Peer Revenue Equity in science

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Sunday 30 August

Number Theory

Counting integral points near curves: an exposition

We give a detailed account of the recent work of Hickman and Srivastava on counting integral points in a $ \delta $-neighbourhood of a dilate $ q \mathcal{M} $ of a non-degenerate curve $ \mathcal{M} \subset \mathbb{R}^{n} $, $ n \ge 3 $. Our aim is expository: we simplify the proof, provide additional details, refine the statement of the theorem and provide calculations from a more fundamental perspective. We also formulate a new conjecture based on recent work of Chen, Seeger, Srivastava and Technau.
Read the full abstract

Statistics Applications

Scalable, Likelihood-Free Calibration of Ice-Sheet Models with Deep Diffusion Emulators and Feature Matching

The Antarctic ice sheet is a major source of uncertainty in future sea-level projections, and physical simulators such as the PSU3D-ICE model are essential for studying its evolution. Calibrating them against observations is challenging: the simulator outputs and observed ice-thickness fields are high-dimensional, spatially dependent, and semi-continuous, with a large point mass at zero denoting ice-free regions. These features make conventional Gaussian-process emulation and likelihood-based calibration ill-suited and computationally infeasible at full resolution. We propose the sequential calibration method guided by a diffusion model and a Siamese network (SC-DS), a fully neural framework. For emulation, we develop a single conditional diffusion model that jointly generates the binary ice presence–absence pattern and the continuous thickness field, using global and local conditioning to represent how the input parameters shape the output. Because the emulator induces an intractable likelihood, our likelihood-free calibration replaces the hand-chosen distance and tolerance of approximate Bayesian computation with a probabilistic acceptance rule learned by an iteratively retrained Siamese network, together with a data–model discrepancy adjustment. Applied to the West Antarctic Ice Sheet, SC-DS matches the accuracy of state-of-the-art Gaussian-process calibration at a fraction of its computational cost and scales to the full-resolution domain, where existing methods become intractable.
Read the full abstract

All authors Kanghyun Wi, Jaewoo Park, Saumya Bhatnagar, Won Chang

Multiagent Systems

Harness-RL: Black-Box Reinforcement Learning with Action-Args Decoupling for Central-Agent Multi-Agent Harnesses

Large language model agents increasingly solve long-horizon tasks through multi-agent harnesses in which a central agent coordinates specialized sub-agents, tools, and environments. Training the central policy in such a harness raises two challenges. First, an action label is a low-cardinality decision, whereas its args form a high-dimensional conditional sequence; optimizing both with a shared sequence-level signal can produce conflicting gradients. Second, dynamic scheduling creates interdependent sessions with branches, parallel calls, and rewritten contexts, which cannot be faithfully reduced to one flat token sequence. We introduce Harness-RL, a structured reinforcement learning framework that combines Conflict-Aware Policy Optimization (CAPO) with interface-level black-box trajectory construction. The black-box component captures Interface Call Records, builds per-session prefix trees, and aligns outcome and process rewards with trainable tokens. CAPO uses forward activations to identify parameter partitions associated with action and args tokens, then routes their policy gradients to the corresponding subspaces. Harness-RL supports both central-only and joint multi-agent training. Across seven multi-hop question answering and agentic retrieval benchmarks, it reaches average F1 scores of 42.93 and 47.79 with Qwen2.5-1.5B and Qwen2.5-3B, respectively, while ablations validate the contribution of CAPO and favor central-only optimization in the evaluated setting. Our code is available at https://github.com/jiangxinke/Harness-RL.
Read the full abstract

All authors Xinke Jiang, Zhixin Zhang, Zhibang Yang, Jiaran Gao, Rihong Qiu, Shijin Chen, Xu Chu, Junfeng Zhao, Yasha Wang

Machine Learning

LLMODE: Aligning ODEs with LLMs via Gated Token Injection for Irregular Spatio-Temporal Forecasting

Large language models (LLMs) have shown promise for spatio-temporal forecasting, but existing approaches often rely on regularly sampled token sequences and struggle with irregular observations because of temporal asynchrony, representation-space misalignment, and limited context windows. We propose LLMODE, a token-efficient framework for irregular spatio-temporal forecasting with a frozen LLM backbone. LLMODE first uses a graph-aware ODE encoder to reconstruct irregular graph observations as a continuous-time latent trajectory. A Fixed-Budget Perceiver Resampler then compresses this variable-length trajectory into a fixed number of dynamic memory tokens. In parallel, compact statistical descriptors are encoded and resampled into context memory tokens. A dual-source gated cross-attention module injects both memories into the frozen LLM, enabling controlled utilization of external spatio-temporal evidence. Experiments on three real-world urban datasets and two physical-dynamics benchmarks show competitive overall performance, with clearer advantages under sparse or dynamically complex irregular sampling. Additional evaluations on unseen urban regions further demonstrate strong zero-shot generalization without adaptation.
Read the full abstract

All authors Di Zhang, Jingyang Zhang, Ziqian Wang, Chi Zhang, Yikun Ban, Ziwei Zhang, Ruijie Wang

