arXiv subjects

Jiayi Sheng

Publications and source records attributed to Jiayi Sheng.

7 recordsLinked to original sources

arXiv2026

AlphaCrafter: Harnessing Multi-Agent Workflows for Cross-Sectional Quantitative Trading

Quantitative trading agents have demonstrated substantial promise in automating factor discovery, signal aggregation, and portfolio execution. However, existing agent-based trading systems predominantly rely on loosely specified natural-language workflows, leading to opaque reasoning processes, inconsistent behaviors across foundation models, and limited controllability and verifiability, all of which introduce significant risks in financial decision-making. To address these limitations, we propose AlphaCrafter, a multi-agent framework built upon a structured agent harness. Instead of treating agent behavior as unconstrained prompt execution, AlphaCrafter encapsulates each agent within programmable policy specifications that integrate procedural workflows, execution constraints, and explicit verification mechanisms. This harness-driven design transforms the entire trading pipeline into a sequence of well-defined, reproducible, and auditable decision processes with explicit execution semantics. Extensive experiments on the CSI 300 and S&P 500 benchmarks demonstrate that AlphaCrafter consistently achieves superior risk-adjusted returns while exhibiting substantially lower cross-model and cross-trial variance. These results suggest that harness-based agent design provides a practical foundation for building more reliable, controllable, and robust multi-agent systems for quantitative trading.

cs.AI↗

arXiv2026

"I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?

Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground the literal sense and evoke the figurative meaning simultaneously. Although Vision-Language Models (VLMs) are widely used in multimodal understanding and generation, their ability to understand puns has not been systematically studied due to a scarcity of rigorous benchmarks. To address this, we first propose a multimodal pun generation pipeline. We then introduce MultiPun, a dataset comprising diverse types of puns alongside adversarial non-pun distractors. Our evaluation reveals that most models struggle to distinguish genuine puns from these distractors. Moreover, we propose both prompt-level and model-level strategies to enhance pun comprehension, with an average improvement of 16.5% in F1 scores. Our findings provide valuable insights for developing future VLMs that master the subtleties of human-like humor via cross-modal reasoning.

cs.CL↗

arXiv2025

Solving Inequality Proofs with Large Language Models

Inequality proving, crucial across diverse scientific and mathematical fields, tests advanced reasoning skills such as discovering tight bounds and strategic theorem application. This makes it a distinct, demanding frontier for large language models (LLMs), offering insights beyond general mathematical problem-solving. Progress in this area is hampered by existing datasets that are often scarce, synthetic, or rigidly formal. We address this by proposing an informal yet verifiable task formulation, recasting inequality proving into two automatically checkable subtasks: bound estimation and relation prediction. Building on this, we release IneqMath, an expert-curated dataset of Olympiad-level inequalities, including a test set and training corpus enriched with step-wise solutions and theorem annotations. We also develop a novel LLM-as-judge evaluation framework, combining a final-answer judge with four step-wise judges designed to detect common reasoning flaws. A systematic evaluation of 29 leading LLMs on IneqMath reveals a surprising reality: even top models like o1 achieve less than 10% overall accuracy under step-wise scrutiny; this is a drop of up to 65.5% from their accuracy considering only final answer equivalence. This discrepancy exposes fragile deductive chains and a critical gap for current LLMs between merely finding an answer and constructing a rigorous proof. Scaling model size and increasing test-time computation yield limited gains in overall proof correctness. Instead, our findings highlight promising research directions such as theorem-guided reasoning and self-refinement. Code and data are available at https://ineqmath.github.io/.

cs.AI↗

arXiv2025

Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards

Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective paradigm for post-training large language models, yet the design of its baselines and learning-rate schedules remains largely heuristic. This limits our understanding of the statistical properties of policy-gradient estimators and their interaction with optimization dynamics. In this work, we develop a theoretical framework for variance-aware baseline design and adaptive learning-rate selection in RLVR. Under a KL-regularized policy-optimization setting, we establish the unbiasedness of the resulting gradient estimator, derive exact variance expressions including the KL cross-covariance, and obtain an optimization-loss upper bound that enables principled reasoning about learning dynamics. Building on these results, we prove convergence guarantees and derive an adaptive learning-rate schedule governed by the signal-to-noise ratio (SNR) of the policy gradient. We further show that the variance-optimal baseline is a gradient-weighted estimator of the KL-regularized reward, providing a principled alternative to commonly used reward-based baselines. These results lead to two complementary improvements: a variance-optimal baseline and an SNR-adaptive learning-rate rule. Experiments on Qwen3-4B-Base show that each component independently improves policy-optimization performance. The learning-rate rule can also be naturally integrated with existing policy optimization methods to yield further gains, while combining it with the variance-optimal baseline gives the full Optimal Baseline and Learning-Rate Policy Optimization (OBLR-PO) method and achieves the strongest overall performance.

