BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:LaMET-Agent: Agentic Workflow for Large-Momentum Effective Theory 
 Analysis
DTSTART;VALUE=DATE-TIME:20261011T063000Z
DTEND;VALUE=DATE-TIME:20261011T065000Z
DTSTAMP;VALUE=DATE-TIME:20261005T083337Z
UID:indico-contribution-2763@indico.itp.ac.cn
DESCRIPTION:Speakers: 殿君 赵 (CUHK(SZ))\nExtracting light-cone parton 
 distributions from lattice QCD within Large-Momentum Effective Theory (LaM
 ET) requires a multi-stage data-reduction pipeline: fitting Euclidean corr
 elators for hadronic matrix elements\, renormalizing the resulting matrix 
 elements\, extending and Fourier-transforming them to momentum space\, mat
 ching to light-cone distributions in perturbation theory\, and extrapolati
 ng to the continuum\, infinite-volume\, and physical-mass limits. Several 
 of these stages are procedurally fixed once a scheme is chosen\, but other
 s require a physicist to judge fit windows\, ansatz choices\, and model-av
 eraging strategies from the data itself\, which makes the full pipeline sl
 ow to execute and difficult to reproduce across practitioners. We present 
 \\lamet\, an open-source large language model (LLM) agent framework that f
 ormalizes this pipeline as a declarative\, job-based manifest and exposes 
 each analysis stage as a registry of typed numerical tools. A tool-calling
  LLM loop drives the stages that require strategy selection\, guided by st
 age-local ``skill'' prompts that encode the underlying physics heuristics\
 , while stages that are procedurally fixed run as deterministic tool pipel
 ines. We describe the resulting architecture\, validate the agent-in-the-l
 oop correlator-fitting stage on synthetic two-point-function data\, and ou
 tline its application to an end-to-end pion quasi-parton-distribution-func
 tion (quasi-PDF) workflow in the Coulomb-gauge formulation of LaMET. This 
 paper documents the design and first release\, \\lamet\\ v1.0\, of the fra
 mework.\n\nhttps://indico.itp.ac.cn/event/437/contributions/2763/
LOCATION:会议楼2 CXII103
URL:https://indico.itp.ac.cn/event/437/contributions/2763/
END:VEVENT
END:VCALENDAR