SQL dialects vary in syntax, types, and functions across database engines. Text-to-SQL benchmarks, however, predominantly support only SQLite. This creates a critical evaluation gap: cross-dialect evaluation reveals weak per-query agreement (Cohen's ), showing that SQLite performance is an unreliable proxy for other dialects. Yet such evaluation remains prohibitively difficult: existing approaches either require expensive manual query transpilation or rely on tools that often fail on complex SQL. To close this gap, we introduce PolySQL, a novel dual-execution method that eliminates the need for query transpilation by comparing normalized execution results. Notably, our approach achieves higher evaluation fidelity than query transpilation with 100% query coverage. PolySQL comprises three datasets, enabling the first large-scale cross-dialect study. Our study reveals a 10.1% average accuracy drop from SQLite to other dialects and identifies a significant dialect difficulty hierarchy. We find this degradation stems from logical rather than syntactic errors (61% vs. 8%). We release our framework code and leaderboard to enable rigorous dialect-robust evaluation.
We present **vstash**, a local-first document memory system that combines vector similarity search with full-text keyword matching via Reciprocal Rank Fusion (RRF) and adaptive per-query IDF weighting. All data resides in a single SQLite file using sqlite-vec for approximate nearest neighbor search and FTS5 for keyword matching. We make four primary contributions. **(1)** Self-supervised embedding refinement via hybrid retrieval disagreement: across 753 BEIR queries on SciFact, NFCorpus, and FiQA, 74.5% produce top-10 disagreement between vector-heavy (vec=0.95, fts=0.05) and FTS-heavy (vec=0.05, fts=0.95) search (per-dataset rates 63.4% / 73.4% / 86.7%, Section 5.2), providing a free training signal without human labels. Fine-tuning BGE-small (33M params) with MultipleNegativesRankingLoss on 76K disagreement triples improves NDCG@10 on all 5 BEIR datasets (up to +19.5% on NFCorpus vs. BGE-small base RRF, Table 6). On 3 of 5 datasets, under different preprocessing, the tuned 33M-parameter pipeline matches or exceeds published ColBERTv2 results (110M params) and an untrained BGE-base (110M); on FiQA and ArguAna it underperforms ColBERTv2 (Section 5.5). **(2)** Adaptive RRF with per-
ResearchPilot is an open-source, self-hostable multi-agent system for literature-review assistance. Given a natural-language research question, it retrieves papers from Semantic Scholar and arXiv, extracts structured findings from paper abstracts, synthesizes cross-paper patterns, and drafts a citation-aware related-work section. The system combines FastAPI, Next.js, DSPy, SQLite, and Qdrant in a local-first architecture that supports bring-your-own-key model access and remote-or-local embeddings. This paper describes the system design, typed agent interfaces, persistence and history-search mechanisms, and the engineering tradeoffs involved in building a transparent research assistant. Rather than claiming algorithmic novelty, we present ResearchPilot as a systems contribution and evaluate it through automated tests and end-to-end local runs. We discuss limitations including external API rate limits, abstract-only extraction, incomplete corpus coverage, and the lack of citation verification.
Logica is an open-source logic programming language that compiles to SQL and runs on DuckDB, SQLite, PostgreSQL, and BigQuery. Unlike classic Datalog, it freely combines recursion and aggregation, concisely expressing algorithms from shortest paths to PageRank. This expressiveness raises semantic challenges: aggregates update by replacement rather than accumulation, evaluation depends on rule scheduling, and programs may converge to meaningful results without reaching a fixpoint, placing them outside traditional fixpoint semantics. We address this with Defendant-Opponent (DO) semantics, a stabilization-based framework for nonmonotonic logic programs. Evaluation is modeled as a rewrite system over derivation states, and a ground atom is true if, from every reachable state, some continuation makes the atom persist in all further derivations. This admits two equivalent characterizations: game-theoretically, truth is what a Defendant can defend against any Opponent in a three-turn game; and modally, truth corresponds to []<>[]t in the derivation graph viewed as a Kripke structure, placing nonmonotonic reasoning within S4. DO semantics coincides with least fixpoint semantics for p
Natural language-to-SQL (NL2SQL) over real-world enterprise databases remains significantly more challenging than on academic benchmarks. Enterprise schemas often contain hundreds of physical tables with cryptic column names, heterogeneous SQL dialects, and complex analytical workloads requiring nested aggregations, temporal reasoning, and multi-table joins. We present a semantic-layer-mediated NL2SQL agent that decouples semantic intent from physical SQL execution. Rather than generating SQL directly over raw schemas, the agent reasons over a curated semantic layer through a compact intermediate representation called the Semantic Model Query (SMQ). A deterministic compiler translates each SMQ into dialect-specific SQL, providing verified building blocks that the agent composes into the final query. The system employs a constrained think-act loop, supports SQLite, BigQuery, and Snowflake backends, and is integrated into an end-to-end evaluation framework. Using Gemini 3 Pro, the system achieves 94.15% execution accuracy on the 547-task Spider2-snow benchmark, ranking third on the official leaderboard and substantially outperforming schema-only approaches. We describe the system arc
