arXiv subjects

Jacopo Tagliabue

Publications and source records attributed to Jacopo Tagliabue.

At least 19 recordsLinked to original sources

arXiv2026

Not Your Usual Type(s): Data contracts as types across languages and engines

Composable data systems promise to let developers combine languages, engines, and catalogs without sacrificing a coherent user experience. In practice, however, pipeline-node boundaries remain weakly specified: transformations exchange tables through schemas that are often checked late, enforced unevenly across languages, and disconnected from the semantics business users care about. Based on over a year of operating millions of jobs in Bauplan, we share the design principles behind our new SDK, which treats data contracts as types for a composable, multi-language lakehouse. Users, whether humans or agents, annotate input and output tables with schema objects that encode column types, constraints, documentation, and lineage; Bauplan then interprets these annotations at different points in the execution lifecycle. We show how this design addresses common production failures, and how an ''everything-as-code'' philosophy enables both deterministic and non-deterministic reasoning over data flows across languages and engines.

cs.DB↗

arXiv2026

GitLake: Git-for-data for the agentic lakehouse

We present GitLake, a Git-for-data design for an agent-first lakehouse. The system lifts single-table Iceberg snapshots into lakehouse-wide commits, branches, and merges, letting agents work on isolated branches while humans review and publish changes. Pipelines run on temporary branches and publish through a final merge, so all outputs become visible atomically or none do. Finally, we report production lessons as well as correctness insights from a preliminary Alloy model of our core abstractions.

cs.DB↗

arXiv2026

"Skill Issues'': Data-Centric Optimization of Lakehouse Agents

Coding agents are becoming users of data infrastructure, but their success depends not only on model quality: it also depends on the skills and environment files that teach agents how to use a system. We study how to optimize these artifacts for agents operating on a branching lakehouse, Bauplan. In our setting, headless APIs and Git-like data primitives expose data workflows through code, branches, commits, and merges. Our central observation is that a branching lakehouse turns data-agent evaluation from an output-matching problem into a state-verification problem: agent-generated pipeline code induces concrete, inspectable lakehouse changes. We present a data-centric optimization pipeline that generates task-verifier pairs, executes candidate skills in isolated sandboxes, and scores trajectories using both trace-level signals and programmatic checks over lakehouse state. In a preliminary evaluation on hundreds of tasks, optimized skills improve held-out reward by up to 28.6%. These results suggest that write-path data workflows provide a useful substrate for optimizing agent skills beyond read-only tasks.

cs.AI↗

arXiv2026

Building a Correct-by-Design Lakehouse. Data Contracts, Versioning, and Transactional Pipelines for Humans and Agents

Lakehouses are now the default substrate for analytics and AI, but they remain fragile under concurrent, untrusted change: schema mismatches often surface only at runtime, development and production easily diverge, and multi-table pipelines can expose partial results after failure. We present Bauplan, a code-first lakehouse that aims to eliminate a broad class of these failures by construction. Bauplan builds on a storage substrate that already provides atomic single-table snapshot evolution, and adds three pipeline-level correctness mechanisms: typed table contracts to make transformation boundaries checkable, Git-like data versioning to support reproducible collaboration and review, and transactional runs that guarantee atomic publication of an entire pipeline execution. We describe the system design, show how these abstractions fit together into a unified programming model for humans and agents, and report early results from a lightweight Alloy model that both validates key intuitions and exposes subtle counterexamples around transactional branch visibility. Our experience suggests that correctness in the lakehouse is best addressed not by patching failures after the fact, but by restricting the programming model so that many illegal states become unrepresentable.

cs.DC↗

arXiv2026

Querying Everything Everywhere All at Once: Supervaluationism for the Agentic Lakehouse

Agentic analytics is turning the lakehouse into a multi-version system: swarms of (human or AI) producers materialize competing pipelines in data branches, while (human or AI) consumers need answers without knowing the underlying data life-cycle. We demonstrate a new system that answers questions across branches rather than at a single snapshot. Our prototype focuses on a novel query path that evaluates queries under supervaluationary semantics. In the absence of comparable multi-branch querying capabilities in mainstream OLAP systems, we open source the demo code as a concrete baseline for the OLAP community.

