General Relativity and Quantum Cosmology
Holographic dark energy from generalized entropies and extended infrared cut-offs
Ke Chen, Simone D'Onofrio, Sergei D. Odintsov et al. (+1 more)
We study
holographic dark energy models constructed from generalized
entropy functionals and local infrared cut-offs. Three
entropies (Barrow and the three and five-parameter generalized
entropies) are each combined with the Granda-Oliveros (GO) cut-off and two extensions, one adding a $\gamma H^{-2}$ term and one a $\gamma \ddot{H}/H$ term, the latter raising the dark-energy
evolution equation to second order. The nine resulting models are constrained against DESI DR2 BAO, Pantheon+ and a Planck compressed CMB likelihood through an MCMC analysis, and compared using the Akaike and
Bayesian information criteria. The Hubble constant is stable across all models. The $H^{-2}$ term is unconstrained in every case, as it becomes relevant only in the far future, and never improves on the GO cut-off. The $\ddot{H}/H$ term, instead, is tightly constrained for Barrow and $S_5$, where it improves the fit substantially, but not for $S_3$. The best fit is obtained for Barrow
entropy with the $\ddot{H}/H$ cut-off, yet the Barrow exponent remains compatible with zero in all cases. The data thus favour a higher-order infrared cut-off, while showing no significant evidence for a departure from the Bekenstein-Hawking area law. We also investigate the dark energy equation of state (EoS) of $S_3$ and $S_5$, discovering quintessence-like behavior and phantom crossing.
Read the full abstract ▾
All authors Ke Chen, Simone D'Onofrio, Sergei D. Odintsov, Tanmoy Paul
Theoretical Economics
Singular Equilibrium and Selection of Narratives
David J. Jin
An
agent learns from data that many parameters of her model explain equally well. Berk's
theorem states that her belief concentrates on the parameters that best fit the data, but does not select between them. We show that, with a continuum of parameters, the posterior concentrates on the best-fitting parameters with the smallest local learning coefficient. We propose a definition of narratives, subsets of the best-fitting parameters on which the learning coefficient is constant. Narratives are characterized by the number of coincidences they require (complexity) and how exactly each must hold (robustness). When the
agent's actions affect her data, every long-run action is a singular
equilibrium, a best reply to a belief supported on the least complex and most robust narratives. Singular
equilibrium refines Berk-Nash and self-confirming
equilibrium by restricting overly complex or knife-edge off-path beliefs, and its strict uniform version characterizes uniformly stable actions.
Read the full abstract ▾
Information Theory
From an entropic inequality for sums in abelian groups to the theorems of Ruzsa and Plünnecke
Chandra Nair, Aref Namayandeh and Zhaobang Zhu
We give a direct information-theoretic proof of the Plünnecke–Ruzsa inequalities for finite subsets of abelian groups. The argument rests on an elementary coupling inequality proved by maximizing joint
entropy, without tensor powers or asymptotic constructions. It also yields Ruzsa's sumset triangle inequality and an extension to non-abelian groups.
Read the full abstract ▾
Artificial Intelligence
AgentEvolver: System-Wide Self-Evolution Through Task Execution
Wentao Zhang, Fuchao Yang, Yilei Zhao et al. (+2 more)
An
agent can complete a task without improving how it works. Turning task experience into reusable capability requires connecting the changed component to its evaluation and subsequent use. We present AgentEvolver, a system for developing capabilities during task execution while keeping the foundation model fixed. Eight entity families expose reusable operations, methods,
agents, control flow, interfaces, and supporting state to revision through a common versioned lifecycle. A shared Runtime coordinates ongoing work, while persistent planning and recoverable context preserve task direction and supporting evidence. We evaluate task outcomes on SWE-bench Pro Public and examine capability changes in six application cases. The team reports an 82.08% resolution rate with
evolution, exceeding its reported baseline without
evolution. The cases show retained capabilities entering later website, game, and research work, while also documenting incomplete objectives and an unsuccessful strategy. These findings distinguish improvement in a reusable component from success on the final task. AgentEvolver provides a concrete basis for studying capability accumulation through execution; independent-task transfer and total development cost remain open questions.
Read the full abstract ▾
All authors Wentao Zhang, Fuchao Yang, Yilei Zhao, Xinrun Wang, Bo An
Computer Vision
PointVGGT: Zero-Shot Multiview RGB-D Point Cloud Registration with Visual Geometry Foundation Priors
Haobo Jiang, Liang Yu and Jianmin Zheng
This paper addresses multiview RGB-D point cloud registration, aiming to estimate global rigid poses for unordered RGB-D scans and align them in a metrically consistent coordinate frame. The conventional pairwise-then-global paradigm suffers from locally optimized pairwise registration, severe error propagation and high computational burden. In particular, existing methods typically treat RGB data as a mere auxiliary matching cue and overlook the holistic
geometric priors (e.g., camera poses and 3D models) encoded across image sequences. This paper introduces PointVGGT, a zero-shot framework built upon a novel foundation-then-refinement paradigm that systematically leverages visual geometry foundation models (e.g., VGGT) as the computational backbone for robust, training-free multiview RGB-D registration. In the foundation stage, we directly recover metrically consistent global poses (without any pairwise estimation) by grounding the scale-ambiguous pose predictions of the foundation model against metric depth observations. In the refinement stage, we introduce an efficient voxelized spatial hashing mechanism that exploits the globally coherent 3D reconstruction (induced by the foundation model) as a shared spatial anchor, enabling dense multiview correspondences in near-linear time. On top of this, an IRLS-based robust motion-only bundle adjustment is performed using a conjugate gradient solver to jointly minimize the correspondence and reprojection residuals for multiview pose refinement. Extensive experiments on indoor/object-centric/outdoor
datasets verify the outstanding zero-shot registration accuracy and computational efficiency of our proposed method.