stat.ML↗

arXiv2025

Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair

LLMs have garnered considerable attention for their potential to streamline Automated Program Repair (APR). LLM-based approaches can either insert the correct code or directly generate patches when provided with buggy methods. However, most of LLM-based APR methods rely on a single type of software information, without fully leveraging different software artifacts. Despite this, many LLM-based approaches do not explore which specific types of information best assist in APR. Addressing this gap is crucial for advancing LLM-based APR techniques. We propose DEVLoRe to use issue content (description and message) and stack error traces to localize buggy methods, then rely on debug information in buggy methods and issue content and stack error to localize buggy lines and generate plausible patches which can pass all unit tests. The results show that while issue content is particularly effective in assisting LLMs with fault localization and program repair, different types of software artifacts complement each other. By incorporating different artifacts, DEVLoRe successfully locates 49.3% and 47.6% of single and non-single buggy methods and generates 56.0% and 14.5% plausible patches for the Defects4J v2.0 dataset, respectively. This outperforms current state-of-the-art APR methods. Furthermore, we re-implemented and evaluated our framework, demonstrating its effectiveness in its effectiveness in resolving 9 unique issues compared to other state-of-the-art frameworks using the same or more advanced models on SWE-bench Lite.We also discussed whether a leading framework for Python code can be directly applied to Java code, or vice versa. The source code and experimental results of this work for replication are available at https://github.com/XYZboom/DEVLoRe.

cs.SE↗

arXiv2024

An Empirical Study of Kotlin-Java Cross-Dependency Issues and Their Detection

Since Google introduced Kotlin as an official programming language for developing Android apps in 2017, Kotlin has gained widespread adoption in Android development. The interoperability of Java and Kotlin's design nature allows them to coexist and interact with each other smoothly within a project. However, there is limited research on how Java and Kotlin interact with each other in real-world projects and what challenges are faced during these interactions. The answers to these questions are key to understanding these kinds of cross-language software systems. In this paper, we implemented a tool; named DependExtractor, which can extract 11 types and 9 types of Kotlin-Java and Java-Kotlin dependencies, and conducted an empirical study of 40 Kotlin-Java real-world projects with 27,427 Java and 36,141 Kotlin source files. Our findings revealed that Java and Kotlin frequently interact with each other in these cross-language projects, with Access and Call dependency types being the most dominant. Compared to files interacting with other files in the same language, Java/Kotlin source files, which participate in the cross-language interactions, experience more commits and exhibit a higher defect rate. Additionally, among all Kotlin-Java problematic interactions, we identified ten common issues, along with their fixing strategies. Furthermore, we implemented a tool called InteropScan to proactively detect these issues from Java and Kotlin source code. The findings of this study can help developers understand and address the challenges in Kotlin-Java projects.

cs.SE↗

arXiv2019

Fully Integrated On-FPGA Molecular Dynamics Simulations

The implementation of Molecular Dynamics (MD) on FPGAs has received substantial attention. Previous work, however, has consisted of either proof-of-concept implementations of components, usually the range-limited force; full systems, but with much of the work shared by the host CPU; or prototype demonstrations, e.g., using OpenCL, that neither implement a whole system nor have competitive performance. In this paper, we present what we believe to be the first full-scale FPGA-based simulation engine, and show that its performance is competitive with a GPU (running Amber in an industrial production environment). The system features on-chip particle data storage and management, short- and long-range force evaluation, as well as bonded forces, motion update, and particle migration. Other contributions of this work include exploring numerous architectural trade-offs and analysis on various mappings schemes among particles/cells and the various on-chip compute units. The potential impact is that this system promises to be the basis for long timescale Molecular Dynamics with a commodity cluster.

cs.DC↗