Formal Languages and Automata

Finite-Monoid Compression in Syntactic Concept Lattices: Arity Hierarchies and a Pseudovariety Trichotomy

Clark's syntactic concept lattice (SCL) records two-sided distributional structure, and Wurm extended it to tuples of arbitrary finite arity. We study \(\operatorname{cmp}_f(L)\), the minimum image size of a finite-monoid observation that preserves guarded tuple substitution through arity \(f\) on the principal layer. For regular languages, we characterize \(\operatorname{cmp}_f(L)\) exactly as the least cardinality of the codomain of an \(f\)-separating relational morphism from the pointed syntactic monoid. Let \(\operatorname{ch}(\mathbf V)\) denote the least arity at which these compression numbers stabilize uniformly over a pseudovariety \(\mathbf V\). Our main result is the following trichotomy of possible uniform heights: \(\operatorname{ch}(\mathbf V)\in\{1,2,\infty\}\), with \(\operatorname{ch}(\mathbf V)=\infty\) if and only if \(\operatorname{Synt}(\{ab\})\in\mathbf V\). Thus no finite uniform compression height \(3,4,\ldots\) occurs. The infinite case is sharp: inside \(\langle\operatorname{Synt}(\{ab\})\rangle\), every boundary \(d\to d+1\) admits unbounded compression gaps, and arbitrary finite strict prefixes of the arity hierarchy are realizable. On the finite side, commutative monoids and bands stabilize at arity one, while every completely regular syntactic monoid stabilizes by arity two; finite group kernels show that the binary bound is sharp. At unary arity, every nonempty finite simple graph is realized by an explicit length-three language, yielding an exact chromatic-number formula and NP-completeness of deciding \(\operatorname{cmp}_1(L)\le 3\) for explicitly listed length-three languages. The structural boundary between compression heights one and two remains open.
Read the full abstract

Numerical Analysis

Tensor Orthogonal Subspace Split: Theory and Applications

Tensor representations have emerged as a fundamental paradigm for modeling multidimensional data by preserving intrinsic correlations across multiple modes. This paper proposes a novel theoretical framework, termed Tensor Orthogonal Subspace Split (TOSS), which explicitly splits a tensor, along a prescribed mode, into two orthogonal components: a dominant component lying in a prescribed subspace and a residual component lying in the corresponding orthogonal complement. We first present the general formulation of TOSS and systematically investigate its fundamental properties. As an important and practically meaningful special case, we further introduce the rank-one TOSS, which imposes a separable rank-one structure along the splitting mode and admits a clear geometric interpretation. This formulation naturally captures dominant consistent patterns while effectively isolating orthogonal residual component. The proposed framework establishes a unified theoretical foundation for tensor-domain orthogonal split and opens new avenues for structured tensor modeling across diverse applications. Building upon the developed TOSS theory, hyperspectral image restoration and color video background modeling are considered as two representative tasks, for which corresponding optimization models are formulated. Efficient algorithms are developed to solve the resulting problems. Extensive experimental results validate the effectiveness and superiority of the proposed approaches.
Read the full abstract

All authors Jifei Miao, Juan Han, Michael K. Ng, Kit Ian Kou

Astrophysics of Galaxies

Tracing Radial Migration in the Outer Disk: A Comprehensive Analysis of the Old Open Cluster Berkeley 36

We present a chemo-kinematical, structural, and photometric analysis of the old open cluster Berkeley 36 using Gaia DR3 astrometry and photometry together with high-resolution spectroscopy from the Gaia-ESO Survey DR5.1. Applying a Gaussian Mixture Model to Gaia astrometry, we identify 946 high-probability cluster members. We derive a core radius of 2.63 +/- 0.21 arcmin and a tidal radius of 14.84 +/- 0.47 arcmin, indicating a moderately concentrated and dynamically relaxed system. By fixing the cluster metallicity to the spectroscopic value of [Fe/H] = -0.19 +/- 0.02 dex and adopting an independently determined geometric distance of 4377 +/- 510 pc, we minimize the classical age-reddening-metallicity degeneracy and derive a robust isochrone age of 6.8 +/- 0.5 Gyr. Independent Ba-based chemical clocks yield a mean age of 7.75 +/- 1.94 Gyr, supporting the isochrone solution. The cluster exhibits a high main-sequence binary fraction of 48.0 +/- 1.7% and hosts 83 blue straggler star candidates with an extended spatial distribution, contrary to classical mass segregation. Orbit integration shows that Berkeley 36 follows a nearly circular orbit in the outer Galactic disc at R_GC = 11.42 +/- 0.44 kpc. Accounting for the Galactic warp and disc flare increases the cluster's maximum vertical excursion by 86% and the local disc scale height by 17%, respectively. Comparison with its chemically inferred birth radius at R_b = 6.71 +/- 0.66 kpc indicates an outward radial migration of approximately 5 kpc, predominantly driven by churning. These results establish Berkeley 36 as a benchmark for investigating radial migration, secular evolution, and the dynamical history of old Galactic open clusters.
Read the full abstract