Read the full abstract ▾
Mathematical Physics
Extended States on the Bethe Lattice Revisited
Vojkan Jaksic and Yoram Last
We give a short proof of the classical weak-disorder result that the Anderson model on the Bethe
lattice has purely absolutely continuous spectrum on compact intervals in the interior of the free spectrum. This note continues [6], where we gave a minimal proof of the existence of a nontrivial absolutely continuous component using the cyclicity criterion of [8]. There, Hellinger overlap yields the required non-cyclicity. Here, a stability argument for the forward Green function, followed by the zero–one law for the tree recursion, yields positivity of its boundary imaginary part. This positivity already gives absolutely continuous spectrum throughout the interval; the structural result of [7] excludes singular spectrum and yields purity. We also observe that the same structural argument shortens the final passage from boundary positivity to purity in the recent OpenAI preprint on the weak-disorder Anderson model on $\zz^d$, $d\geq3$ [10].
Read the full abstract ▾
Computer Vision
Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence
Yuchen Yang, Xin Wang, Lufan Wang et al. (+3 more)
Generating ultrasound reports from multiple images requires aggregating clinical evidence across views, yet archived key frames capture only part of the dynamic examination. Raw-report imitation is therefore misaligned with visual supervision: content that is clinically valid for the full examination may be unverifiable from the images available to a model. This gap creates a clinical behavior
alignment problem. A model must preserve visible findings, avoid diagnostic reversals and unsupported completion, and not collapse into conservative templates. We propose CAMEO, a Clinically Aware Multi-image Evidence-grounded Orchestration framework for ultrasound report generation. Stage I learns ultrasound visual-
language primitives; Stage II performs Cross-View Evidence Grounding by distilling trusted visible report points into multi-image QA and report-style supervision; and Stage III performs Clinically Aware Preference
Alignment using clinical-error-oriented preference pairs. From USReport, we construct USReport-Distilled with 17,670 evidence-grounded paired-image training instances and USReport-Pref with 21,869 preference pairs; we additionally use 25,631 PubMedVision-US ultrasound instruction samples for domain adaptation and multi-image instruction tuning. On the primary USReport-Distilled
benchmark, CAMEO improves over EchoVLM from 0.25 to 0.40 BLEU-1, 0.28 to 0.45 ROUGE-1, and 0.27 to 0.43 METEOR, while raising ClinicalScore from 55.02 to 74.20. These results underscore the value of evidence-grounded supervision, clinically aware
alignment, and clinically structured evaluation for reliable ultrasound report generation.
Read the full abstract ▾
All authors Yuchen Yang, Xin Wang, Lufan Wang, Yinghong Pan, Yujuan Feng, Yuqing Yang
Information Theory
Three Improved Lower Bounds for Binary Error-Correcting Codes
Kazuki Ota, Takayuki Osa and Tatsuya Harada
Error-correcting codes are a foundational technology for representing information robustly against noise in communication and data storage. The binary code packing problem, which seeks to maximize the number of codewords at a fixed code length and minimum distance, is a fundamental problem in coding theory that remains open for many parameter choices. We give explicit binary codes with parameters $(n,M,d)=(22,84,9)$, $(24,196,9)$, and $(25,65,11)$, where $n$, $M$, and $d$ denote the code length, number of codewords, and minimum distance, respectively. These establish the lower bounds $A_2(22,9)\ge84$, $A_2(24,9)\ge196$, and $A_2(25,11)\ge65$, where $A_2(n,d)$ denotes the maximum possible number of codewords, improving the respective lower bounds 80, 192, and 64 in the public table of general binary codes. Most notably, the third result improves the lower bound supplied by a lexicographic construction for the first time in 66 years, while the first two improve bounds that have stood for 21 years. The new codes represent more messages without changing the code length or error-correction guarantees, with gains compounding multiplicatively across blocks. We release all codewords and an exhaustive verifier to enable independent verification.
