arXiv subjects

Zhongyang Liu

Publications and source records attributed to Zhongyang Liu.

5 recordsLinked to original sources

arXiv2025

The Gaining Paths to Investment Success: Information-Driven LLM Graph Reasoning for Venture Capital Prediction

Most venture capital (VC) investments fail, while a few deliver outsized returns. Accurately predicting startup success requires synthesizing complex relational evidence, including company disclosures, investor track records, and investment network structures, through explicit reasoning to form coherent, interpretable investment theses. Traditional machine learning and graph neural networks both lack this reasoning capability. Large language models (LLMs) offer strong reasoning but face a modality mismatch with graphs. Recent graph-LLM methods target in-graph tasks where answers lie within the graph, whereas VC prediction is off-graph: the target exists outside the network. The core challenge is selecting graph paths that maximize predictor performance on an external objective while enabling step-by-step reasoning. We present MIRAGE-VC, a multi-perspective retrieval-augmented generation framework that addresses two obstacles: path explosion (thousands of candidate paths overwhelm LLM context) and heterogeneous evidence fusion (different startups need different analytical emphasis). Our information-gain-driven path retriever iteratively selects high-value neighbors, distilling investment networks into compact chains for explicit reasoning. A multi-agent architecture integrates three evidence streams via a learnable gating mechanism based on company attributes. Under strict anti-leakage controls, MIRAGE-VC achieves +5.0% F1 and +16.6% PrecisionAt5, and sheds light on other off-graph prediction tasks such as recommendation and risk assessment. Code: https://anonymous.4open.science/r/MIRAGE-VC-323F.

cs.AI↗

arXiv2025

Beyond Isolated Investor: Predicting Startup Success via Roleplay-Based Collective Agents

Due to the high value and high failure rates of startups, predicting their success is a critical challenge. Existing approaches typically model startup success from a single decision-maker's perspective, overlooking the collective dynamics that dominate real-world venture capital (VC) decision-making. We propose SimVC-CAS, a collective agent system that simulates VC decisions as a multi-agent interaction process. By designing role-playing agents and a GNN-based supervised interaction module, we reformulate startup financing prediction as a group decision-making task, capturing both enterprise fundamentals and investor network dynamics. Each agent represents an investor with distinct traits and preferences, enabling heterogeneous evaluations and realistic information exchange over a graph-structured co-investment network. Using both proprietary and public VC data with strict anti-leakage controls, we show that SimVC-CAS significantly improves predictive performance, achieving approximately 25% relative improvement in average precision@10, while exhibiting consistency with real investor decisions. The interaction mechanism is particularly effective for network-central startups, confirming the importance of network in VC decision-making. Analysis of agents' reasoning for decision changes further reveals how network environment influence decision quality, demonstrating the system's interpretability. Our approach may generalize to broader group decision-making scenarios.

cs.AI↗

arXiv2025

Theoretical models for the Late Thermal Pulse in post-AGB stars: the case of DY Cen

We present theoretical predictions of the born-again scenario for post-asymptotic giant-branch stars. An extensive model grid for born-again objects has been constructed, particularly including models for the Very Late Thermal Pulse with and without convective overshooting, and also including models for the Late Thermal Pulse. We constructed a large parameter space to analyze the dependencies of the born-again model on core mass, hydrogen-envelope mass, and overshoot parameters, and we analyzed how changes in these parameters affect the models' evolution. We applied our grid of models to interpret observations of DY\,Cen, a star exhibiting characteristics similar to confirmed born-again stars. We compared DY\,Cen with models from multiple aspects, including heating rate, evolutionary tracks, and surface abundances. Ultimately, we concluded that none of our born-again models could match all of the observed properties of DY\,Cen, especially its surface chemistry; DY\,Cen is therefore an unlikely born-again star.

astro-ph.SR↗

arXiv2025

When Life Paths Cross: Extracting Human Interactions in Time and Space from Wikipedia

Interactions among notable individuals -- whether examined individually, in groups, or as networks -- often convey significant messages across cultural, economic, political, scientific, and historical perspectives. By analyzing the times and locations of these interactions, we can observe how dynamics unfold across regions over time. However, relevant studies are often constrained by data scarcity, particularly concerning the availability of specific location and time information. To address this issue, we mine millions of biography pages from Wikipedia, extracting 685,966 interaction records in the form of (Person1, Person2, Time, Location) interaction quadruplets. The key elements of these interactions are often scattered throughout the heterogeneous crowd-sourced text and may be loosely or indirectly associated. We overcome this challenge by designing a model that integrates attention mechanisms, multi-task learning, and feature transfer methods, achieving an F1 score of 86.51%, which outperforms baseline models. We further conduct an empirical analysis of intra- and inter-party interactions among political figures to examine political polarization in the US, showcasing the potential of the extracted data from a perspective that may not be possible without this data. We make our code, the extracted interaction data, and the WikiInteraction dataset of 4,507 labeled interaction quadruplets publicly available.

cs.SI↗

arXiv2025

Precise Asteroseismology of the High-amplitude Delta Scuti Star EH Librae, an AE UMa Analogue in the Hertzsprung Gap

A subclass of intermediate mass variables Delta Scuti stars, known as High-amplitude Delta Scuti (HADS) stars, exhibits pronounced radial pulsations with high amplitudes. The ground-based and space-based observations of the HADS star EH Lib are used to help making asteroseismological analysis of this pulsating star. Following the reduction of the light curves, the frequency analysis reveals the fundamental frequency as $f_0=11.3105$ c day$^{-1}$ and two more significant frequencies $f_1$ and $f_2$, in addition to the harmonics of $f_0$ and a linear combination. The period change rate is determined as $(1/P_0)(dP_0/dt)=(5.4\pm0.5)\times10^{-9}$ yr$^{-1}$ derived from an O-C diagram, which is constructed from 342 times of maximum light spanning over 70 years. Using these observational constraints, along with the metallicity reported in the literature, we construct theoretical models using the stellar evolution code MESA and calculate the theoretical frequencies of the eigen modes using the oscillation code GYRE. The appropriate models are selected by matching both $f_0$ and $(1/P_0)(dP_0/dt)$ within their respective uncertainties. The results indicate that the observed period change of EH Lib can be attributed to stellar evolutionary effects. The stellar parameters of EH Lib are derived as: the mass of $1.715\pm0.065$ M$_{\odot}$, the luminosity of log $(L/L_{\odot})=1.38\pm0.06$, and the age of $(1.14\pm0.13)\times10^{9}$ years. EH Lib is classified as a single-mode HADS star, locating currently in the Hertzsprung gap, with a helium core and a hydrogen-burning shell. This work expands the asteroseismological sample of HADS stars and establishes a foundation for future investigations into their commonalities and specific properties, thereby advancing our understanding of these variables.

astro-ph.SR↗