Turning ideas into full software projects from scratch has become a popular use case for language models. Agents are being deployed to seed, maintain, and grow codebases over extended periods with minimal human oversight. Such settings require models to make high-level software architecture decisions. However, existing benchmarks measure focused, limited tasks such as fixing a single bug or developing a single, specified feature. We therefore introduce ProgramBench to measure the ability of software engineering agents to develop software holisitically. In ProgramBench, given only a program and its documentation, agents must architect and implement a codebase that matches the reference executable's behavior. End-to-end behavioral tests are generated via agent-driven fuzzing, enabling evaluation without prescribing implementation structure. Our 200 tasks range from compact CLI tools to widely used software such as FFmpeg, SQLite, and the PHP interpreter. We evaluate 9 LMs and find that none fully resolve any task, with the best model passing 95\% of tests on only 3\% of tasks. Models favor monolithic, single-file implementations that diverge sharply from human-written code.
Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL dialects. However, real-world database systems differ substantially in syntax, functions, type systems, and execution semantics, so the same natural language intent often requires dialect-specific SQL realizations. We introduce UniQL, a human-verified benchmark for cross-dialect text-to-SQL evaluation. UniQL aligns 1,534 natural language questions with executable SQL annotations across 16 SQL dialects, yielding 24,544 dialect-specific queries. All dialects share the same intents, aligned schemas and database contents, enabling controlled evaluation of dialect generalization. UniQL is constructed through a hybrid pipeline combining database migration, SQL translation, execution-guided verification, iterative rule summarization, and human validation. Experiments on both open-source and closed-source LLMs show that current models remain far from dialect-universal, with substantial performance variation across database systems and limited transfer from SQLite success to other dialects. These findings highlight the need for aligned cross-
Extraction at ingestion is the wrong primitive for agent memory: content discarded before the query is known cannot be recovered at retrieval time. We propose True Memory, a six-layer architecture that shifts the center of the system from a storage schema to a multi-stage retrieval pipeline operating over events preserved verbatim. The full system runs as a single SQLite file on commodity CPU with no external database, vector index, graph store, or GPU. On LoCoMo (1,540 questions across 10 multi-session conversations), True Memory Pro reaches 93.0% accuracy (3-run mean) against 61.4% for Mem0, 65.4% for Supermemory, approximately 71% for Zep, and 94.5% for EverMemOS under a matched gpt-4.1-mini answer model. On LongMemEval (500 questions), True Memory Pro reaches 87.8% (3-run mean). On BEAM-1M (700 questions at the 1-million-token scale), True Memory Pro reaches 76.6% (3-run mean), above the prior published result of 73.9% for Hindsight. A 56-configuration ablation shows a 1.3-percentage-point spread within the top-performing configuration family.
Authoritative competency frameworks such as ESCO, ROME, and O*NET are essential for aligning education with labor market needs, yet their technical complexity and structural heterogeneity hinder practical adoption by educators. This paper introduces SkillGraph-Service, an interoperable microservice designed to bridge this gap by unifying these resources into a provenance-preserving Knowledge Graph (KG). Adopting a KG-first, LLM-fallback architecture, the system combines symbolic rigor with sub-symbolic flexibility. It implements a lightweight hybrid retrieval engine (fusing SQLite FTS5 and HNSW vector search) to handle the vocabulary mismatch in educator queries, and utilizes Large Language Models (LLMs) strictly for constrained ranking and audience-aware explanation. Empirical evaluation on a multilingual dataset reveals that the proposed hybrid strategy achieves superior retrieval effectiveness (nDCG@5>0.94) with sub-200 ms latency, rendering computationally expensive cross-encoder re-ranking may be unnecessary for this domain. Furthermore, an analysis of generated explanations highlights a trade-off between fluency and faithfulness: while JSON-constrained LLMs ensure high cit
