arXiv subjects

Qilin Cai

Publications and source records attributed to Qilin Cai.

3 recordsLinked to original sources

arXiv2026

Constructing Exceptional Knots and Links with Arbitrary Braiding Topology

Exceptional knots and links represent a remarkable class of non-Hermitian metals in which exceptional degeneracies form knotted or linked manifolds in momentum space. Here, we report a universal construction framework for realizing exceptional knots and links with arbitrary braiding topology in 3D minimal two-band non-Hermitian systems. Our approach combines braid theory with semiholomorphic polynomials to establish a direct correspondence between braid words and non-Hermitian Bloch Hamiltonians. This framework enables the realization of a broad variety of exceptional configurations, including torus knots, lemniscate knots, nonfibred knots, hyperbolic knots, and multi-component links, within explicit tight-binding Hamiltonians. Furthermore, we demonstrate controllable topological transitions in which exceptional knots can be continuously untied through redistribution and reconnection of exceptional points, accompanied by transient exceptional chains and changes in spectral complex energy braiding. Our results establish a universal route toward programmable non-Hermitian knot topology and provide a versatile platform for exploring knotted band degeneracies and their associated physical phenomena across photonic, acoustic, mechanical, and cold-atom systems.

cond-mat.mes-hall↗

arXiv2025

Enhancing Automated Paper Reproduction via Prompt-Free Collaborative Agents

Automated paper reproduction has emerged as a promising approach to accelerate scientific research, employing multi-step workflow frameworks to systematically convert academic papers into executable code. However, existing frameworks often lack mechanisms to verify and refine the outputs at each generation step, or rely heavily on manually designed prompts for self-refinement, which limits their adaptability and scalability. To address these limitations, we propose a prompt-free collaborative agent framework that automatically enhances the quality of paper-to-code generation. Our approach employs two collaborative agents: a verification agent that examines whether the outputs at each step satisfy the requirements specified in the corresponding system prompt, and a refinement agent that revises the outputs based on the identified issues. Unlike previous methods that require human experts to craft specific refinement prompts for each step, our framework achieves automatic verification and improvement by leveraging only the original system prompts. We integrate our collaborative agents into the Paper2Code framework and conduct comprehensive experiments on PaperBench Code-Dev and Paper2CodeBench datasets. Experimental results demonstrate that our approach significantly improves the accuracy and completeness of reproduced code, achieving performance gains of approximately 15\% and 13\%, respectively, compared to the baseline without our agents. Furthermore, comparative experiments against Self-Refine validate the robustness and consistency of our prompt-free approach across different datasets.

cs.AI↗

arXiv2025

AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers

Machine Learning (ML) research is spread through academic papers featuring rich multimodal content, including text, diagrams, and tabular results. However, translating these multimodal elements into executable code remains a challenging and time-consuming process that requires substantial ML expertise. We introduce ``Paper-to-Code'' (P2C), a novel task that transforms the multimodal content of scientific publications into fully executable code repositories, which extends beyond the existing formulation of code generation that merely converts textual descriptions into isolated code snippets. To automate the P2C process, we propose AutoP2C, a multi-agent framework based on large language models that processes both textual and visual content from research papers to generate complete code repositories. Specifically, AutoP2C contains four stages: (1) repository blueprint extraction from established codebases, (2) multimodal content parsing that integrates information from text, equations, and figures, (3) hierarchical task decomposition for structured code generation, and (4) iterative feedback-driven debugging to ensure functionality and performance. Evaluation on a benchmark of eight research papers demonstrates the effectiveness of AutoP2C, which can successfully generate executable code repositories for all eight papers, while OpenAI-o1 or DeepSeek-R1 can only produce runnable code for one paper. The code is available at https://github.com/shoushouyu/Automated-Paper-to-Code.

cs.SE↗