All authors Deniz Cennet Ç{\i}nar, D. Bisht, Ing-Guey Jiang, K. Belwal, Selçuk Bilir

Number Theory

On the special values of Berndt's generalized $L$-function

In this paper, we study the generalized $L$-function considered by Berndt (1975). We introduce the generalized Apostol-Bernoulli polynomials and the generalized Apostol-Bernoulli functions, and establish some properties for them, including the Fourier series for these functions. We show that the values of Berndt's generalized $L$-function at integers are explicitly evaluated in terms of the generalized Apostol-Bernoulli functions.
Read the full abstract

Machine Learning

Unsupervised Multi-Scale Gromov-Wasserstein Hypergraph Alignment

We study unsupervised hypergraph alignment, where the goal is to infer node correspondences between two hypergraphs using only structural information, without node features, labels, seed matches, or side information. Direct higher-order formulations can represent hyperedge interactions faithfully, but they can be computationally demanding and cumbersome for non-uniform hypergraphs. Graph-reduction approaches introduce a different challenge: clique expansions keep the alignment problem on the original node set but collapse all hyperedge evidence into one pairwise graph, whereas bipartite expansions preserve incidence structure but enlarge the problem from nodes to nodes plus hyperedges. We introduce FALCON (Filtration-based hypergrAph aLignment via Cross-scale Optimal traNsport), an unsupervised optimal-transport framework for hypergraph alignment. Instead of representing each hypergraph by a single collapsed clique graph, FALCON constructs a filtration-induced sequence of clique-based co-occurrence dissimilarity matrices and jointly aligns all levels through one shared multi-scale Gromov–Wasserstein (GW) objective. The shared transport plan enforces a globally consistent node correspondence across filtration levels while avoiding the auxiliary hyperedge nodes introduced by bipartite expansion. Experiments on perturbation benchmarks derived from real-world hypergraphs show that FALCON is robust to structural noise and in almost all cases outperforms strong graph- and hypergraph-alignment baselines.
Read the full abstract

Rings and Algebras

Degree-shifted derived invariance of derived delooping levels

Gélinas introduced the delooping level of an Artin algebra as a homological invariant that bounds the big finitistic dimension of the opposite algebra. A natural question is whether such invariants are preserved under derived equivalences. Chen recently showed that the finiteness of the classical delooping level and its sub-derived variant is not derived-invariant, but the case of the finer derived delooping level of Guo and Igusa remained open. In this paper, we prove that the finiteness of the derived delooping level is degree-shift invariant under derived equivalences: if two algebras are derived equivalent via a tilting complex of width $k_T$, then finiteness of the $(k+k_T)$-derived delooping level on one side implies finiteness of the $k$-derived delooping level on the other. Consequently, the finiteness of the derived $\infty$-delooping level is invariant under derived equivalences. Furthermore, we introduce the global derived delooping level and prove that, under a derived equivalence, its $\infty$-version changes by at most $k_T$. In particular, its finiteness is a derived invariant.
Read the full abstract

Computational Engineering

QoI-Aware Provisional Rollout and Retrospective Reconciliation for Reduced-State Scientific Twins

Scientific twins may need to continue operating when updates from an authoritative primary system are temporarily unavailable. Once synchronization resumes, the new boundary can also be used to revise the intervening history. We distinguish an immediately available causal provisional trajectory from a delayed, future-conditioned reconciled trajectory. For reduced-state twins, we introduce a deterministic, calibration-based reconciliation method. A smooth temporal bridge carries the residual observed at the next synchronization block backward through the provisional interval. An analytic energy-matching stage then applies smooth regional gains and a global rescaling to match a component-energy trajectory estimated by cubic regression in log-energy space from synchronized frames on both sides of the gap. The method uses no additional correction network and revises decoded history without changing the latent state used for later rollouts. We evaluate 64 spatial patches from 16 JHTDB isotropic-turbulence slices for both velocity components and gaps S in {4, 6, 8}. During the longest gap, field error and gradient-sensitive QoI error degrade at markedly different rates, so field error alone does not characterize provisional fidelity. At S = 8, full reconciliation reduces window-averaged NRMSE by about 60% for both components and global gradient-intensity error from 4.21% to 2.91% for vx, whereas future-aware physical interpolation reaches 20.40% on the same metric. Energy matching additionally makes the reconciled history match its boundary-inferred global energy trajectory exactly. Future boundary information therefore substantially improves scientifically relevant properties within the evaluated regime.
Read the full abstract

All authors Liangji Zhu, Scott Klasky, Jaemoon Lee, Qian Gong, Anand Rangarajan, Sanjay Ranka