Read the full abstract ▾
Computer Vision
S$^3$Geo: Structure-Semantic Synergistic Learning for Cross-View Geo-Localization
Ziqian Mo, Hill Zhang, Haosheng Tan et al. (+2 more)
Cross-view geo-localization (CVGL) aims to estimate geographic locations by matching images captured from different viewpoints, such as drone and satellite views. Existing methods mainly rely on visual representations, but often fail to jointly model fine-grained structural correspondences and semantic priors, making them prone to confusion between visually similar but semantically different regions, and thus limiting robustness under large viewpoint variations. To address these challenges, we propose \textbf{S$^3$Geo}, a structure-semantic synergistic learning framework for cross-view matching. Specifically, we first introduce a Decoupled Query Pooling (DQP) module to extract a compact set of region-aware features from dense
tokens, enabling explicit modeling of local structural patterns. We then design a query-level contrastive learning scheme with an optimal transport (OT)-based formulation to establish soft correspondences under cross-view spatial misalignment. Furthermore, we incorporate a Semantic Knowledge
Distillation (SKD) strategy from a frozen CLIP teacher to transfer semantic priors and relational structures, thereby improving discrimination on hard negatives. By operating synergistically, the semantic priors provide robust contextual filtering, which guides the structural module to establish precise spatial
alignments. Experiments on the University-1652 and SUES-200
datasets demonstrate that \textbf{S$^3$Geo} consistently outperforms state-of-the-art approaches without increasing inference complexity, validating the effectiveness of jointly modeling structural and semantic information for CVGL.
Read the full abstract ▾
All authors Ziqian Mo, Hill Zhang, Haosheng Tan, Ling Li, Jiaheng Wei
Quantum Physics
Remote nonreciprocal magnon magnon entanglement via the Barnett effect with coherent feedback
Jinhao Jia, Yingyu Li, Ran Liang et al. (+3 more)
We propose a scheme for generating and controlling remote nonreciprocal
magnon–
magnon entanglement in a cavity magnonic system with coherent feedback.The two microwave cavities are driven by independent single-mode squeezed
vacuum fields, with a rotating YIG sphere in the left cavity and a stationary one in the right cavity. For a fixed rotation direction, reversing the bias
magnetic field applied to the rotating sphere changes the sign of the Barnett shift, leading to nonreciprocal
magnon–
magnon entanglement. By tuning the cavity detuning and feedback phase,
entanglement can be generated for one direction of the bias
magnetic field while it vanishes for the opposite direction, yielding complete nonreciprocity. Coherent feedback enhances the
entanglement at an appropriate reflectivity, whereas stronger feedback can reduce it. The relative squeezing phase provides additional control, and an appropriate choice of unequal squeezing factors improves the
entanglement at fixed total input
photon occupation. With the squeezed inputs kept fixed, moderate feedback also increases the critical temperature for
magnon entanglement.Our results provide a controllable approach to preparing remote nonreciprocal
quantum correlations in cavity magnonic systems.
Read the full abstract ▾
All authors Jinhao Jia, Yingyu Li, Ran Liang, Qinghua Cai, Xin Wen, Mei Zhang
High Energy Astrophysical Phenomena
Radio Continuum Study of One of the Brightest Large Magellanic Cloud Supernova Remnants N 132D
Rami Z. E. Alsaberi, Zachary J. Smeaton, Miroslav D. Filipovic et al. (+5 more)
We present a new
radio continuum study of the Large Magellanic Cloud
supernova remnant N 132D using observations from the Australia
Telescope Compact Array (ATCA) and MeerKAT. The
radio morphology shows a clear spatial correlation with the X-ray emission in the central and left regions of the remnant, as well as in the right portion of the shell, indicating a close connection between the thermal and non-thermal
plasma components. Polarisation measurements reveal predominantly radial
magnetic fields, with mean fractional polarisations of 1.2 per cent, 3.0 per cent, and 4.0 per cent at 2100, 5500, and 9000 MHz, respectively. There is also a complex structure in the Faraday Depth spectrum, showing a double-peaked profile that indicates regions with differing magnetisation properties or varying
magnetic field geometry. The rotation measure derived from ATCA data has an average value of ~2 rad m^-2, with a maximum of ~338 rad m^-2. We estimate a constant partition
magnetic field of ~90 microG and a minimum energy of 3 x 10^50 erg, which is in a constant partition between the energy density of electrons and the energy density of the
magnetic field. The integrated
radio spectrum follows a power law with a spectral index of -0.74 +- 0.01. These results provide new constraints on the
magnetic field structure and energetic properties of N 132D and offer insight into particle acceleration and shock
evolution in young
supernova remnants.
Read the full abstract ▾
All authors Rami Z. E. Alsaberi, Zachary J. Smeaton, Miroslav D. Filipovic, Roland Kothes, Hidetoshi Sano, Ahmed H. Abdullah, Dejan Urosevic, Sanja Lazarevic
Machine Learning
NanoProof: Open and Efficient Automated Theorem Proving in Lean 4
Matěj Kripner and Milan Straka
We introduce NanoProof, to our knowledge the first factorized execution-guided
theorem prover in Lean 4 whose training data, extraction tooling, training pipeline, and weights are all released, making it end-to-end reproducible using open-source resources. To this end, we build and release a
dataset of structured proof trees, as well as a tool for programmatic interaction and data extraction within the Lean 4 formal verifier. To support sustainable research, we focus on compute efficiency to facilitate accessible training and evaluation. NanoProof achieves 50.8% pass@16 on MiniF2F-Test, exceeding the two closest systems of its class, HyperTree Proof Search and ABEL, at roughly 90x and 7x less compute, and using more than four orders of magnitude less compute than AlphaProof. Stronger open-weight provers exist, but they are fine-tuned from large pretrained
language models and release neither training data nor pipeline; NanoProof shows that the factorized execution-guided class of provers can be rebuilt from scratch with modest resources.