We present MonaVec, a deterministic, embedded vector-search kernel for edge and offline AI -- settings where server infrastructure, network connectivity, and training data are all unavailable. Existing vector-search systems assume a persistent server, gigabytes of RAM, or a training pass over the corpus; MonaVec instead targets the deployment profile of SQLite: one file, one function call, runs anywhere. Its quantization core is training-free by default and data-oblivious: a Randomized Hadamard Transform (RHDH) conditions any input distribution toward N(0,1), so precomputed Lloyd-Max tables quantize to 4 bits (8x smaller) with no learned codebook and no data pass. The index persists as a single .mvec file whose embedded ChaCha20 rotation seed makes results reproducible across architectures and byte-identical within a build -- a determinism guarantee that parallel-build graph libraries cannot offer. On semantic embeddings (AG News, 45K x 1024-dim BGE-M3, cosine), MonaVec 4-bit BruteForce reaches 0.960 Recall@10 in 27 MB -- leading float32 FAISS-IVF and 8-bit usearch on recall -- while trading peak throughput for byte-identical determinism. A single-pass global standardization (fit()
Autonomous AI agents can execute complex tasks with limited human review, yet they often lack the grounded operational knowledge to make their outputs not just executable but correct, secure, and maintainable. We introduce SkillCenter, to our knowledge the largest open skill library for agents by total count: 216,938 structured skills across 24 domain bundles. A SkillGate-filtered pipeline contributes 114,565 source-grounded skills from peer-reviewed journals, ArXiv, and over 24,000 technical sources, integrated with 102,373 community skills from GitHub and the ClawHub marketplace. We present the end-to-end framework that builds the pipeline subset: multi-source acquisition, an LLM-based quality gate (SkillGate), template-driven generation, iterative source-grounding, and quality-controlled publishing. Source grounding is a traceability guarantee: each retained claim maps to an exact quotation in its source. All skills ship as offline-searchable SQLite FTS5 bundles.
Production analytics products often depend on reusable methodologies: multi-step definitions such as headcount growth, top-skill growth, or differentially-private impression distributions. Although these methodologies define business-critical numbers, they are commonly implemented as imperative glue around OLAP queries, service calls, joins, transformations, and conditional logic. As a result, teams duplicate orchestration code, definitions drift across products, and methodologies are difficult to test or analyze. We present QDAG, a production system at LinkedIn that represents an analytics methodology as a declarative directed acyclic graph of typed steps. Nodes may execute Apache Pinot queries, downstream service calls, in-memory SQLite joins, jq transformations, conditionals, differentially-private aggregations, or calls to other QDAGs. The engine evaluates graphs demand-driven, memoized, pruned, and parallelized in the per-request analytics mid-tier. QDAG is deployed across more than 500 hosts and over 100 production use cases, adding roughly 10 ms median orchestration overhead and under 50 ms at the 99th percentile. Our experience shows that making methodologies declarative im
Many administrative processes, such as internship agreement processes, often rely on manual approval workflows and centralized record-keeping. This makes the process susceptible to delays and unauthorized modification while introducing limited traceability. This study presents StajChain, a permissioned blockchain-based multi-party internship management system developed using Hyperledger Fabric. The proposed system implements the complete internship agreement lifecycle through smart contracts and enforces role-based authorization using Hyperledger Fabric CA. The architecture consists of a React frontend, a NodeJS backend, an off-chain SQLite database, and the on-chain Fabric ledger. Users such as students, companies, faculty internship committee members, and the central internship unit can perform specified operations according to their role and identity. The agreement lifecycle follows predefined sequential steps, and at each step, the ledger status is updated and recorded securely. Furthermore, the system was evaluated using functional and performance tests, indicating acceptable throughput and latency for verifiable administrative workflows. This implementation demonstrates how p
Moltbook is a social media platform in which posts and comments are authored exclusively by autonomous AI agents. We present the Moltbook Observatory Archive, an incremental dataset that passively records agent profiles, posts, comments, community metadata (``submolts''), platform-level time-series snapshots, and word-frequency trend aggregates obtained by continuously polling the Moltbook API. Data are stored in a live SQLite observatory database and exported as date-partitioned Parquet files to enable efficient analysis and reproducible research. The documented release covers 78~days of platform activity (2026-01-27 to 2026-04-14) and contains 2,615,098~posts and 1,213,007~comments from 175,886~unique posting agents across 6,730~communities. This is, to our knowledge, the first large-scale observational dataset of a social network populated exclusively by autonomous AI agents. The archive is intended to support research on multi-agent communication, emergent social behavior, and safety-relevant phenomena in agent-only online environments, and it is released under the MIT license with code for collection and export.