Software Engineering

InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information

Competitive programming is increasingly being used to evaluate the algorithmic reasoning capabilities of large language models (LLMs). However, existing benchmarks primarily focus on full-information tasks where all problem inputs are provided upfront. This overlooks a critical dimension of algorithmic reasoning: the ability of generated programs to operate when key information is not revealed upfront. Interactive problems, a distinctive component of competitive programming, embody this challenge. These problems require programs to engage in multi-round interaction with an interactor (a judge program) under strict protocol constraints and limited query budgets, with new information revealed only in response to queries. To address this gap, we introduce InteractBench, a benchmark comprising 322 high-quality interactive problems curated from Codeforces, AtCoder, IOI, and ICPC. Each problem is packaged with executable local interactors, enabling fully offline evaluation. Unlike existing benchmarks, InteractBench assesses whether model-generated code can acquire information and track state dynamically. Our evaluation reveals a significant interaction gap: even the most advanced reasoning models achieve limited success on interactive problems. Beyond success rates, we propose a fine-grained failure taxonomy to diagnose the root causes of these deficiencies. Although algorithmic logic errors remain dominant, protocol violations and query-budget overruns are frequent. Code is available at https://github.com/kmsgk0/InteractBench.
Read the full abstract

All authors Jiaze Li, Aocheng Shen, Bing Liu, Boyu Zhang, Xiaoxuan Fan, Qiankun Zhang, Xianjun Deng

Information Theory

Efficient Polynomial-Time Decoding of Simplicial Anticodes with Near-Optimal Performance

In this work, we propose an efficient decoding algorithm for codes arising from simplicial complexes, a family of binary linear codes for which no decoding method of this type was previously known. Although the algorithm does not always attain the maximum theoretical error-correcting capability, it provides an explicit bound that can be computed directly from the structure of the complex. Moreover, this bound is asymptotically optimal: the ratio between the guaranteed correcting capability and the theoretical maximum converges to $1$ as the code length increases, under natural assumptions on the dimension of the maximal faces. The correction capability is also presented in specific examples. Finally, we introduce specific families of simplicial complexes where the algorithm successfully reaches this theoretical bound.
Read the full abstract

Dynamical Systems

Existence and Stability of Dancing Equilibria in Asymmetric Kuramoto Networks

We study nonzero-frequency phase-locked motions in asymmetrically coupled Kuramoto networks. Such motions are relative equilibria with fixed phase differences and a nonzero common angular velocity, and we call them dancing equilibria. Their existence requires all coupling sums to have the same nonzero value. We show that neither symmetric coupling nor an acyclic associated digraph can support a dancing equilibrium. We introduce structurally equitable and $q$-twisted state equitable partitions and prove a partition-based criterion for the resulting class-constant profiles, with standard labeled $q$-twisted profiles recovered from singleton partitions. For the forward $m$-neighbor model, we characterize existence by an exact indivisibility criterion. Stability is studied modulo the common phase-shift direction. For general directed networks, strong connectivity and edgewise phase differences in $\left(-\pi/2,\pi/2\right)$ imply local orbital exponential stability and yield an explicit positively invariant set contained in the local basin of attraction. For arbitrary twisted indices, this contraction argument gives a low-winding stability regime with explicit positively invariant neighborhoods. For each existing $q$-twisted branch of the forward model, a discrete Fourier transform criterion yields local orbital exponential stability when all nonzero Fourier-mode factors are positive and nonlinear instability when at least one is negative. In the unstable case, the proof constructs explicit escaping real Fourier perturbations. We further derive additional explicit stability and instability ranges for arbitrary twisted indices in terms of constants $N$, $m$, and $q$. For the first two twisted branches, sharper arguments yield a first-mode transition criterion for $q=1$ and a complete finite-size classification for $q=2$, with the degenerate case in each branch handled separately.
Read the full abstract

Other Statistics

Statistical Leadership of What? Statistics After AI

Statisticians have spent over a century arguing that we are more than calculators, usually by pointing to what else we know. AI is making that defense harder, since the list of what only statisticians can do grows shorter with each model release. AI makes claims cheap to generate and may eventually make the statistics behind them cheap too. However, a model cannot be answerable in the way that statistical practice requires. Statistical leadership then becomes a question of which claims we are there to answer for, including the ones we answer for in advance by building judgment into systems.
Read the full abstract

Optimization and Control

Reciprocal-Manifold Annealed KKT Flows for Constrained Optimization: Application to the Nonconvex AC Optimal Power Flow

Safety-critical optimization applications, such as real-time power system operation, maintain feasibility at every intermediate step, not merely at convergence. Existing approaches either violate constraints mid-solve (interior-point methods) or enforce feasibility through per-instant quadratic programming subproblems with cubic computational cost and unbounded worst-case execution time. We propose a continuous-time optimization framework for smooth constrained nonlinear problems that preserves feasibility throughout the optimization process without requiring projection operators, quadratic programming subproblems, or other per-iteration optimization routines. The method is built around a reciprocal multiplier manifold, which establishes an explicit relationship between inequality constraints and their associated Lagrange multipliers. By designing a continuous multiplier update law, the manifold is shown to remain forward invariant, while the resulting dynamics are equivalent to continuous-time logarithmic barrier gradient descent. The proposed framework naturally extends to multiple inequality constraints, equality constraints, nonconvex feasible sets, and infeasible initial conditions. The method is further enhanced through an augmented Uzawa flow that eliminates oscillatory transients commonly observed in classical primal-dual saddle-point dynamics. The effectiveness of the proposed approach is applied to the AC Optimal Power Flow problem of IEEE 9-bus and IEEE 57-bus systems. Numerical results show convergence to solutions within 0.4% of the benchmark optimum while maintaining strict feasibility of all constraints. A computational complexity analysis shows that the proposed dynamics reduce the per-step computational cost from cubic to linear complexity. Finally, dynamic tracking studies under time-varying operating conditions demonstrate reliable feasibility preservation.
Read the full abstract