Read the full abstract ▾
Analysis of PDEs
Some counterexamples concerning a model of eradication of invasive species
Stefano Bianchini and Chiara Trifone
In this note we study the regularity properties of the \emph{Effort Function $E(\beta)$}. This can be defined as the minimal $L^1$-norm of the control $\tilde \alpha(x) \geq 0$ so that the PDE $$U_t = \Delta U + f(U) - \tilde \alpha(t,x) U, \quad U \in [0,1], %\ \tilde \alpha \geq 0,$$ admits a traveling profile $U(x - \beta t)$ connecting $0$ to $1$. The above PDE models the
evolution of an invasive species, where the control $\tilde \alpha(t,x)$ describes the percentage amount of species removal. In the literature some conditions are assumed on the properties of $f(U)$ and (consequently) on the effort function $E(\beta)$, the main ones being that the traveling profile has a simple structure and that the effort function can be used as an anisotropic perimeter to generated a cost function over sets of finite perimeter. This note gives some examples showing that in the interesting cases, i.e. when the PDE has a non trivial dynamics, these assumptions are in general not satisfied. We also show that $E(\beta)$ is in general only $C^1$.
Read the full abstract ▾
Plasma Physics
Imaging ablator-fuel mix of hot spot in inertial confinement fusion via resonant X-ray absorption using an X-ray free electron laser
Lingen Huang, Long Yang, Alejandro Laso Garcia et al. (+44 more)
A novel diagnostic is proposed for active probing of doped inertial confinement fusion (ICF) spherical shells, enabling direct measurements of mix and burn dynamics at next-generation implosion facilities via resonant absorption imaging with an X-ray free-electron
laser (XFEL). The charge-state-sensitive imaging of embedded dopants provides spatiotemporally resolved constraints on ionization, opacity, and material mix seeded by hydrodynamic instabilities in stagnated
plasmas. Proof-of-principle experiments demonstrating resonant XFEL probing of hot spot in coated copper wires driven by an ultra-short relativistic
laser pulse, have established the feasibility of this approach. Furthermore, atomic and radiation-hydrodynamic simulations, combined with synthetic resonant X-ray absorption imaging, extend the diagnostic concept to
laser-driven direct-drive ICF shells with copper-doped ablators and radiation-driven indirect-drive shells with tungsten-doped ablators. This unique approach, combining a
laser-driven implosion facility with a high-brightness XFEL, could enable precise measurements of fusion-relevant hot dense
plasmas at multi-keV temperatures, provide stringent
benchmarks for radiation-hydrodynamics models, and advance the realization of inertial fusion energy.
Read the full abstract ▾
All authors Lingen Huang, Long Yang, Alejandro Laso Garcia, Oliver S. Humphries, Michal Šmíd, Mikhail Mishchenko, Victorien Bouffetier, Carsten Baehtz, Erik Brambrink, Samuele D. Di Dio Cafiso, Gabriel Pérez-Callejo, Yangzhe Cui, Thea Engler, Wen Feng, Sebastian Göde, Joerg Grenzer, Christian Gutt, Johannes Hagemann, Marie-Luise Herbert, Arthur Hirsch-Passicos, Hauke Höppner, Thomas Kluge, Dominik Kraus, Julian Lütgert, Masruri Masruri, Motoaki Nakatsutsumi, Özgül Öztürk, Paweł Ordyna, Xiayun Pan, Franziska Paschke-Bruehl, Alexander Pelka, Thomas R. Preston, Chongbing Qu, S.V. Rahul, Lisa Randolph, Martin Rehwald, Hans-Peter Schlenvoigt, Samuel Schumacher, Ulrich Schramm, Jan-Patrick Schwinkendorf, Georgiy Shoulga, Monika Toncian, Jan Vorberger, Karl Zeil, Ulf Zastrau, Toma Toncian, Thomas E. Cowan
Cryptography and Security
Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery
Li Lu, Yanjie Zhao, Hongjie Chen et al. (+1 more)
LLM
agents can spend millions of
tokens during vulnerability discovery without producing a working proof of concept (PoC). What consumes that budget, and why does it fail to produce results? We diagnose these costs and failures through a multi-axis open-coding study of 200 CyberGym traces, spanning four
agents (i.e., Codex, OpenCode, Cybench, and EnIGMA) under an unaided baseline and four existing efficiency methods. The study reveals three key findings. First, different
agents vary substantially in success and cost, and higher spending does not consistently yield better outcomes. Second, code localization and understanding, together with vulnerability
reasoning and trigger design, account for 60.4% of
tokens and represent the two leading bottlenecks in failed runs. Third, only 24.4% of matched comparisons preserve success at lower total cost; unsuitable signals and auxiliary overhead limit the benefits of existing methods. Motivated by these findings, we present AVRI, an
Agent-centric Vulnerability
Reasoning Interface built around a persistent Bidirectional Evidence Trace (BET). BET connects how the harness consumes input with the conditions required to make a selected operation unsafe, retaining source-supported correspondences alongside the
agent's hypotheses and open questions. Reading, analysis, and persistence commands help
agents build and reuse this evidence rather than repeatedly retrieve and reconstruct it. On 20 evaluation tasks, AVRI reduces total cost by 18.0% for Codex and 23.7% for OpenCode while preserving success rates and improving or maintaining recall.
