Introducing Consort: A Spec-First Agent Framework for Enforced, Test-Driven Development on Live Database Branches
本文介绍了一种名为Consort的框架,通过在实时数据库分支上实施不可绕过的控制来强制执行规范优先、测试驱动的开发方法,以确保由代理编写的代码的质量和可维护性。
本文介绍了一种名为Consort的框架,通过在实时数据库分支上实施不可绕过的控制来强制执行规范优先、测试驱动的开发方法,以确保由代理编写的代码的质量和可维护性。
Sintr通过冗余执行和灵活的策略框架防止拜占庭客户端破坏数据库完整性,解决了BFT系统中性能与开发者便利性之间的矛盾。
This study addresses the “temporal misalignment” problem in legal Retrieval-Augmented Generation (RAG), which arises when statutory provisions are treated without regard to their temporal validity. The work provides the first systematic definition and quantification of this issue, introduces a multi-version corpus spanning 93 years of French tax law, and presents FiscalQA Pro—the first version-aware legal question-answering benchmark. The proposed approach formulates legal QA as a time-indexed retrieval task, leveraging multi-version indexing, an atomic scoring mechanism based on regular expressions and numerical tolerance, and an end-to-end learnable retriever. Crucially, it avoids reliance on large language models for judgment to prevent temporal bias. Experiments show that static RAG achieves 0% recall for the correct statutory version, whereas the proposed method attains a strict accuracy of 98.3% without oracle information, approaching the oracle upper bound of 99.1%.
This work addresses the problem of efficiently approximating dominant eigenvectors of large symmetric matrices in sublinear time. By uniformly or column-norm-squared-weighted sampling a small number of columns and applying a truncated Nyström method to construct a low-dimensional subspace, the proposed approach achieves per-entry computational complexity poly(log n, 1/ε) while controlling approximation error via the Frobenius norm. It extends random column sampling to eigenvector estimation for the first time: for any eigenvalue satisfying |λ| ≥ εn, only Õ(log n/ε⁴) columns suffice to guarantee ‖Av − λv‖₂ ≤ εn; for the leading eigenvector under weighted sampling, merely Õ(log n/ε²) columns are required, achieving the optimal error bound ε‖A‖_F. The algorithm is also compatible with quantum-inspired frameworks.
This work addresses the limitation of traditional retrieval systems, which treat document representation as a static preprocessing step and thus struggle to adapt to downstream tasks. The authors propose AutoIndex, a novel framework that formulates document representation construction as a learnable program synthesis problem. AutoIndex dynamically generates retrieval-oriented representations by searching over executable transformation programs—such as slicing, augmentation, and normalization—and iteratively refines them using validation feedback. By integrating proxy-guided program search with retrieval quality evaluation, the method enables explicit optimization of document representations. Evaluated on the CRUMB benchmark across all eight tasks, AutoIndex consistently outperforms the full-document BM25 baseline, achieving average improvements of 8.4% in Recall@100 and 8.3% in nDCG@10, with peak gains reaching 30.5% and 43.6%, respectively.
本文介绍了一种名为Consort的框架,通过在实时数据库分支上实施不可绕过的控制来强制执行规范优先、测试驱动的开发方法,以确保由代理编写的代码的质量和可维护性。
Sintr通过冗余执行和灵活的策略框架防止拜占庭客户端破坏数据库完整性,解决了BFT系统中性能与开发者便利性之间的矛盾。
This study addresses the “temporal misalignment” problem in legal Retrieval-Augmented Generation (RAG), which arises when statutory provisions are treated without regard to their temporal validity. The work provides the first systematic definition and quantification of this issue, introduces a multi-version corpus spanning 93 years of French tax law, and presents FiscalQA Pro—the first version-aware legal question-answering benchmark. The proposed approach formulates legal QA as a time-indexed retrieval task, leveraging multi-version indexing, an atomic scoring mechanism based on regular expressions and numerical tolerance, and an end-to-end learnable retriever. Crucially, it avoids reliance on large language models for judgment to prevent temporal bias. Experiments show that static RAG achieves 0% recall for the correct statutory version, whereas the proposed method attains a strict accuracy of 98.3% without oracle information, approaching the oracle upper bound of 99.1%.
This work addresses the problem of efficiently approximating dominant eigenvectors of large symmetric matrices in sublinear time. By uniformly or column-norm-squared-weighted sampling a small number of columns and applying a truncated Nyström method to construct a low-dimensional subspace, the proposed approach achieves per-entry computational complexity poly(log n, 1/ε) while controlling approximation error via the Frobenius norm. It extends random column sampling to eigenvector estimation for the first time: for any eigenvalue satisfying |λ| ≥ εn, only Õ(log n/ε⁴) columns suffice to guarantee ‖Av − λv‖₂ ≤ εn; for the leading eigenvector under weighted sampling, merely Õ(log n/ε²) columns are required, achieving the optimal error bound ε‖A‖_F. The algorithm is also compatible with quantum-inspired frameworks.
This work addresses the limitation of traditional retrieval systems, which treat document representation as a static preprocessing step and thus struggle to adapt to downstream tasks. The authors propose AutoIndex, a novel framework that formulates document representation construction as a learnable program synthesis problem. AutoIndex dynamically generates retrieval-oriented representations by searching over executable transformation programs—such as slicing, augmentation, and normalization—and iteratively refines them using validation feedback. By integrating proxy-guided program search with retrieval quality evaluation, the method enables explicit optimization of document representations. Evaluated on the CRUMB benchmark across all eight tasks, AutoIndex consistently outperforms the full-document BM25 baseline, achieving average improvements of 8.4% in Recall@100 and 8.3% in nDCG@10, with peak gains reaching 30.5% and 43.6%, respectively.