All authors M Parimi, Aditi Ramteke, Rachit Mehra, Arun Mahindrakar, Navdeep Singh

High Energy Physics (Theory)

Genuine Multi-Entropy in Abelian Chern–Simons Theory: Exact Key-Ring Collapse and Its Breakdown for Generic Link States

We study genuine multi-entropy in Abelian $U(1)_k$ Chern-Simons theory. For key-ring link states, where only the linking numbers between one distinguished component $K$ and the remaining $\mathtt{q}-1$ components are nonzero, we derive an exact closed-form expression for the $\mathtt{q}$-partite Rényi multi-entropy for general $\mathtt{q}$, level $k$, and Rényi index $n$. For $\mathtt{q}=4$, this shows that the genuine multi-entropy $\mathrm{GM}^{(4)}_n$ collapses exactly onto the tripartite information $I_{3,n}$ for all $n$, while for $\mathtt{q}=5$ it is likewise completely determined, for all $n$, by a linear combination of tripartite and bipartite Rényi multi-entropies. We then go beyond the key-ring class and study general four-component link states with arbitrary pairwise linking numbers. A numerical scan over Chern–Simons levels $2\leq k\leq24$ shows that the all-$n$ collapse found analytically for key-ring states does not survive for generic link states. Remarkably, the collapse remains exact at $n=2$ for every level examined. At $n=3$, violations occur, within the scanned range, only when $3\mid k$, with a further dependence on the $3$-adic valuation of $k$. At $n=4$ and $n=5$, violations occur for every level examined, with rates that vary strongly with $k$. These results show that the breakdown is not controlled simply by the zero-divisor structure of composite $\mathbb Z_k$, but instead exhibits a nontrivial joint dependence on the Rényi index and the arithmetic structure of the Chern–Simons level.
Read the full abstract

All authors Yen-Cheng Chang, Kaberi Goswami, Norihiro Iizuka, Akihiro Miyata

Computer Vision

SPLG-Mamba: Structure-Preserving Local-Global Mamba Network for Salient Object Detection in Optical Remote Sensing Images

Salient object detection in optical remote sensing images (ORSI-SOD) requires dense predictions that preserve object completeness and structural continuity under complex backgrounds, scale variation, and irregular object shapes. Existing methods often localize salient regions, but their predictions may still suffer from structural degradation, including fragmented, incomplete, or locally missing foreground responses. This degradation is closely related to hierarchical feature propagation, where shallow details can introduce texture-induced background responses, deep semantics may over-smooth weak structures, and uncontrolled cross-scale fusion can disturb coherent regions. To address this issue, we propose a novel Structure-Preserving Local-Global Mamba Network, SPLG-Mamba, for ORSI-SOD. Specifically, SPLG-Mamba integrates Smooth-Detail Recalibration (SDR), hierarchy-aware Local-Global Mamba, and Gated Cross-Scale Fusion (GCSF). SDR recalibrates smoothed responses and detail residuals before state-space modeling, Local-Global Mamba assigns local modeling to shallow feature levels and global modeling to deep feature levels, and GCSF controls cross-scale detail injection during decoding. Experiments on ORSSD, EORSSD, and ORSI-4199 demonstrate state-of-the-art results and improved structural completeness and continuity. The code is available at https://github.com/yxu9910/SPLG-Mamba
Read the full abstract

All authors Yi Xu, Ruichao Hou, Tongwei Ren, Gangshan Wu

Statistical Methodology

One-step group factor analysis via penalized least squares

In this article, we revisit the problem of group factor analysis and propose a one-step penalized least squares method to estimate the factor loadings and factors in large-dimensional group factor models, offering a distinct alternative to the conventional two-step principal component approach. Our procedure originates from the equivalence between the group factor structure and the carefully tailored identification conditions. Leveraging this insight, we develop a tricky Lagrange multiplier formulation for a penalized least square loss function. This one-step optimization framework, combined with the fine-tuned penalty parameters, facilitates the direct derivation of central limit theorems for factor loadings, factor scores, common and local components, as well as the convergence rates for them. Our theory demonstrates that our one-step approach achieves the same rate as the two-step aggregated principal-component method and even the same limiting standard error in the balanced group panel case, but smaller limiting standard error than the two-step canonical correlation procedure. Extensive simulation studies justify the theory. Applications to U.S. house prices and CSI300 weekly returns confirm that our method identifies global factors and heterogeneous local patterns.
Read the full abstract