Read the full abstract ▾
All authors Li Lu, Yanjie Zhao, Hongjie Chen, Haoyu Wang
Computers and Society
Political polarization and mental wellbeing: asymmetric evidence for bidirectionality
Afrooz Mahir, Shivam Sharma, Juhi Kulshrestha et al. (+2 more)
A growing body of evidence suggests that political polarization and mental health and wellbeing influence each other. Yet the two directions, how polarization shapes mental wellbeing and how mental wellbeing shapes polarization, remain siloed across disciplines. We review both literatures to evaluate the strength and
alignment of evidence for bidirectional effects. We find that the literature varies widely in constructs, measures, and levels of analysis, and that the evidence for the two pathways is asymmetric: links from polarization to mental wellbeing are more direct, grounded in well-developed theoretical frameworks and social-relational mechanisms. In contrast, the reverse pathway is substantially less direct, with studies often examining cognitive and socio-emotional factors, or political outcomes adjacent to polarization rather than polarization itself. We identify clear gaps in the literature highlighting the need for future studies with conceptual clarity, unified frameworks, validated measures, and multilevel designs examining both pathways within the same empirical and theoretical setting.
Read the full abstract ▾
All authors Afrooz Mahir, Shivam Sharma, Juhi Kulshrestha, Mikko Kivelä, Talayeh Aledavood
Artificial Intelligence
Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems
Jiaqi Liao, Yuanzhao Zhai, Huanxi Liu et al. (+5 more)
LLM-based multi-
agent systems (MASs) are increasingly used to solve complex tasks through coordinated
reasoning, tool use, and interaction with external resources. However, attributing failures in such systems remains challenging because the observed outcome often does not directly reveal the error responsible for the failed execution. In this work, the attribution target is the decisive error, defined as the
agent–step pair whose correction would recover the failed execution. Existing approaches largely identify suspicious steps without explicitly modeling how errors propagate across interactions or persist in unresolved loops, making decisive errors difficult to distinguish from downstream failure symptoms. We propose Error-Propagation Modeling for Failure Attribution (EMFA). EMFA constructs a structured representation of the failed trajectory, models both cascading propagation and persistent interaction loops, and uses propagation-aware candidate screening followed by counterfactual verification to identify the decisive
agent–step pair. On the Who&When
benchmark, EMFA achieves state-of-the-art step-level attribution accuracy and remains competitive at the
agent level. It improves the previous best step-level results by 3.45 and 4.40 percentage points on the Hand-Crafted and
Algorithm-Generated subsets, respectively.
Read the full abstract ▾
All authors Jiaqi Liao, Yuanzhao Zhai, Huanxi Liu, Xu Zhang, Zheming Zhuang, Dawei Feng, Bo Ding, Huaimin Wang
Computation and Language
Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing
Kazuki Nakajima and Takayuki Mizuno
Journals and conferences have begun to screen submitted manuscripts for text written using large
language models (LLMs). The reliability of this screening rests on
benchmark evaluations against a fixed set of LLM versions, while the versions in actual use keep changing. Here we quantify how this LLM turnover affects the screening of scientific manuscripts. We paired 4,000 pre-ChatGPT abstracts from the Proceedings of the National Academy of Sciences with their rewrites by 23 LLM versions from three vendors, released between June 2023 and August 2026. We then trained detectors under maintenance scenarios ranging from a detector retrained on every new version to one trained once and never updated. Detectors trained only on a vendor's past versions can collapse at the boundaries between model generations: calibrated to falsely flag 1% of human-written abstracts, they catch above 99% of rewrites just before the sharpest boundary and 3.8% just after it. Detectors trained on later versions can also miss rewrites of earlier ones. Vocabulary differences between versions largely track where detection transfers and where it fails. In the two screening scenarios we simulated, screens covering all 23 versions either flagged one in eight human-written abstracts or missed one in three rewrites of the newest version. Indeed, a commercial detector missed most rewrites of the version just after the sharpest boundary while flagging almost no human-written abstracts. Research-integrity policy should therefore treat the
benchmark accuracy of a detector as provisional, to be re-verified with every LLM release, including earlier versions.