cs.DB↗

arXiv2026

Test-Time Optimization of Physical Query Plans with LLMs

Traditional query optimization relies on cost-based optimizers that estimate execution cost (e.g., runtime, memory, and I/O) using predefined heuristics and statistical models. Improving these requires substantial engineering effort, yet they often cannot exploit semantic correlations in queries and schemas that could enable better physical plans. Large language models (LLMs), however, can reason about column semantics, value distributions, and broader domain context that classical statistics miss. We introduce DBPlanBench, a harness for the DataFusion engine that exposes physical plans through a compact serialized representation and applies LLM-proposed edits as JSON patches. On this harness, we instantiate a test-time optimization workflow where an LLM examines physical query plans, proposes localized edits based on semantic reasoning, and an evolutionary search refines the candidates across iterations. We target OLAP queries, where heavy, repeated execution turns even small efficiency gains into substantial cumulative savings. We specifically focus our evaluation on join reordering and join-side selection, where cardinality-estimation errors compound multiplicatively. Median speedups reach $1.10$-$1.12\times$ on TPC-H and $1.05$-$1.07\times$ on TPC-DS, with some achieving up to $4.78\times$. We also demonstrate that optimizations discovered at small scale factors transfer effectively to larger ones, supporting a low-cost small-to-large workflow.

cs.DB↗

arXiv2025

Trustworthy AI in the Agentic Lakehouse: from Concurrency to Governance

Even as AI capabilities improve, most enterprises do not consider agents trustworthy enough to work on production data. In this paper, we argue that the path to trustworthy agentic workflows begins with solving the infrastructure problem first: traditional lakehouses are not suited for agent access patterns, but if we design one around transactions, governance follows. In particular, we draw an operational analogy to MVCC in databases and show why a direct transplant fails in a decoupled, multi-language setting. We then propose an agent-first design, Bauplan, that reimplements data and compute isolation in the lakehouse. We conclude by sharing a reference implementation of a self-healing pipeline in Bauplan, which seamlessly couples agent reasoning with all the desired guarantees for correctness and trust.

cs.AI↗

arXiv2025

AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators

We explore AI-driven distributed-systems policy design by combining stochastic code generation from large language models (LLMs) with deterministic verification in a domain-specific simulator. Using a Function-as-a-Service runtime (Bauplan) and its open-source simulator (Eudoxia) as a case study, we frame scheduler design as an iterative generate-and-verify loop: an LLM proposes a Python policy, the simulator evaluates it on standardized traces, and structured feedback steers subsequent generations. This setup preserves interpretability while enabling targeted search over a large design space. We detail the system architecture and report preliminary results on throughput improvements across multiple models. Beyond early gains, we discuss the limits of the current setup and outline next steps; in particular, we conjecture that AI will be crucial for scaling this methodology by helping to bootstrap new simulators.

cs.DC↗

arXiv2025

Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse

Data lakehouses run sensitive workloads, where AI-driven automation raises concerns about trust, correctness, and governance. We argue that API-first, programmable lakehouses provide the right abstractions for safe-by-design, agentic workflows. Using Bauplan as a case study, we show how data branching and declarative environments extend naturally to agents, enabling reproducibility and observability while reducing the attack surface. We present a proof-of-concept in which agents repair data pipelines using correctness checks inspired by proof-carrying code. Our prototype demonstrates that untrusted AI agents can operate safely on production data and outlines a path toward a fully agentic lakehouse.

cs.AI↗

arXiv2025

Eudoxia: a FaaS scheduling simulator for the composable lakehouse

Due to the variety of its target use cases and the large API surface area to cover, a data lakehouse (DLH) is a natural candidate for a composable data system. Bauplan is a composable DLH built on "spare data parts" and a unified Function-as-a-Service (FaaS) runtime for SQL queries and Python pipelines. While FaaS simplifies both building and using the system, it introduces novel challenges in scheduling and optimization of data workloads. In this work, starting from the programming model of the composable DLH, we characterize the underlying scheduling problem and motivate simulations as an effective tools to iterate on the DLH. We then introduce and release to the community Eudoxia, a deterministic simulator for scheduling data workloads as cloud functions. We show that Eudoxia can simulate a wide range of workloads and enables highly customizable user implementations of scheduling algorithms, providing a cheap mechanism for developers to evaluate different scheduling algorithms against their infrastructure.

cs.DB↗

arXiv2025

Zerrow: True Zero-Copy Arrow Pipelines in Bauplan

Bauplan is a FaaS-based lakehouse specifically built for data pipelines: its execution engine uses Apache Arrow for data passing between the nodes in the DAG. While Arrow is known as the "zero copy format", in practice, limited Linux kernel support for shared memory makes it difficult to avoid copying entirely. In this work, we introduce several new techniques to eliminate nearly all copying from pipelines: in particular, we implement a new kernel module that performs de-anonymization, thus eliminating a copy to intermediate data. We conclude by sharing our preliminary evaluation on different workloads types, as well as discussing our plan for future improvements.

cs.OS↗

arXiv2024

FaaS and Furious: abstractions and differential caching for efficient data pre-processing

