Searcharxiv⌕ Search

arXiv subjects

Huan Zhou

Publications and source records attributed to Huan Zhou.

At least 19 recordsLinked to original sources

SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12 application domains. Each assignment places an agent in a simulated engineering organization with 26 colleagues who have distinct responsibilities, bounded knowledge, and controlled collaboration behavior. Starting from a brief handoff, agents must recover requirements distributed across colleagues and workplace records, reconcile conflicting evidence, and implement changes evaluated by private executable tests. We evaluate eleven models and find a substantial gap between partial implementation and complete task delivery. The two leading models satisfy approximately 63% of fail-to-pass (F2P) tests but complete fewer than 8% of assignments. Providing complete requirements upfront improves F2P by approximately 16 percentage points for Seed Evolving and GPT-6 Astra, yet leaves complete task success unchanged. Requirement-level trajectory analysis reveals failures throughout the delivery process: Claude-Opus-5.5 directs a mean of 93% of first questions about queried cards to their accountable owners across runs but obtains only 64% of colleague-held requirements. Deferred questions go unfollowed, implementations remain incomplete even after requirements are acquired, and 31% of requirements reported as completed fail their tests. These findings highlight sustained requirement tracking, from clarification through implementation, verification, and handoff, as a key challenge for reliable autonomous software engineering.

cs.SE↗

Probing the Activity History of Repeating Fast Radio Bursts with Cluster Lensing

Fast radio bursts (FRBs) are millisecond duration coherent radio transients, some of whose sources repeat, but the nature and active lifetimes of their engines remain uncertain. Strong lensing by galaxy clusters provides a physical lever on this lifetime problem: a short campaign can sample emission epochs of a repeating FRB separated by years, and distinct bursts in different lensed images, given a known relative lens delay, set a lower bound on its active lifetime, whereas delayed copies of a single burst only encode the lens delay. Based on the cluster-lens model of MACS J0717.5+3745, we quantify the accessible range of emission epochs for finite activity episodes, observing windows, and discovery selection. For a source-frame episode of duration \(100~{\rm yr}\) at \(z_s=2\) and a source-frame rate of \(0.1\,{\rm h}_{\rm src}^{-1}\), a five year campaign conditional on discovery yields a \(95\%\) gain threshold of \(m_{95}\simeq25.6\), corresponding to a source-frame span of \(L_{95}\simeq42.6~{\rm yr}\). At the population level, combining distinct burst associations with same burst echoes provides a way to test specified activity durations with a finite lens catalogue, e.g., activity durations differing by an order of magnitude can be distinguished with expected Bayes factor above $20$. More broadly, these lensed source frame epochs enable applications beyond activity-duration tests, e.g., linking burst activity to the evolution of the engine and its environment. Galaxy-cluster lensing therefore provides a promising future probe for accessing otherwise unobserved source history and for distinguishing between different activity duration models.

astro-ph.HE↗

Colouring signed analogues of Kneser, Schrijver, and Borsuk graphs

The Kneser signed graph $\KS(n,k)$, $k\leq n$, is the graph whose vertices are signed $k$-subsets of $[n]$ (i.e. $k$-subsets $S$ of $\{ \pm 1, \pm 2, \ldots, \pm n\}$ such that $S\cap (-S)=\emptyset$). Two vertices $A$ and $B$ are adjacent with a positive edge if $A\cap (-B)=\emptyset$ and with a negative edge if $A\cap B=\emptyset$. We prove that the balanced chromatic number of $\KS(n,k)$ is $n-k+1$. We then introduce the signed analogue of Schrijver graphs and show that choosing one representative from each antipodal pair of alternating signed $k$-sets gives a vertex-critical subgraph of $\KS(n,k)$ with respect to balanced colouring. For the Borsuk signed graph on $S^d$, we obtain balanced chromatic number $d+1$ for sufficiently small distance parameter and relate this equality to antipodal covers of the sphere. On $S^2$, spherical and projective covering bounds give three, four and six as the first successive values of the balanced chromatic number.