Read the full abstract ▾
Information Retrieval
Overview of the NTCIR-19 Automatic Evaluation of LLMs 2 (AEOLLM-2) Task
Junjie Chen, Yuxi Dong, Haitao Li et al. (+2 more)
In this paper, we provide an overview of the NTCIR-19 Automatic Evaluation of LLMs 2 (AEOLLM-2) task. Building on the success of the NTCIR-18 core task AEOLLM, we proposed AEOLLM-2 for NTCIR-19 to further investigate automatic evaluation methods for Large
Language Models (LLMs), particularly in long-form text generation scenarios. In AEOLLM-2, we introduced a new subtask, Deep Research Evaluation, which focuses on the automatic evaluation of long-form deep research reports generated by LLMs. Participants developed evaluation methods to automatically assess the quality of these reports, and the performance of each method was measured by comparing its scores against human-annotated ground-truth labels. This year, we received 91 runs from 10 teams in total. This paper describes the background of the task, the
dataset construction, the evaluation measures, the participants' methods, and the final evaluation results.
Read the full abstract ▾
All authors Junjie Chen, Yuxi Dong, Haitao Li, Yiqun Liu, Qingyao Ai
Statistics Theory
Single-graph inference for fractal Gaussian networks
Chunhao Cai
We study inference on the strength of Gaussian multiplicative chaos from one
geometric graph with unobserved vertex positions. In the planar model, the edge-count statistic has a piecewise deterministic limit with a transition at $\gamma=1$, whereas degree
quantiles consistently estimate $\nu=\gamma^2/2$ throughout the subcritical range. Fractional moments give uniform finite-sample risk bounds. At finite resolution, common graph envelopes calibrate tests over continuous parameter boxes with unknown Poisson intensity. They give simultaneous coverage under adaptive refinement for a fixed statistic, and conditional coverage for an independently piloted size–degree residual on a fixed partition. For the exact periodic FFT–pixel approximation, we prove explicit total-variation rates for the annealed spatial Cox law and the observed graph law, uniformly on every compact subcritical range $0\le\gamma\le\Gamma<2$. The rates allow intensity to grow with resolution and imply uniform asymptotic coverage after recalibration at each resolution. Numerical studies examine parameter refinement, residual calibration, and multiresolution stability.
Read the full abstract ▾
Metric Geometry
On the Graph Corresponding to Center of Distances of Metric Space
Oleksiy Dovgoshey and Olga Rovenska
The center of distances $C(Y)$ of a metric space $(Y,\rho)$ is the set of all $t\geq 0$ for which the equation $\rho(y,p)=t $ has a solution for each point $p\in Y$. We say that a simple graph $CG_Y$ is the central graph of a metric space $(Y,\rho)$ if $Y$ is the vertex set of $CG_Y$ and distinct vertices $x,y\in Y$ are adjacent if and only if $\rho(x,y)\in C(Y)$. We prove the inequality $|E(CG_Y)| \geq \left\lceil \frac{1}{2}|Y| \right\rceil $ for all finite metric spaces $(Y,\rho)$ with $|Y|\geq 2$ and non-empty $CG_Y.$ It is also proved that the inequality $|E(CG_X)| \geq |X|-1 $ holds for each finite ultrametric space $(X,d)$. The central graphs of metric spaces $(Y,\rho)$ and ultrametric spaces $(X,d)$ satisfying $|E(CG_Y)|=\left\lceil \frac{1}{2}|Y| \right\rceil $ and, respectively, $|E(CG_X)|=|X|-1 $ are described up to graph isomorphism.
Read the full abstract ▾
Numerical Analysis
Quantitative finite-time approximation of scattering fields for Alfvén waves in ideal MHD
Junming Duan and Mengni Li
In this paper, we establish a quantitative finite-time approximation of scattering fields for nonlinear Alfvén waves in three-dimensional ideal incompressible magnetohydrodynamics near a strong constant
magnetic background. Using the global weighted estimates, we prove that truncating the scattering profiles at time $T$ introduces an error in both the $L^\infty$ norm and the $H^{N_*+1}$ norm of order $$ O\bigl(\varepsilon^2(R+T)^{-\delta}\bigr), $$ where $\varepsilon\in (0,1)$ measures the size of the initial perturbation, $R\ge100$ is the scale parameter in the weighted energy, $\delta\in(0,2/3)$ is the exponent related to weights, and $N_*+1$ is the Sobolev regularity order assumed for the initial data. The pointwise estimate follows from the decay of the nonlocal pressure along nonlinear characteristics, while the Sobolev estimate combines higher-order weighted pressure bounds with estimates for derivatives of the characteristic flows. Numerical experiments measure pointwise and Sobolev pressure-integral tails to verify the quadratic dependence of the initial perturbation amplitude.
