submissions between January 2022 and August 2026. Using staged screening and automated full-text coding, we examine changes in target systems and domains, evaluation materials and conditions, and scoring mechanisms. The collection shows growing emphasis on action, interaction, and professional applications, while established and newer design elements frequently coexist. Model participation also develops unevenly: LLM-based scoring grows within both agent and non-agent groups, whereas model-generated materials show no comparable sustained increase in recent cohorts. These findings illuminate how public research translates capability expectations into concrete tests and criteria for success. As AI participates in constructing tests, performing tasks, and judging responses, they also raise a question: does expanding evaluation provide more independent evidence, or risk reproducing the preferences and blind spots of its participating models?
Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry
arXiv:2609.19154v1 Announce Type: new Abstract: While Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns. To address this issue, we introduce Neo-Classic, an evaluation benchmark that combines a constructionist Out-of-Sample (OOS) dataset with a suite of reverse understanding probes. Unlike traditional benchmarks that rely on verification or generation over historical corpora, Neo-Classic comprises strictly metrical poetry authored by contemporary experts, reducing the possibility of direct retrieval. We evaluate state-of-the-art models, including Qwen3-Max, Gemini-3-Pro, and DeepSeek-V3.2, across five behavioral probes designed to test hierarchical constraint satisfaction. Our results reveal two primary limitations. First, a performance gap of 20 to 50 percent emerges when models transition from historical to contemporary texts. Second, models exhibit substantial difficulties in discourse-level ordering tasks, with standard accuracy remaining low (0 to 13 percent). Although expert-level guidance improves the performance of reasoning-enhanced models to 36 percent, a notable gap with human experts persists. These findings suggest that while current LLMs capture local formal patterns, they struggle with global hierarchical planning required for robust Linguistic-Aesthetic Reasoning.
FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA
arXiv:2609.19680v1 Announce Type: cross Abstract: Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafter. In practice, new SEC-filing questions repeatedly expose heterogeneous errors in period, entity, evidence use, and calculation. Existing self-improvement methods can turn failures into new behaviors, but offer limited control over where a correction should apply or which previously correct answers it may break. We therefore frame post-deployment improvement as controlled behavioral maintenance: recurring failures should become scoped skill patches, and each patch should earn deployment with- out introducing regressions. We instantiate this view in FINSKILLOPS, a multi-agent system for SEC filing QA. FINSKILLOPS derives reusable skills from evidence-grounded, typed failure diagnoses and governs them through targeted validation, protected-case regression checks, negative controls, and versioned replacement or retirement. Across six financial QA benchmarks, a single frozen skill registry achieves the highest verdict-weighted correctness and reference consistency among the evaluated systems. Evolved skills raise correctness from 3.70 to 4.55 on our enhanced benchmark. In a separate 12-round operational study, only six of 33 proposed skills are promoted, while the monitoring non-correct rate falls from 20.0% to 12.5%. These results establish controlled skill scope, admission, and lifecycle management as the foundation for reliable self-improvement.
Open ultrasound foundation model for robust segmentation and clinical measurement across heterogeneous settings
arXiv:2609.19230v1 Announce Type: new Abstract: Ultrasound is the most widely deployed imaging modality worldwide, yet clinical AI remains fragmented into narrow single-task models that fail when device, operator, or anatomy changes. Here we present SonoCorpus, an open resource unifying 456,963 images and 1,626,085 expert masks from 53 public datasets spanning 24 clinical applications and 17 countries, and SonoBase, an interactive segmentation foundation model pretrained on it. Across fifteen evaluation datasets introducing new organs, devices, operators, and geographies, SonoBase outperforms SAM2, MedSAM2, and the concept-promptable MedSAM3 on every dataset and matches per-dataset specialist models trained on the same data; on fully external data it exceeds the accuracy these baselines achieve on their own in-distribution benchmarks. Ejection fraction derived from its segmentations falls within inter-observer variability (6.63\% error), with fewer misclassifications at the defibrillator-candidacy threshold than either promptable baseline (13\% versus 18--42\%); fetal head-circumference (1.81~mm) and gestational-age (1.2 days) errors fall below inter-observer variability. Where a baseline fails outright, one in four test cases, SonoBase recovers a usable segmentation in 81\% of them, including on handheld probes operated by minimally trained users in two low- and middle-income countries (Sierra Leone and Tanzania). Five labeled examples can help the model adapt to a new setting, and the identical training protocol transfers well to newer models such as SAM3, locating the advantage in ultrasound-specific pretraining rather than any single architecture. To ensure reproducibility and enable the community to build on SonoBase as a platform, we release all checkpoints, optimizer states, data-split indices, deduplication hashes, and starter code.