math.CO↗

ACE-CaP-0: Real-World Code-as-Policies in the Era of Experience

Recent advances in frontier models have pushed the boundaries of agentic robot control, enabling agents to perform complex robotic tasks through reasoning and interaction. However, repeated calls to these models during execution can substantially increase task completion time. Code as Policies (CaP) offers a route for coding agents to acquire physical skills through experience and retain them in executable programs, allowing the reasoning invested in development to be reused across runs. Developing reliable code policies while limiting the cost of physical experimentation remains a central challenge. We investigate human guidance as a source of priors for feasible actions and simulation as an auxiliary environment for exploring and testing candidate policies. Our findings favor robot demonstrations available on request and simulation used selectively during real-world policy refinement. These findings inform ACE-CaP-0, an agentic recipe that couples policy revision with experience acquisition through Demonstrations on Request and Simulation on Demand. Across eight real-world manipulation tasks spanning alignment, multi-object handling, and bimanual coordination, the resulting frozen programs achieve 92.1\% success (221/240 trials). Mean execution times across tasks range from 0.97 to 2.27 minutes. The programs execute with runtime perception and control, without a human or coding agent in the loop. These results highlight CaP's potential to turn experience into reliable, reusable physical skills.

cs.RO↗

Constraints on Compact Dark Matter Population from Micro-lensing Effect of Gravitational Wave for the third-generation gravitational Wave Detector

Since the first direct detection of gravitational waves (GWs) from a binary black-hole merger by the LIGO-Virgo Collaboration, GWs have emerged as a powerful probe of astrophysics and cosmology. If extragalactic compact dark matter (DM) candidates, such as primordial black holes, constitute a non-negligible fraction of the DM component over a broad mass range, they can imprint distinctive microlensing signatures on GW signals. In this work, we develop a framework to infer the population properties of extragalactic compact DM by simulating microlensing GWs in the frequency band of the third-generation ground-based GW detector, the Einstein Telescope, and analyzing them via hierarchical Bayesian inference. For a population described by a power-law mass function, we show that the detection of only several microlensing GW events among $10^4$ binary black-hole coalescences can constrain the compact DMs abundance to the level of $\sim 10^{-3}$. This forecast demonstrates that searching for and identifying microlensing signatures in future GW observations can provide a complementary approach to constraining compact DM scenarios.

astro-ph.CO↗

Degree-truncated DP-colouring of $\{K_4,K_{2,t}\}$-minor-free graphs

A graph $G$ is degree-truncated DP-$k$-colourable (respectively, degree-truncated $k$-choosable) if it is DP-$f$-colourable (respectively, $f$-choosable), where $f(v)=\min\{k,d_G(v)\}$ for every vertex $v$. Hutchinson proved that every $2$-connected maximal outerplanar graph other than the triangle is degree-truncated $5$-choosable. Lo, Wang, Zhou and Zhu strengthened this result by proving that every $2$-connected $K_{2,4}$-minor-free graph other than cycles and complete graphs is degree-truncated DP-$5$-colourable. Outerplanar graphs are precisely the $\{K_4,K_{2,3}\}$-minor-free graphs. We study how the truncation threshold grows when $K_{2,3}$ is replaced by $K_{2,t}$, while $K_4$-minor remains excluded. A bound independent of $t$ is impossible, as shown by the family $\{K_{2,n}| n\ge 2\}$. Let $\mathcal S_t$ be the class of $2$-connected $\{K_4,K_{2,t}\}$-minor-free graphs other than cycles. Writing $χ^{\text{\sout{d}}}_{\mathrm{DP}}(\mathcal S_t)$ for the least truncation threshold valid throughout this class, we prove that, for every integer $t\ge3$, \[ \left\lfloor2\sqrt{2t}\right\rfloor \le χ^{\text{\sout{d}}}_{\mathrm{DP}}(\mathcal S_t) \le \left\lceil4\sqrt{2t}\right\rceil. \]

math.CO↗

A planar signed graph with circular chromatic number five

A circular $r$-coloring of a signed graph maps its vertices to a circle of circumference $r\ge2$, with the endpoints of negative edges at circular distance at least $1$ and those of positive edges at most $r/2-1$; the circular chromatic number is the infimum of such $r$. We construct a simple planar signed triangulation on $85$ vertices with circular chromatic number exactly $5$. This improves the lower bound on the supremum of the circular chromatic numbers of simple planar signed graphs from $14/3$ to $5$, giving a partial answer to a question posed by Naserasr, Wang, and Zhu.

math.CO↗

Aspire: Can Models Self-Evolve from Vague Goals?

Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved. In contrast, existing work on LLM self-evolution typically begins with tasks and evaluation metrics specified by humans, reducing self-evolution to optimizing an explicit objective rather than deciding what and how to learn. We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution. ASPIRE provides only a natural-language capability goal while downstream evaluation tasks remain hidden. The agent must operationalize the goal by choosing data and update methods, constructing training and validation signals, and deciding when to evaluate. ASPIRE supports both model-weight and agent-harness evolution in a unified interactive environment and evaluates the resulting systems on a hidden, expert-authored set of 520 items spanning six goals. Our experiments show that vague goals redirect search effort toward goal interpretation. Current agents routinely complete training and harness-editing loops, but weight-level gains remain sparse and unstable, and the strongest evolved harness remains below the engineered Qwen-Agent reference. Agents often train on mismatched data and trust narrow self-evaluations, so local gains fail to transfer to hidden evaluation and continued search and training can erase earlier improvements.

cs.CL↗

Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning

Document understanding aims to perform question answering and information extraction over document images, where the visual content is highly information-dense and most queries rely on only a few relevant layout regions. However, existing methods either adopt a one-pass strategy that implicitly assumes all layouts are equally important, or focus excessively on small regions at the cost of losing critical layout information. To address these limitations, we introduce Doc-CoB (Chain-of-Boxes), a simple-yet-effective framework that integrates coarse-to-fine layout-aware visual reasoning into multimodal large language models. Instead of directly zooming into small regions, Doc-CoB progressively focuses on query-relevant layouts while preserving global document information. Specifically, it first selects key layout boxes and then focuses on them for further understanding with visual prompting. To support this paradigm, we introduce two reasoning tasks for box recognition and box reasoning, with an automatic pipeline that constructs 249k training samples with intermediate visual supervision. Experiments on seven benchmarks with four popular models show that Doc-CoB significantly improves performance, demonstrating its effectiveness and wide applicability. The code and the data are available at https://github.com/Doc-CoB/Doc-CoB.

cs.AI↗

Evidence for Intermediate-Mass Black Holes From Microlensing Signatures in CHIME/FRB catalog 2

Intermediate-mass black holes (IMBHs) are the missing link in the cosmic hierarchy of black holes, bridging the gap between stellar-mass black holes and supermassive ones. They also serve as unique laboratories for testing strong-field gravity and are prime targets for future multi-messenger observations. However, IMBHs are a population that has remained notoriously difficult to detect. The microlensing effect of fast radio bursts (FRBs) can serve as a clean and powerful method to probe IMBHs. In this work, we develop a pipeline to search for microlensed FRBs based on their dynamic spectra and apply it to the CHIME/FRB Catalog 2. Two microlensing signatures have been identified in two separate sources, i.e. FRB~20190131D and FRB~20211115A. The inferred lens masses for these two signatures are $\sim[280-467]~M_{\odot}$ and $\sim[539-609]~M_{\odot}$, respectively. Here we interpret them as evidence for IMBHs. If there are no intervening structures-such as galaxies or clusters-along the line of sights for these two sources, the two identified IMBHs might be isolated and of primordial origins. In that case, we obtain primordial black holes (PBHs) within these two mass ranges would constitute $\sim4\%$ of dark matter. Moreover, if these two candidates are not genuine lensing signatures, the abundance of intermediate-mass PBHs with masses $>300,M_{\odot}$ is constrained to be $\sim13\%$ at $95\%$ confidence level. Therefore, more comprehensive observational information for FRBs, together with a deeper understanding of whether the intrinsic emission mechanisms of FRBs can produce lensing-like signals, will be crucial for establishing this effect as a powerful tool for probing (primordial) IMBHs.

astro-ph.HE↗

StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows

Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-validated AI startup products. Rather than defining tasks from pre-defined assumptions about useful agent capabilities, we systematically study AI products with demonstrated adoption, together with their product workflows and users, to identify real-world tasks for which AI has established practical demand across diverse professional domains. We translate these workflows into complete deliverable-oriented tasks and evaluate them with fine-grained rubrics capturing their complex requirements. Across representative models evaluated under a unified agent harness, even the strongest model successfully completes only approximately 30\% of StartupBench, despite making substantial partial progress on many tasks. Further analysis identifies aspects like complex instruction following and domain-specific expertise as major sources of failure. Our results reveal that many market-validated workflows remain beyond the reliable capabilities of current general-purpose agents, establishing StartupBench as an empirical measure of progress toward E2E completions of real-world user tasks.