All authors Xinbing Kong, Xiaoying Pan, Long Yu, Tong Zhang

Computation and Language

PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization

Natural Language Processing methods have enabled novel solutions and advances in the field of privacy, particularly in the sub-domain of text-to-text privatization, where the goal is to transform a sensitive input text into a privatized output by ideally masking (in)directly identifiable or otherwise private information. The evaluation of text-to-text privatization, however, is not straightforward, and the extant literature has utilized a myriad of techniques and metrics to quantify the privacy-preserving capabilities of privatization methods. Seeking to unify the evaluation of text-to-text privatization, we introduce PrivBench, a holistic and modular benchmarking platform for researchers and practitioners working on text privatization. PrivBench is holistic in that it evaluates privatization on a series of defined desiderata, which are structured into modules. PrivBench is not only modular but also extensible, allowing for future updates and benchmark versions. PrivBench is user-centered and promotes competition via real-time evaluation and a live public leaderboard. The platform is free to use and openly accessible at https://privbench.com/.
Read the full abstract

All authors Stephen Meisenbacher, Andreea-Elena Bodea, Ahmet Bilal Ak{\i}n, Alexandra Klymenko, Jana Diesner, Florian Matthes

Computation and Language

MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation

Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning. However, distilling such trajectories into smaller student models remains challenging: direct Long CoT supervision often provides limited gains and can be less effective than concise Short CoT rationales. In this work, we investigate this phenomenon from a gradient-centric perspective. Our analysis shows that Long CoT induces larger gradient magnitudes and more concentrated update directions than Short CoT, with this effect becoming more pronounced as student model capacity increases. These findings suggest that effective Long CoT distillation requires balancing the reasoning information density of reasoning trajectories with their distributional alignment to the student model. Motivated by this insight, we propose Model Interporlation Distillation (MI-Distillation), a framework that constructs a continuous Instruct-Reasoning data spectrum through model interpolation. To select suitable trajectories from this spectrum, we further introduce Sequential Learnable Surprisal Score (SeqLSS), which favors reasoning paths that are both informative and learnable for the student. Extensive experiments on reasoning benchmarks show that MI-Distillation consistently improves small model CoT distillation over strong Long CoT baselines.
Read the full abstract

All authors Yangsong Lan, Renkai Hu, HongKai Zheng, Bo Zhang, Renzhi Wang, Hongliang Dai, Piji Li

Multiagent Systems

AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requires adaptive retrieval and continuous revision of intermediate contexts. Recent reinforcement learning (RL)-based agentic RAG methods partially alleviate this issue, but typically rely on coarse-grained action spaces and trajectory-level rewards, resulting in weak reward assignment and a bias toward short-horizon, stereotyped reasoning template. To address, we propose AgenticRag-R1, a RL framework that deeply integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space, supported by hierarchical action-aware rewards and an information-aware trajectory rejection strategy to enable effective long-horizon learning. Experiments across a diverse set of multi-hop, open-domain, and agentic reasoning benchmarks, spanning multiple backbone model sizes, demonstrate that AgenticRag-R1 consistently outperforms strong baselines. Moreover, AgenticRag-R1 learns more robust, interpretable, and memory-aware reasoning behaviors, highlighting the effect of fine-grained action modeling and information-aware optimization for long-horizon reasoning. Our code is anonymous available at https://github.com/jiangxinke/Harness-RL/tree/AgenticRAG-R1-Whitebox.
Read the full abstract

All authors Xinke Jiang, Yue Fang, Zhibang Yang, Jiaran Gao, Zhixin Zhang, Tao Feng, Rihong Qiu, Wentao Zhang, Hongxin Ding, Ruizhe Zhang, Yongxin Xu, Yuheng Huang, Xu Chu, Junfeng Zhao, Yasha Wang

Computer Vision

CineForge: Self-Improving Agents for Long-Horizon Video Generation

Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt construction, rendering, and revision across interdependent scenes. Existing adaptive video systems primarily refine requests or reusable skills, leaving recurring production failures disconnected from persistent, stage-targeted improvements across stories. We introduce CineForge, a self-evolving video-production agent framework that couples CineForge-Produce for video generation with CineForge-Evolve for cross-story policy evolution. CineForge-Produce organizes each source story into typed narrative, character, spatial, and cinematic states, uses them to coordinate asset and clip generation, and records the process as a canonical production trajectory. CineForge-Evolve applies Case-to-Pattern-to-Policy Evolution (CPPE) to review trajectory evidence, consolidate recurrent findings into bounded stage-local patches, and deploy validated updates through structural replay and confidence-controlled paired evaluation. To measure complete story realization, we introduce CineScope, which combines a 100-script CineScope-Data suite with a human-aligned, multiscale CineScope-Metric spanning causal state, directorial orchestration, pacing and resource allocation, and character arc. Across CineScope-Data and two public benchmarks, the evolved CineForge policy improves CineScope-Metric from 4.024 to 4.380, outperforms three long-video baselines with consistent gains under ScriptAgent, and reduces review LLM calls by 37.0% on new stories. These results establish production trajectories as actionable experience for video agents that improve cumulatively across long-form storytelling tasks.
Read the full abstract

