BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.adass.org//adass2026//talk//WR3GKK
BEGIN:VTIMEZONE
TZID:AWST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=20051231T160000Z
TZNAME:AWST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
BEGIN:STANDARD
DTSTART:20070325T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:AWST
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20071028T030000
RRULE:FREQ=YEARLY;BYDAY=4SU;BYMONTH=10;UNTIL=20081025T190000Z
TZNAME:AWDT
TZOFFSETFROM:+0800
TZOFFSETTO:+0900
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-adass2026-WR3GKK@pretalx.adass.org
DTSTART;TZID=AWST:20261102T143000
DTEND;TZID=AWST:20261102T144500
DESCRIPTION:Astronomical data discovery often requires identifying appropri
 ate archives\, resolving astronomical object names and coordinates\, trans
 lating observational constraints into service-specific query parameters\, 
 and interpreting complex metadata returned by heterogeneous data services.
  Although the Astroquery Python package provides programmatic access to ma
 ny astronomical archives\, coordinating these resources still requires det
 ailed knowledge of individual interfaces. We present AstroAKD\, a data-sea
 rch agent developed within NASA IMPACT’s Accelerated Knowledge Discovery
  (AKD) ecosystem\, a modular platform for developing\, evaluating\, and de
 ploying scientific AI agents that connect natural-language reasoning with 
 external data and software services.\n\nAstroAKD employs a [Model Context 
 Protocol (MCP) server](https://github.com/nasa-impact/astroquery-mcp) buil
 t on Astroquery that dynamically exposes supported archive functions to a 
 large language model (LLM) agent. At runtime\, the agent discovers availab
 le functions\, inspects their parameters\, converts structured requests in
 to astronomy-specific objects such as coordinates and unit-bearing quantit
 ies\, and normalizes returned tables and metadata into machine-readable re
 sponses. Supported services include SIMBAD\, ADS\, MAST\, HEASARC\, IRSA\,
  NED\, Gaia\, VizieR\, and Virtual Observatory resources.\n\nGiven a scien
 tific request\, AstroAKD resolves target identifiers\, extracts observatio
 nal constraints\, selects appropriate services\, constructs executable que
 ries\, and returns relevant metadata and candidate datasets with archive p
 rovenance. We describe the agent architecture and evaluate representative 
 single- and multi-archive workflows using archive and function selection\,
  parameter correctness\, task completion\, and recovery from ambiguous ide
 ntifiers\, empty results\, and unavailable services. Benchmark requests\, 
 tool calls\, and outputs are retained as inspectable traces for validation
  and repeatability. AstroAKD demonstrates how domain-specific AI agents an
 d standardized tool interfaces can support transparent\, rapid exploration
  of astronomical archives.
DTSTAMP:20261001T111430Z
LOCATION:Banquet Hall
SUMMARY:AstroAKD: An MCP-Based Agent for Natural-Language Search of Astrono
 mical Archives - Ashkbiz Danehkar
URL:https://pretalx.adass.org/adass2026/talk/WR3GKK/
END:VEVENT
END:VCALENDAR