cs.AI↗

Arc weighted acyclic orientations and variations of degeneracy of graphs

This paper studies generalizations of the concept of acyclic orientations to arc-weighted orientations. These lead to four types of variations of strict degeneracy of graphs. Some of these variations are studied in the literature under different names and we put them in a same framework for comparison. Then we concentrate on one of these variations, which is new and is defined as follows: For a graph $G$ and a mapping $f \in \mathbb{N}^G$, we say $G$ is $ST^{(2)}$-$f$-degenerate if there is an arc-weighted orientation $(D, w)$ of $G$ such that $d_{(D,w)}^+(v) < f(v)$ for each vertex $v$, and every sub-digraph $D'$ of $D$ contains an arc $e=(u,v)$ with $w(e) > d_{(D', w)}^+(v)$. We prove that if $G$ is $ST^{(2)}$-$f$-degenerate, then $G$ is $f$-paintable, as well as $f$-AT. Then we use $ST^{(2)}$-degeneracy to study truncated degree choosability of graphs. A graph $G$ is called $k$-truncated degree-choosable (respectively $ST^{(2)}$-$k$-truncated degree degenerate) if $G$ is $f$-choosable (respectively, $ST^{(2)}$-$f$-degenerate), where $f(v)= \min\{k, d_G(v)\}$. Richter asked whether every 3-connected non-complete planar graph is $6$-truncated-degree-choosable. We answer this question in negative by constructing a 3-connected non-complete planar graph which is not $7$-truncated-degree-choosable. On the other hand, we prove that every 3-connected non-complete planar graph is $ST^{(2)}$-$16$-truncated-degree-degenerate, and hence $16$-truncated-degree-choosable. We further prove that for an arbitrary proper minor closed family ${\mathcal G}$ of graphs, let $s$ be the minimum integer such that $K_{s,t} \notin \mathcal{G}$ for some $t$, then there is a constant $k$ such that every $s$-connected non-complete graph $G \in {\mathcal G}$ is $ST^{(2)}$-$k$-truncated-degree-degenerate and hence $k$-truncated-degree-choosable.

math.CO↗

Constraints on Primordial Black Hole Dressed by Dark Matter Halo from Microlensing Effect of Fast Radio Bursts

Primordial black holes (PBHs) are not only considered as a candidate for dark matter, but also as potential sources of gravitational waves from binary black hole mergers by the LIGO-Virgo-KAGRA and as seeds for the supermassive black holes observed by the James-Webb Space Telescope, thereby remaining intense interest in cosmology and astrophysics. Fast radio bursts (FRBs) are bright millisecond-duration radio transients whose physical origin remains elusive, which have rapidly developed into one of the most active and rapidly evolving fields in astronomy. The microlensing effect of FRBs offers a clean and powerful probe of PBHs, especially in the mass range above stellar-mass window. In this work, we derive a complete transformation that converts any upper limit on the abundance of PBHs originally derived for `bare' PBHs with monochromatic mass distribution, into the corresponding constraint on `dressed' PBHs with arbitrary extended mass distributions. Based on this framework, we estimate the future constraints on the dressed PBH abundance \(f_{\mathrm{PBH}}\) from FRB observations assuming an expected sample of \(10^5\) FRBs accumulated over the next decade well within the projected detection capabilities of SKA. Our results indicate that including halo enhancement tightens the upper limits on \(f_{\mathrm{PBH}}\) by approximately one order of magnitude, with the most stringent constraint reaching \(\sim10^{-4}\) for the typical mass range from stellar-mass to intermediate-mass black holes.

astro-ph.CO↗

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.

cs.AI↗

Tighter Bounds on the Degree-Truncated Choice Number of Planar Graphs

Assume $G$ is a graph and $k$ is a positive integer. Let $f:V(G)\to \mathbb{N}$ be defined as $f(v)=\min\{k,d_G(v)\}$. If $G$ is $f$-choosable, then we say $G$ is degree-truncated $k$-choosable. The degree-truncated choice number of $G$ is $\operatorname{ch}^{\text{\st{d}}}(G) = \min\{k: G \text{ is degree-truncated $k$-choosable}\}$. For a family $\mathcal{G}$ of graphs, $\operatorname{ch}^{\text{\st{d}}}(\mathcal{G}) = \max\{\operatorname{ch}^{\text{\st{d}}}(G):G \in \mathcal{G}\}$. Let $\mathcal{P}$ denote the family of 3-connected non-complete planar graphs. Richter asked in 2008 whether $ch^{\text{\st{d}}}(\mathcal{P}) \le 6$. In 2025, Zhou, Zhu and Zhu answered this question in negative and proved that $8 \le ch^{\text{\st{d}}}(\mathcal{P}) \le 16$. This result was improved by Jiang, Xu, Xu, and Zhu, who proved that $9 \le ch^{\text{\st{d}}}(\mathcal{P}) \le 12$. In this paper, we further improve the result and prove that $10 \le \operatorname{ch}^{\text{\st{d}}}(\mathcal{P}) \le 11$. We conjecture that $\operatorname{ch}^{\text{\st{d}}}(\mathcal{P}) =10$, and we confirm this conjecture for those planar graphs $G \in \mathcal{P}$ for which the subgraph induced by vertices of degree at least 11 is 4-choosable.