All authors Junxiang Liu, Lin Wang, Haiyu Shi, Hongxu Ma, Xiaoyu Yang, Chunjie Chen, Xiaoxiao Xu, Kaiqiao Zhan, Boao Wang, Shuizhou Shi, Tianyun Zhu, Jie Li, Jiangtong Li

Signal Processing

Robust Decentralized Multi-Satellite Massive MIMO Transmission via Knowledge Distillation

This paper investigates robust decentralized transmission for cooperative multi-satellite massive multiple-input multiple-output (MIMO) systems under imperfect statistical channel state information (sCSI). In the considered scenario, each satellite has complete access to its local information but receives partial information from other satellites due to limited inter-satellite links (ISLs), with only imperfect sCSI available. To address these challenges, we propose a knowledge distillation (KD) framework that transfers cooperative precoding knowledge from a centralized teacher neural network (NN) to lightweight decentralized student NNs. Specifically, a global-clean teacher, aggregating information from all satellites and accessing accurate sCSI during offline training, transfers its cooperative precoding knowledge to partial-noisy students, relying on complete local information, limited information exchanged by other satellites, and error-corrupted sCSI for local precoding. The teacher NN combines patch-wise self-attention with dual-axis attention to learn inter-user interference and inter-satellite coordination, whereas each student NN adopts a compact per-satellite architecture for efficient onboard inference. The teacher learns a high-quality weighted minimum mean square error precoding policy from global-clean inputs, which is then distilled into the students operating on partial-noisy inputs. To mitigate the resulting teacher-student performance gap, we develop a hybrid KD mechanism with explicit angle- and phase-error calibration. Simulation results demonstrate that the proposed framework significantly enhances the decentralized sum-rate performance and remains robust under diverse configurations.
Read the full abstract

All authors Wenjing Cao, Zheng Lin, Yafei Wang, Wenjin Wang, Ye Wang, Rui Ding, Symeon Chatzinotas, Björn Ottersten

Statistical Methodology

Adaptive Functional Clustering with Structured Dependence via Variational Inference

Functional clustering is an important tool for identifying latent heterogeneity in functional data and has been widely applied across various scientific fields. However, many existing methods are not fully adaptive, as they may require the number of clusters to be prespecified and may lack automatic control over the smoothness of the underlying functions. They also commonly assume independent and identically distributed errors, thereby overlooking additional within-curve dependence. We propose a fully adaptive Bayesian procedure for functional clustering that addresses these limitations through Dirichlet process priors, adaptive smoothness control, and flexible covariance modeling. For computational scalability, the proposed method employs variational inference as an efficient alternative to Markov chain Monte Carlo. Together, these features provide a unified Bayesian framework for functional clustering and cluster-specific mean function estimation in the presence of structured within-curve dependence.
Read the full abstract

Information Theory

Multi-Access Speculative Inference: Uplink or Downlink?

Multi-access speculative inference (Multi-SPIN) extends SPIN to multi-device edge networks to accelerate cooperative token generation. It allows on-device small language models (SLMs) to autoregressively draft multiple tokens for individual generation tasks, while an edge-server large language model (LLM) verifies them in parallel. The major communication overhead arises when a drafted token is rejected by the server, in which case sampling the correction token requires access to both the SLM-output draft distribution and the LLM-output target distribution over the full token vocabulary. Existing designs typically perform correction at the server by uploading the draft distribution, but transmitting a vocabulary-wide distribution creates a critical uplink (UL) bottleneck. Alternatively, the correction can be performed at the device by downloading the target distribution, leveraging the high transmission rates available on the downlink (DL). Motivated by this insight, we introduce communication-mode selection as a new design dimension for Multi-SPIN. Specifically, each device can adaptively switch between the UL and DL modes to balance the UL bottleneck against the shared DL resource constraint, thereby relieving the overall communication burden. We formulate a sum-token-goodput maximization problem that jointly accounts for mode selection, draft-length control, and power allocation. For mode selection, we reveal a simple optimal structure that enables efficient search over the number of UL devices, with the corresponding transmit powers optimized accordingly. For draft-length control, we develop a greedy-search algorithm that adapts device-specific draft lengths to heterogeneous computation and communication capabilities. Experimental results on Qwen2.5 and DeepSeek-R1 model pairs demonstrate that the proposed framework significantly improves token goodput.
Read the full abstract

