{"id":764,"date":"2025-04-14T09:24:49","date_gmt":"2025-04-14T07:24:49","guid":{"rendered":"https:\/\/ibex.tudelft.nl\/?p=764"},"modified":"2025-04-14T09:28:24","modified_gmt":"2025-04-14T07:28:24","slug":"764","status":"publish","type":"post","link":"https:\/\/ibex.tudelft.nl\/?p=764","title":{"rendered":"EconAgents live on GitHub"},"content":{"rendered":"\n[et_pb_section fb_built=”1″ _builder_version=”4.23″ _module_preset=”default” custom_padding=”0px|||||” global_colors_info=”{}”][et_pb_row _builder_version=”4.23″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.23″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.23″ _module_preset=”default” custom_padding=”0px|||||” global_colors_info=”{}”]

Last year the IBEX lab received a subsidy from NWO to build a Multi-Actor LLM tool that can be used to automate experiments with LLM agents.\u00a0 A first version of the tool is now available on GitHub.<\/p>\n

The tool consists of a Python package that allows you:<\/p>\n

– to connect to a server that runs a game, as a python script, as a local server, or online<\/p>\n

– initiate different players with different roles, different LLM models, and different prompts<\/p>\n

– manage the information state of each of the each role actor<\/p>\n

– specify how the players respond to the server to provide their chosen action<\/p>\n

 <\/p>\n

an example game, repeated prisoners dillema, is part of the package already. So are the implementation of more complicated choices of our Futarchy for Spatial Planning via Harberger Taxation | IBEX-lab<\/a> experiment ( but you will have to provide the server for that).<\/p>\n

\u00a0Python library:<\/p>\n

IBEX-TUDelft\/econagents<\/a><\/p>\n

with documentation here:<\/p>\n

https:\/\/econagents.readthedocs.io\/<\/a>\u00a0<\/p>\n

 <\/p>\n

 <\/p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section]\n","protected":false},"excerpt":{"rendered":"

Last year the IBEX lab received a subsidy from NWO to build a Multi-Actor LLM tool that can be used to automate experiments with LLM agents.\u00a0 A first version of the tool is now available on GitHub. The tool consists of a Python package that allows you: – to connect to a server that runs […]<\/p>\n","protected":false},"author":5,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[10,11],"tags":[],"class_list":["post-764","post","type-post","status-publish","format-standard","hentry","category-news","category-projects"],"_links":{"self":[{"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=\/wp\/v2\/posts\/764","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=764"}],"version-history":[{"count":5,"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=\/wp\/v2\/posts\/764\/revisions"}],"predecessor-version":[{"id":771,"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=\/wp\/v2\/posts\/764\/revisions\/771"}],"wp:attachment":[{"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=764"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=764"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ibex.tudelft.nl\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=764"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}