math.CO↗

Decision-focused Conservation Voltage Reduction to Consider the Cascading Impact of Forecast Errors

Conservation Voltage Reduction (CVR) relies on the effective coordination of slow-acting devices, such as OLTCs and CBs, and fast-acting devices, such as SVGs and PV inverters, typically implemented through a hierarchical multi-stage Volt-Var Control (VVC) spanning day-ahead scheduling, intra-day dispatch, and real-time control. However, existing sequential methods fail to account for the cas-cading impact of forecast errors on multi-stage decision-making. This oversight results in suboptimal day-ahead schedules for OLTCs and CBs that hinder the ef-fective coordination with fast-acting SVGs and inverters, inevitably driving a trade-off between real-time voltage security and CVR efficiency. To improve the Pareto front of this trade-off, this paper proposes a novel bi-level multi-timescale forecasting (Bi-MTF) framework for multi-stage VVC optimization. By integrating the downstream multi-stage VVC optimization into the upstream forecasting mod-els training, the decision-focused forecasting models are able to learn the trade-offs across temporal horizons. To solve the computationally challenging bi-level for-mulation, a modified sensitivity-driven integer L-shaped method is developed. It utilizes a hybrid gradient feedback mechanism that integrates numerical sensitivity analysis for discrete variables with analytical dual information for continuous fore-cast parameters to ensure tractability. Numerical results on a modified IEEE 33-bus system demonstrate that the proposed approach yields superior energy savings and operational safety compared to conventional MSE-based sequential paradigms. Specifically, as the capacity of fast-acting devices increases, the energy savings of the proposed method rise from 2.74% to 3.41%, which is far superior to the 1.50% to 1.76% achieved by conventional MSE-based sequential paradigms.

eess.SY↗

Generalizable Self-Evolving Memory for Automatic Prompt Optimization

Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits generalization across heterogeneous queries and prevents models from accumulating reusable prompting knowledge over time. In this paper, we propose MemAPO, a memory-driven framework that reconceptualizes prompt optimization as generalizable and self-evolving experience accumulation. MemAPO maintains a dual-memory mechanism that distills successful reasoning trajectories into reusable strategy templates while organizing incorrect generations into structured error patterns that capture recurrent failure modes. Given a new prompt, the framework retrieves both relevant strategies and failure patterns to compose prompts that promote effective reasoning while discouraging known mistakes. Through iterative self-reflection and memory editing, MemAPO continuously updates its memory, enabling prompt optimization to improve over time rather than restarting from scratch for each task. Experiments on diverse benchmarks show that MemAPO consistently outperforms representative prompt optimization baselines while substantially reducing optimization cost.

cs.CL↗

Testing supermassive primordial black holes with lensing signals of binary black hole merges

Next-generation ground-based gravitational wave (GW) detectors are expected to observe millions of binary black hole mergers, a fraction of which will be strongly lensed by intervening galaxies or clusters, producing multiple images with characteristic distribution of time delay. Importantly, the predicted rate and properties of such events are sensitive to the abundance and distribution of strong lensing objects which directly depends on cosmological models. One such scenario posits the existence of supermassive primordial black holes (SMPBHs) in the early universe, which would enhance the formation of dark matter halos. This mechanism has been proposed to explain the abundance of high-redshift galaxies observed by James Webb Space Telescope. Crucially, the same cosmological model with SMPBHs would also leave a distinct imprint on the population of strongly lensed GWs. It predicts both an increased event rate and a modified distribution of time delays between the multiple images. Therefore, we propose statistical measurements of the rate and time delay distribution of strong lensing GW events as a powerful probe to directly constrain the abundance of SMPBHs. Considering $Λ$CDM cosmology with (non-)clustered SMPBHs, we find that the abundance of SMPBHs $f_{\rm PBH}$ with masses above $10^8~M_{\odot}$ is constrained to be $\sim10^{-4}$ at $95\%$ confidence level. It will be comparable and complementary to the currently available constraint from large scale structure observations.

astro-ph.CO↗