Data pre-processing pipelines are the bread and butter of any successful AI project. We introduce a novel programming model for pipelines in a data lakehouse, allowing users to interact declaratively with assets in object storage. Motivated by real-world industry usage patterns, we exploit these new abstractions with a columnar and differential cache to maximize iteration speed for data scientists, who spent most of their time in pre-processing - adding or removing features, restricting or relaxing time windows, wrangling current or older datasets. We show how the new cache works transparently across programming languages, schemas and time windows, and provide preliminary evidence on its efficiency on standard data workloads.

cs.DB↗

arXiv2024

Bauplan: zero-copy, scale-up FaaS for data pipelines

Chaining functions for longer workloads is a key use case for FaaS platforms in data applications. However, modern data pipelines differ significantly from typical serverless use cases (e.g., webhooks and microservices); this makes it difficult to retrofit existing pipeline frameworks due to structural constraints. In this paper, we describe these limitations in detail and introduce bauplan, a novel FaaS programming model and serverless runtime designed for data practitioners. bauplan enables users to declaratively define functional Directed Acyclic Graphs (DAGs) along with their runtime environments, which are then efficiently executed on cloud-based workers. We show that bauplan achieves both better performance and a superior developer experience for data workloads by making the trade-off of reducing generality in favor of data-awareness

cs.DB↗

arXiv2024

Reproducible data science over data lakes: replayable data pipelines with Bauplan and Nessie

As the Lakehouse architecture becomes more widespread, ensuring the reproducibility of data workloads over data lakes emerges as a crucial concern for data engineers. However, achieving reproducibility remains challenging. The size of data pipelines contributes to slow testing and iterations, while the intertwining of business logic and data management complicates debugging and increases error susceptibility. In this paper, we highlight recent advancements made at Bauplan in addressing this challenge. We introduce a system designed to decouple compute from data management, by leveraging a cloud runtime alongside Nessie, an open-source catalog with Git semantics. Demonstrating the system's capabilities, we showcase its ability to offer time-travel and branching semantics on top of object storage, and offer full pipeline reproducibility with a few CLI commands.

cs.DB↗

arXiv2024

How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis

Negotiation is the basis of social interactions; humans negotiate everything from the price of cars to how to share common resources. With rapidly growing interest in using large language models (LLMs) to act as agents on behalf of human users, such LLM agents would also need to be able to negotiate. In this paper, we study how well LLMs can negotiate with each other. We develop NegotiationArena: a flexible framework for evaluating and probing the negotiation abilities of LLM agents. We implemented three types of scenarios in NegotiationArena to assess LLM's behaviors in allocating shared resources (ultimatum games), aggregate resources (trading games) and buy/sell goods (price negotiations). Each scenario allows for multiple turns of flexible dialogues between LLM agents to allow for more complex negotiations. Interestingly, LLM agents can significantly boost their negotiation outcomes by employing certain behavioral tactics. For example, by pretending to be desolate and desperate, LLMs can improve their payoffs by 20\% when negotiating against the standard GPT-4. We also quantify irrational negotiation behaviors exhibited by the LLM agents, many of which also appear in humans. Together, \NegotiationArena offers a new environment to investigate LLM interactions, enabling new insights into LLM's theory of mind, irrationality, and reasoning abilities.

cs.AI↗

arXiv2023

Building a serverless Data Lakehouse from spare parts

The recently proposed Data Lakehouse architecture is built on open file formats, performance, and first-class support for data transformation, BI and data science: while the vision stresses the importance of lowering the barrier for data work, existing implementations often struggle to live up to user expectations. At Bauplan, we decided to build a new serverless platform to fulfill the Lakehouse vision. Since building from scratch is a challenge unfit for a startup, we started by re-using (sometimes unconventionally) existing projects, and then investing in improving the areas that would give us the highest marginal gains for the developer experience. In this work, we review user experience, high-level architecture and tooling decisions, and conclude by sharing plans for future development.

cs.DB↗

arXiv2023

EvalRS 2023. Well-Rounded Recommender Systems For Real-World Deployments

EvalRS aims to bring together practitioners from industry and academia to foster a debate on rounded evaluation of recommender systems, with a focus on real-world impact across a multitude of deployment scenarios. Recommender systems are often evaluated only through accuracy metrics, which fall short of fully characterizing their generalization capabilities and miss important aspects, such as fairness, bias, usefulness, informativeness. This workshop builds on the success of last year's workshop at CIKM, but with a broader scope and an interactive format.

cs.IR↗

arXiv2023

(Vector) Space is Not the Final Frontier: Product Search as Program Synthesis

As ecommerce continues growing, huge investments in ML and NLP for Information Retrieval are following. While the vector space model dominated retrieval modelling in product search - even as vectorization itself greatly changed with the advent of deep learning -, our position paper argues in a contrarian fashion that program synthesis provides significant advantages for many queries and a significant number of players in the market. We detail the industry significance of the proposed approach, sketch implementation details, and address common objections drawing from our experience building a similar system at Tooso.

cs.IR↗