{"paper":{"title":"EconAI: Dynamic Persona Evolution and Memory-Aware Agents in Evolving Economic Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"EconAI is the first LLM-powered system to simulate macro and micro economic interactions together in one adaptive framework.","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Annie Liu, Lang Chen, Zane Cao, Zigan Wang, Zongxin Xu","submitted_at":"2026-05-13T16:41:21Z","abstract_excerpt":"The integration of large language models (LLMs) in economic simulations has significantly enhanced agent-based modeling, yet existing frameworks struggle to capture the interplay between short-term optimization and long-term strategic planning. Conventional approaches rely on static data-driven predictions, failing to incorporate adaptive behaviors influenced by economic sentiment, market volatility, and individual goals. To address these limitations, we introduce a novel EconAI framework, incorporating economic sentiment indexing (ESI), memory weighting, and dynamic decision-making mechanisms"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"It is the first LLM-powered simulation system that can simulate the macro/microeconomic environment and interactions in a unified framework.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That adding economic sentiment indexing and memory weighting to standard LLM agents will produce measurably more stable and human-like employment-consumption cycles without further validation against real economic data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EconAI adds memory weighting and economic sentiment indexing to LLM agents so they adapt short-term actions to long-term goals inside a single macro/micro simulation loop.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"EconAI is the first LLM-powered system to simulate macro and micro economic interactions together in one adaptive framework.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c64bf3463ffc53a75ab39723804010db41f3f55c7a86bfd50ce634e362eb8b34"},"source":{"id":"2605.13762","kind":"arxiv","version":1},"verdict":{"id":"50e33b62-0c4c-4bfc-a2b3-89a8c3d4378d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T17:40:42.149449Z","strongest_claim":"It is the first LLM-powered simulation system that can simulate the macro/microeconomic environment and interactions in a unified framework.","one_line_summary":"EconAI adds memory weighting and economic sentiment indexing to LLM agents so they adapt short-term actions to long-term goals inside a single macro/micro simulation loop.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That adding economic sentiment indexing and memory weighting to standard LLM agents will produce measurably more stable and human-like employment-consumption cycles without further validation against real economic data.","pith_extraction_headline":"EconAI is the first LLM-powered system to simulate macro and micro economic interactions together in one adaptive framework."},"references":{"count":48,"sample":[{"doi":"","year":null,"title":"GPT in game theory experiments.arXiv preprint arXiv:2305.05516https://arxiv.org/abs/2305 .05516 (2024)","work_id":"07d32a9a-b970-497d-a54f-64b9bcd2751d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Put your money where your mouth is: Evaluating strategic planning and execution of LLM agents in an auction arena","work_id":"e2738d0f-b240-4cad-8f58-4ab275058560","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2310.17512 , year=","work_id":"a6e40e52-e487-4fd1-b455-3e5d33d67656","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Playing repeated games with large language models.arXiv preprint arXiv:2305.16867","work_id":"7273af04-dee7-401d-96f4-63c7a60137c1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2305.12763 , year=","work_id":"4d32356b-45cc-49ca-b8f3-17797fd4c4d2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":48,"snapshot_sha256":"e766fe6882c980f76e7992ac4081fb6b3db967930004939e9398586ae0047599","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7532fc886c4270b4410f7cc4d4f88216e4b28adcefd91c9cfe4a1ccf464fbd16"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}