Papers for

enterprise ai integration teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Anassa breaks down spatial ai framework into executable architecture

ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI

Abstract: Agentic AI systems operating over geospatial data require more than autonomous reasoning and tool use; they must also support explicit orchestration, spatial validation, governance, provenance, failure handling, and human decision authority. Prior work introduced ANASSA, an agentic AI orchestration framework for spatial intelligence that established high-level components and responsibility boundaries for governed agentic execution (arXiv:2609.14824). However, the framework did not specify how those high-level responsibilities should be systematically decomposed into an implementation-facing low-level architecture. This paper addresses that gap by applying Design Science Research (DSR) to refine the ANASSA framework from high-level architectural (HLA) responsibilities into a low-level architecture (LLA). The resulting design preserves the responsibility boundaries of the foundational framework while translating them into executable architectural structures, including 47 logical roles, versioned task graphs, capability-based agent selection, typed contracts, explicit runtime states, spatial validation mechanisms, governance controls, failure and recovery paths, and provenance records. The architecture is demonstrated through an end-to-end execution trace and analytically evaluated for requirements traceability, internal consistency, responsibility preservation, and technology independence. The resulting high-level-to-low-level design provides an implementation-facing bridge between the ANASSA framework and future system implementations, defining how governed spatial agentic workflows can be made inspectable, reconstructable, and testable without binding the architecture to a specific AI model, geospatial platform, communication protocol, or deployment environment.

Fri 9 OctArtificial IntelligenceMultiagent SystemsSoftware Engineering
The gist
Spatial AI systems need to do more than just think on their own—they must also manage tasks like checking locations, handling errors, and keeping humans in control. The authors had developed a big-picture plan for such systems but hadn't explained how to build them exactly. In this paper, they turned that plan into a detailed and practical design with clear roles and processes to make these systems work smoothly and safely. This design works independently of specific AI tools or software, so it can be adapted widely.
Open → 2610.14382v1

Skill packages improve financial AI agents for portfolio and risk tasks

Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows

Abstract: Financial AI agents must do more than retrieve facts: investment workflows require correct quantitative execution, reliable use of procedural resources, and auditable structured outputs. We introduce FinSkillBench, an evaluation suite of 2,603 point in time episodes across 12 subtasks in portfolio construction, risk management, and fundamental analysis, with hidden regenerable ground truth and task specific deterministic verifiers. Executing 17,820 episodes across 9 models and 3 resource conditions, the paired analysis across 8 models shows that curated skill packages raise mean scores by +16.2 points (0.366 to 0.528), whereas skills generated within a single episode add only +0.5 points while consuming more tokens and turns. We then decompose the curated premium by granting human authored procedural documents and executable domain tools separately: documents alone add +5.6 points, tools alone add +19.5 points, and their combination is subadditive. The premium is strongly workflow dependent: executable tools dominate numerically intensive workflows, documentation matters more when procedural or output schema guidance is the bottleneck, and interpretive tasks benefit from both. The effects are sign stable across 10 scoring variants and cluster bootstrap analyses, and an independently implemented second harness reproduces the directional pattern while showing that effect magnitudes depend on how tools and data are exposed. Overall, a measured "skill premium" is a property of the full model, resource, and harness system rather than of the underlying model alone.

Fri 2 OctArtificial Intelligence
The gist
FinSkillBench is a new test suite that checks how well financial AI agents perform tasks involving investment and risk management. The authors found that using pre-made skill sets helps the agents do better than creating skills on the fly. They separated the effects of human-written instructions and automated tools, showing tools help more with number-heavy tasks while instructions help where procedures matter. This means the whole system of model, tools, and instructions—rather than just the AI model—affects performance.
Open → 2610.03564v1