Read the full abstract ▾
Symplectic Geometry
Kuranishi spaces in a category of fibrant objects and their homotopy fiber products
Taesu Kim
We study several fundamental properties of the category $\mathbf{Kur}$ introduced in \cite{Kim1}. By defining fibrations and weak equivalences, we show that morphisms with
manifold targets admit homotopy fiber products; this is then applied to obtain a notion of generalized intersections of two submanifolds. A definition of the Weinstein category in the context of Kuranishi spaces is also presented. Finally, we establish that $\mathbf{Kur}$ forms a category of fibrant objects in the sense of Brown \cite{Brown}, and discuss its homotopy category $\operatorname{Ho}(\mathbf{Kur})$.
Read the full abstract ▾
Software Engineering
Runnable Commit Untangling for Coding Agents
Jinfeng Jiang, Dongsun Kim, Dayi Lin et al. (+1 more)
Coding
agents produce large, tangled patches that mix multiple development purposes, making the code hard to review and maintain. Commit untangling offers the promise of organizing such large patches into untangled, manageable commits. This paper emphasizes two important limitations in existing commit untangling studies. First, they do not consider that untangled commits are ordered and should leave the code runnable. In practice, maintainers are unlikely to accept commits that prevent the code from running. Second, existing studies claim that commit untangling helps software maintenance. However, they conduct syntactic comparisons between the untangled commits and developers' original commits without directly showing the claimed maintenance benefits. To address these gaps, this paper makes two novel contributions: (1) RucTangle, the first agentic method that untangles commits while keeping the code runnable after each commit; and (2) TangleEval, the first evaluation framework that quantifies how untangled, manageable commit histories help coding
agents repair bugs. We compare RucTangle against four untangling methods on 131
agent-generated patches. All histories produced by RucTangle are runnable, while baselines produce 20.6%-37.4% unrunnable commit histories. We further collect 453
agent-generated patches that introduce regressions (i.e., causing previously passing tests to fail) and ask two other coding
agents to repair regressions. Augmenting
agent context with RucTangle-produced histories yields 5.2% absolute improvement in pass@1. We also analyze
agent trajectories to learn how they use untangled commits to navigate and fix bugs. Our findings demonstrate the value of adopting established software engineering practices in the era of coding
agents, which broaden the future research agenda: how can
agents actively use software history to make better development decisions?
Read the full abstract ▾
All authors Jinfeng Jiang, Dongsun Kim, Dayi Lin, Zhou Yang
Computation and Language
Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog
Hadeel Al-Negheimish, Jasna Ilieva and Yoon Kim
Current frontier LLMs can theoretically process long contexts with 1M
tokens or more. But to what extent can they go beyond simple
retrieval and perform deeper
reasoning over such long contexts? We empirically investigate long-horizon
reasoning capabilities of LLMs, focusing on deductive logic expressed in Prolog. We construct ProloNg, a synthetic testbed to probe Prolog Long
Reasoning, which systematically varies the complexity (
reasoning depth) of problems, where the hardest case has a
reasoning depth of 22 and 62k context length. We study 8
reasoning models across 5 families of frontier LLMs, and find that performance degrades substantially as
reasoning depth grows, with the majority of models approaching chance beyond depth 10.
Read the full abstract ▾
Robotics
Acting from Belief, Looking When Needed: A Bayesian Spatial World Model for Navigation under Intermittent Perception
Feihong Yang, Xiang Long, Jincheng Yu et al. (+4 more)
Robot navigation commonly uses wide-coverage, high-frequency sensing to reduce partial observability; this reliance becomes restrictive when another task temporarily redirects a shared sensor from
navigation, interrupting
navigation-relevant observations. We study
navigation under intermittent perception: acting from an internal spatial belief and looking again only when execution needs a new observation, potentially freeing the shared sensor for other tasks between
navigation observations. ALONE, a
Bayesian spatial world model, propagates a structured spatial belief using executed actions and corrects it with selectively acquired observations; learned priors over common
geometric structures infer unobserved structure from available observation history. It decodes the belief into a spatial estimate for the motion-planning module and predicts a reliability map expressing confidence in the estimate's accuracy. ALONE requests an observation only if insufficient reliability hinders
navigation and new evidence should make relevant-region spatial information more reliable; otherwise, it continues acting from the propagated belief. We instantiate ALONE for drone
navigation with intermittent single-camera depth images. Across two simulated scene families, it achieves 98% and 97% closed-loop success at a 10 Hz decision rate. Among successful trials, median fractions of decision steps requiring a new depth observation are only 0.9% and 1.3%, respectively, demonstrating high
navigation success with substantially reduced observation demand. Real-world indoor flight experiments further validate
navigation under intermittent depth observations, with all 10 trials successful.