What Do Current Systematic Generalization Tasks Miss? A Reasoning-Centered Analysis
arXiv:2609.19212v1 Announce Type: new Abstract: Systematic generalization, the ability to solve novel problems by recombining known atomic elements, is central to human intelligence but difficult to study rigorously under controlled settings. Existing studies therefore rely on simplifications such as approximately linear action composition, productivity-based tests, and action-explicit goals, which make systematic generalization easier to study but omit some essential aspects of this capability. To characterize what these simplifications miss, we adopt a reasoning-centered lens and introduce TranSGrid, a testbed that brings deductive, inductive, and abductive reasoning together within a unified task. Experiments with seven Transformers on 4,800 TranSGrid instances show that all models perform much worse on TranSGrid than on a held-out test set: the largest model solves 79.6% of the test set, but only 55.3% of TranSGrid and 15.8% of the hardest subset. The gap remains within the training length range, showing that productivity alone is not sufficient to evaluate systematic generalization. Additionally, we reintroduce the other two simplifications into TranSGrid: one variant makes actions compose almost linearly (reducing the inductive demand), the other makes goals action-explicit (reducing the abductive one). In both, solve rates return to roughly the test set level, showing that either simplification alone is enough to reduce TranSGrid to an ordinary held-out test set. Together, our results show that existing tasks reduce either or both of the inductive and abductive demands, and that comprehensively measuring systematic generalization requires a task that involves all three forms of reasoning.
WZPlanner: Safe End-to-End Path Planning for Autonomous Driving in Work Zones
arXiv:2609.19393v1 Announce Type: new Abstract: Work zones alter lane geometry through temporary traffic controls and closures that may be absent from on-board maps, challenging autonomous vehicle (AV) perception and planning. Generalization is also limited by scarce public datasets with structured geometric supervision. We present WorkZonePlan, a dataset comprising 149K+ synthetic and 5K+ real-world multimodal samples with 3D annotations for lane boundaries, work zone boundaries, and driving trajectory options. It also provides 76 closed-loop CARLA scenarios replayed under three weather conditions, yielding 228 Bench2Drive-format evaluation routes. We introduce WAVE (Work-zone-focused AV data generation in Virtual and rEal Environments), a semi-automated pipeline for creating the dataset, and BoundaryFormer (BF), a transformer-based model that jointly predicts lane and work zone boundary polynomials and driving trajectories. BF uses slot attention for boundary prediction. Ablations show that a separate trajectory decoder using boundary slot features substantially improves trajectory prediction over a slot-attention-only approach. Building on this finding, BF++ offers Camera and Camera+LiDAR variants with metric ground-plane encoding, typed boundary/trajectory queries, long-range point anchors, image-space curve refinement, and conservative gated LiDAR fusion. On the 211 routes common to all four models at the evaluation freeze, BF++-Camera and BF++-Camera+LiDAR achieve Driving Scores of 63.0 and 64.4, respectively, compared with 59.3 for SimLingo and 26.1 for TransFuser++ (TF++). BF++ is 40 times smaller than SimLingo and more than 10 times smaller than TF++, while achieving higher Driving Scores. These results support jointly predicting lane boundaries, work zone boundaries, and driving trajectories as a promising direction toward safer AV operation in work zones. Code and dataset: https://github.com/Nishad-Sahu/WZPlanner.
Randomized SVD Approximations for Spectral Co-Clustering of Word-Document Matrices
arXiv:2609.19243v1 Announce Type: new Abstract: Spectral co-clustering is a useful tool for discovering latent structure in word-document matrices, but its reliance on singular value decomposition (SVD) can make standard formulations expensive on high-dimensional data. This paper presents two randomized approximations for normalized spectral co-clustering of bipartite text data when the numbers of document and word clusters may differ. The first method uses randomized SVD through random projection, while the second combines partial SVD with element-wise random sampling. Across real-world and synthetic datasets, both methods reduce runtime relative to the full-SVD baseline, but their behavior depends on matrix sparsity. The random projection method is the more reliable approximation across the tested settings, whereas the sampling-based method is most useful on denser matrices and provides limited benefit on already sparse text data. These results show that randomized approximations for spectral co-clustering should be selected according to the underlying structure of the data.
Characterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responses
arXiv:2609.19244v1 Announce Type: new Abstract: Conversational LLM agents increasingly rely on Web search, yet the end-to-end lifecycle of agentic search remains poorly understood. We present the first study of Web search across four major conversational platforms (ChatGPT, Claude, Grok, and DeepSeek), combining real-world user interactions (invivo) with controlled experiments using the same platform's models by their APIs (invitro). We investigate the quality of agentic decisions to invoke Web search, their strategies to formulate queries, the potential domain preferences in the search results they receive, and the choices they make when transforming search results into grounded responses. We find that Web-search decisions vary substantially across platforms and models, while more frequent Web-search invocation does not necessarily yield better response quality. We further show that conversational agents employ different complex querying strategies and that platform specific search engines return search results from their preferred domains. Finally, although responses are largely grounded in search results, some claims rely on uncited search results, raising concerns about attribution and reliability. Our findings have important implications for the design of future AI agents and Web search tools optimized for conversational retrieval.