Database Management System (DBMS) developers have implemented extensive test suites to test their DBMSs. For example, the SQLite test suites contain over 92 million lines of code. Despite these extensive efforts, test suites are not systematically reused across DBMSs, leading to wasted effort. Integration is challenging, as test suites use various test case formats and rely on unstandardized test runner features. We present a unified test suite, SQuaLity, in which we integrated test cases from three widely-used DBMSs, SQLite, PostgreSQL, and DuckDB. In addition, we present an empirical study to determine the potential of reusing these systems' test suites. Our results indicate that reusing test suites is challenging: First, test formats and test runner commands vary widely; for example, SQLite has 4 test runner commands, while MySQL has 112 commands with additional features, to, for example, execute file operations or interact with a shell. Second, while some test suites contain mostly standard-compliant statements (e.g., 99% in SQLite), other test suites mostly test non-standardized functionality (e.g., 31% of statements in the PostgreSQL test suite are nonstandardized). Third, te
Database systems incorporate an ever-growing number of functions in their kernels (a.k.a., database native functions) for scenarios like new application support and business migration. This growth causes an urgent demand for automatic database native function synthesis. While recent advances in LLM-based code generation (e.g., Claude Code) show promise, they are too generic for database-specific development. They often hallucinate or overlook critical context because database function synthesis is inherently complex and error-prone, where synthesizing a single function may involve registering multiple function units, linking internal references, and implementing logic correctly. To this end, we propose DBCooker, an LLM-based system for automatically synthesizing database native functions. It consists of three components. First, the function characterization module aggregates multi-source declarations, identifies function units that require specialized coding, and traces cross-unit dependencies. Second, we design operations to address the main synthesis challenges: (1) a pseudo-code-based coding plan generator that constructs structured implementation skeletons by identifying key el
In this paper, we present a tool for analyzing .NET CLR event logs based on a novel method inspired by Natural Language Processing (NLP) approach. Our research addresses the growing need for effective monitoring and optimization of software systems through detailed event log analysis. We utilize a BERT-based architecture with an enhanced tokenization process customized to event logs. The tool, developed using Python, its libraries, and an SQLite database, allows both conducting experiments for academic purposes and efficiently solving industry-emerging tasks. Our experiments demonstrate the efficacy of our approach in compressing event sequences, detecting recurring patterns, and identifying anomalies. The trained model shows promising results, with a high accuracy rate in anomaly detection, which demonstrates the potential of NLP methods to improve the reliability and stability of software systems.
The complexity of modern Just-In-Time (JIT) compiler optimization poses significant challenges for developers seeking to understand and debug intermediate representation (IR) behavior. This work introduces JITScope, an interactive visualization framework that illustrates how IR nodes and instructions evolve across compilation phases. The system features a full-stack architecture: a Python-based backend transforms raw JSON-formatted IR data-representing an abstract model of the JIT compiler IR-into a normalized SQLite database; a controller layer serves processed CSV data; and a D3.js-powered frontend renders an interactive, phase-aware graph of IR node transformations. The design emphasizes modularity, traceability, and flexibility. Our roadmap explores intuitive visual representations of phase-level changes in IR node connectivity, values, and access patterns. Ultimately, JITScope lays a foundation for future tooling that enables visual exploration of IR evolution, including phase filtering, value tracking, and function-access mapping-offering a new lens into the behaviors and impacts of compiler optimizations.
Open-domain table question answering traditionally relies on a two-stage pipeline: static table retrieval followed by a closed-domain answer. In contrast, we propose an end-to-end agentic framework that embeds multi-turn tool calls-using a BM25+-based search API and a SQLite SQL executor-directly into a large language model. To further adapt a compact 4B-parameter model, we introduce a two-stage fine-tuning process: supervised cold-start on easy questions, then Async GRPO reinforcement learning on harder cases with LoRA adapters and a rollout buffer. This unified approach enables the model to jointly retrieve, reason, and execute queries, yielding a dramatic accuracy improvement from single-digit zero-shot performance to over 0.86 exact match on a held-out test set. Our results underscore the effectiveness of integrating structured tool calls with targeted RL fine-tuning for scalable, accurate table QA. The code is available at https://github.com/TabibitoQZP/OpenTableR1.
This study presents the development of Geolog-IA, a novel conversational system based on artificial intelligence that responds naturally to questions about geology theses from the Central University of Ecuador. Our proposal uses the Llama 3.1 and Gemini 2.5 language models, which are complemented by a Retrieval Augmented Generation (RAG) architecture and an SQLite database. This strategy allows us to overcome problems such as hallucinations and outdated knowledge. The evaluation of Geolog-IA's performance with the BLEU metric reaches an average of 0.87, indicating high consistency and accuracy in the responses generated. The system offers an intuitive, web-based interface that facilitates interaction and information retrieval for directors, teachers, students, and administrative staff at the institution. This tool can be a key support in education, training, and research and establishes a basis for future applications in other disciplines.