Read the full abstract ▾
All authors Feihong Yang, Xiang Long, Jincheng Yu, Jianfei Zhang, Guangjun Ge, Chao Wang, Yu Wang
Human-Computer Interaction
NeuroDivSim: An Interactive Tool for Model-Based Reflection on Cognitive Diversity in Interface Design
Eske Beckefeld and Henrik H.J. Detjen
Recent approaches to simulated and synthetic users offer new ways to support design, but raise questions about how computational representations of users should contribute to design practice. We present NeuroDivSim, an interactive tool that explores simulation as an inspectable mechanism for reflecting on cognitive diversity during design and prototyping. Rather than using an LLM to act as a simulated user, NeuroDivSim uses generative AI to construct inspectable task, interface, and environment models from a usage scenario. After human review, these models are combined with explicit cognitive reference configurations and processed through deterministic simulation. This enables designers to hold a modeled usage situation constant while varying cognitive assumptions and tracing their consequences to interaction steps and rule-based design recommendations. We further report an exploratory pilot evaluation (N=10) that provided formative insights into how participants engaged with the workflow and informed subsequent refinements to the presentation of models, simulation results, and recommendations.
Read the full abstract ▾
Networking
An Experimental Evaluation of Scheduled Transmission and Hardware Timestamping on the Intel E830 NIC
Takahiro Hirofuchi
High-precision packet transmission is increasingly important in deterministic networking applications, including 5G fronthaul and Time-Sensitive Networking (TSN). Some recent high-speed network interface cards (NICs), including the Intel E830 and NVIDIA ConnectX series, support hardware-assisted transmission at specified times and hardware timestamping of received and transmitted frames. Despite the relevance of these capabilities to the stringent timing requirements of 5G fronthaul, little public information is available on their timing accuracy and performance characteristics. As a companion to our previous study of scheduled transmission on the NVIDIA ConnectX series, this paper experimentally characterizes the scheduled transmission and hardware timestamping capabilities of the Intel E830 NIC. Using an FPGA-based measurement platform with deterministic frame generation and nanosecond-resolution timestamping, we evaluate receive and transmit hardware timestamping and scheduled-transmission accuracy. The results show only several-nanosecond timing variation in hardware timestamping. Receive timestamp-derived frame intervals showed a peak-to-peak variation of up to 6 ns, while the transmit timestamp comparison showed a residual range of 4.6 ns after clock-drift compensation. Approximately 99% of the observed frame intervals were within $\pm$300 ns of the target interval, with occasional outliers of up to approximately 2 us. These results indicate that scheduled transmission can support applications with timing requirements on the order of several tens of microseconds, such as 5G fronthaul, but may be insufficient for TSN applications requiring transmission timing accuracy on the order of a few to a few tens of nanoseconds.
Read the full abstract ▾
Astrophysics of Galaxies
Measuring radial flows in disc galaxies
Yi He, Filippo Fraternali, Pavel E. Mancera Piña et al. (+1 more)
Numerous theoretical studies suggest that gas
accretion from the intergalactic medium is essential to feed
star formation in
galaxies throughout
cosmic time. However, the mechanism of gas
accretion remains poorly understood, as direct evidence is lacking. In some models, gas
accretion is expected to take place in the outer discs of
galaxies, from where it should be transferred to the inner
star-forming discs through radial flows. Finding such flows and quantifying them, therefore, opens the possibility of inferring the detailed properties of the accreting gas. Unfortunately, detecting radial flows is challenging due to the large disparity between radial and rotational velocities. Additionally, the distortions in velocity fields produced by these flows resemble the effects of warped structures, further complicating their quantification. To address this, we have developed a new methodology to measure axisymmetric radial velocities in disc
galaxies. Relying on the 3D kinematic fitting software \texttt{$^{\rm 3D}$Barolo}, we have designed a dedicated workflow to measure axisymmetric radial motions in disc
galaxies and to obtain robust uncertainty estimates through a bootstrapping approach. We validated this approach using realistic axisymmetric mock
galaxies as well as a small sample of `observed' Milky Way-like
galaxies drawn from the TNG50 hydrodynamic simulation. These tests demonstrate that our method works well and is capable of overcoming the degeneracy between radial motions and warps. The TNG50
galaxies we analysed have large regions in their discs with non-axisymmetric inflows and
outflows, but they show, on average, no global trend of coherent radial flows.
Read the full abstract ▾
All authors Yi He, Filippo Fraternali, Pavel E. Mancera Piña, Enrico M. Di Teodoro
Materials Science
Achieving room temperature plasticity in TiO2 ceramics by flash processing
Xinghua Su, Zhenyu Li, Xufei Fang et al. (+3 more)
Ceramics are indispensable materials for modern engineering and high-technology applications. However, the intrinsic brittleness at room temperature can cause catastrophic failure and severely limit their widespread applications. Here, we report a flash processing (FP) method based on the coupling of electric and thermal fields to significantly improve the room-temperature plasticity of TiO2 ceramics with a large plastic compressive strain of 15.4% during micropillar compression. This large room-temperature plasticity is attributed to the proliferation of stacking faults and twin boundaries during the loading process, which may be assisted by the high concentration of oxygen vacancies introduced by the FP method. Our findings suggest that FP can be a simple and effective method for achieving improved room-temperature plasticity of ceramic materials through defect engineering.
Read the full abstract ▾
All authors Xinghua Su, Zhenyu Li, Xufei Fang, Wenjun Lu, Mengyao Wang, Peng Zhao