Computation and Language

Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection

This paper introduces a hybrid fact-checking framework that integrates Knowledge Graph-based semantic memory with adversarial multi-agent reasoning for explainable misinformation detection. The proposed system follows a memory-first, web-fallback architecture, in which input claims are initially evaluated against a dual-index Knowledge Graph through Sentence-BERT-based semantic retrieval and Natural Language Inference. When the evidence retrieved from the graph is insufficient to support a reliable decision, the framework collects information from trusted web sources and assesses it using an adversarial tribunal composed of support, contradiction, and judging agents. A graph-aware confidence mechanism combines semantic similarity, NLI confidence, and structural graph evidence to determine whether internal knowledge is sufficient, thereby reducing unnecessary web retrieval. Following verification, validated information is transformed into structured triples and incorporated into the Knowledge Graph, supporting the incremental expansion of the system's semantic memory. Experimental evaluation on a curated COVID-19 misinformation benchmark demonstrates that the proposed framework achieves an accuracy of 97.4% and a macro-averaged F1-score of 92.6% on resolved claims, outperforming a Llama~3.3~70B baseline, which obtains an accuracy of 87.7% and a macro-averaged F1-score of 86.3%.
Read the full abstract

Computation and Language

JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction

Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing outcomes from case facts. Unlike standard classification tasks, it involves a structured reasoning process in which statutes should be matched with facts, charges should be justified by statutes, and sentencing outcomes should remain consistent with charges. Existing approaches optimize final labels, and while some have attempted to evaluate reasoning quality, their evaluations are indirect, often relying on LLM-generated rubrics that reflect model-internal preferences rather than the inherent logical structure of legal adjudication. We propose Juris Policy Optimization (JPO), a post-training framework for structured legal reasoning in Chinese criminal judgment prediction. JPO first uses teacher-generated rationales to supervise a standardized four-step reasoning process, and then applies reinforcement learning with a composite reward over legal prediction quality, reasoning structure completeness, and cross-step consistency. JPO further introduces token-level advantage reweighting and adaptive clipping for legally salient reasoning segments. Experiments on multiple open-source language models and three Chinese legal benchmarks show that JPO consistently improves both judgment prediction and reasoning quality over supervised fine-tuning and reinforcement learning baselines.
Read the full abstract

All authors Zhaolu Kang, Yantao Liu, Tailong Luo, Leqi Zheng, Lei Wei, Chenghua Zhu, Junhao Gong, Jiachen Qian, Eric Hanchen Jiang, Jiaxin Liu, Yuan Wang, Hao Zhang, Zixia Wang, Rong Fu, Zheng Lin, Richeng Xuan, Zhichao Hu

Multiagent Systems

Forward-Deployed Full-Stack Engineering for Autonomous Cloud MLOps

Across industries, machine-learning systems support applications ranging from prediction and anomaly detection to forecasting, optimization, and scheduling, yet operationalizing these systems requires coordinating application development, model pipelines, cloud infrastructure, security, deployment, monitoring, retraining, recovery, and rollback. We present an evidence-gated multi-agent framework for transforming a natural-language MLOps cloud engineering task into a verified repository and operational cloud deployment. The framework combines graph engineering, loop engineering, and agent harness engineering. A stateful Graph Orchestrator coordinates specialized agents for repository generation, review, execution, verification, release, and monitoring while governing workflow dependencies, evidence gates, retry bounds, recovery paths, and termination. Consequential lifecycle transitions proceed only when their required predicates are supported by verifiable execution or runtime evidence. Verification failures activate bounded reflection, repair, and re-verification, while runtime evidence of failure, drift, degradation, or policy violation can trigger bounded adaptation, recovery, or rollback. Agent harness engineering constrains repository generation, review, and repair, artifact execution, and cloud operations through controlled capabilities and isolated execution environments. We realize the framework on Google Cloud Platform and evaluate repository completeness, controlled execution, evidence-gated transitions, cloud promotion, and bounded recovery. Our experimental results show that the framework prevents unsupported lifecycle transitions and drives each run toward either a verified operational deployment or an auditable terminal failure.
Read the full abstract

Statistical Methodology

Prognosis-equivalent mapping of clinical measurements via survival analysis

A continuous clinical measurement recorded in fixed physical units may have different prognostic meaning across patients when its effect depends on a patient-level modifier. For example, the same tumor diameter may imply markedly different prognosis in an infant and an adult, because patient size can modify its prognostic effect. We formalize this problem through prognosis-equivalent mapping for time-to-event outcomes. The resulting estimand maps a measurement value observed at one modifier level to the value under a reference modifier level that yields the same conditional prognostic quantity. The basic operation is to equate a monotone conditional prognostic score and invert the reference-side curve. In observational data, however, treatment may be selected according to the modifier and the measurement, so a direct equate-and-invert procedure may reflect differences in treatment assignment as well as the prognostic meaning of the measurement itself. We therefore define, in addition to a direct approach, a policy-standardized mapping that standardizes treatment under a common policy using the g-formula. We also introduce an origin-referenced mapping that compares changes in prognostic score from a common anchor, thereby separating modifier-specific prognostic levels from modifier dependence in the measurement–prognosis relationship. Using Cox models, we develop linear and flexible inversion estimators with analytic and bootstrap confidence bands. Simulations evaluate finite-sample performance and illustrate how treatment standardization and origin referencing clarify what is being mapped.
Read the full abstract