The paper introduces Sophrosyne, a system that moderates LLM agent exploration in relational data systems, significantly reducing over-exploration and boosting SQL generation accuracy by guiding the a…

This paper proposes Trellis, a data foundation that treats experience graphs from long-horizon agentic tasks as first-class, governed, queryable database state.

SpecDB is a novel system that uses LLMs to synthesize highly customized, purpose-built relational databases, achieving performance comparable to commercial systems while significantly reducing code si…

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

SessionBound is a system that creates short-lived, budgeted, and auditable database sessions for AI agents based on approved enterprise tasks.

Jailbreak bypasses database engines by reading storage files directly and materializing data as in-memory columnar buffers using LLM-assisted code synthesis.

The paper proposes PROTECT-DB, a practical system utilizing Byzantine-fault tolerant replicated state machines built on PostgreSQL to achieve efficient, concurrent detection and recovery from database…

This paper proposes an organizational memory for LLM-based agents to access and share enterprise-specific procedural knowledge for reliable business process execution.

The paper introduces DBA-Bench, a benchmark for evaluating database agents with production fidelity, outcome-first evaluation, and controlled scenario reproducibility.

This paper presents Vivace, a serverless system for exact temporal OLAP over interval histories, which addresses the issues of incomplete data and incorrect answers in serverless functions.

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

This paper introduces the Always-On Evaluation Protocol (AOEP-v0) for evaluating always-on agents by focusing on state mutation and recovery obligations.

The paper introduces ERUnderstand, a benchmark for structured understanding of Entity-Relationship Diagrams (ERDs) with machine-readable representations for 2,960 diagrams.

The paper introduces Post-Deterministic Distributed Systems (PDDS) as a new model to coordinate autonomous infrastructure where participants, including stochastic agents, produce divergent reasoning p…

The paper proposes a novel hybrid authorization framework that combines roles and First-Order Logic to enforce fine-grained, triple-level access control for autonomous agents interacting with knowledg…

The paper argues that current Software Bills of Materials (SBOMs) are fundamentally flawed due to a lack of shared understanding regarding what constitutes a 'component,' demonstrating that existing t…

The paper evaluates two novel LLM-based systems, RADAGAS and RefleXQLi, for generating adversarial SQL injection payloads, finding that RADAGAS-GPT4o achieves a high bypass rate, particularly against…

The paper introduces the concept of the atomic decision boundary, proving that for autonomous systems to guarantee execution-time admissibility, the decision and the resulting state transition must oc…

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex be…