{"paper":{"title":"ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Adaptive prompt optimization lets LLM trading agents improve over time using noisy market feedback","cross_cats":["cs.AI"],"primary_cat":"q-fin.TR","authors_text":"Angeliki Dimitriou, Charidimos Papadakis, Giorgos Filandrianos, Giorgos Stamou, Konstantinos Thomas, Maria Lymperaiou","submitted_at":"2025-10-10T13:01:51Z","abstract_excerpt":"Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to synthesize heterogeneous information streams into coherent decisions, and how to bridge the gap between model outputs and executable market actions. We present ATLAS (Adaptive Trading with LLM AgentS), a unified multi-agent framework that integrates structured information from markets, news, and corporate fundamentals to support robust trading decisions. Within ATL"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Adaptive-OPRO consistently outperforms fixed prompts, while reflection-based feedback fails to provide systematic gains across regime-specific equity studies and multiple LLM families.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That real-time stochastic feedback from trading outcomes, despite arriving late and being obscured by market noise, can be effectively incorporated into prompt adaptation to produce systematic performance gains over time.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ATLAS is a multi-agent LLM trading system that employs Adaptive-OPRO for real-time prompt optimization using stochastic feedback, outperforming fixed prompts in equity regime studies across multiple model families.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Adaptive prompt optimization lets LLM trading agents improve over time using noisy market feedback","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9772b0c27ddca7e4e0583e33065a233955b881f7cc262de1e889b55f5833d0fd"},"source":{"id":"2510.15949","kind":"arxiv","version":5},"verdict":{"id":"0117f3b7-cfe1-4d9a-b58f-5d5e54df6cb9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T08:16:46.812492Z","strongest_claim":"Adaptive-OPRO consistently outperforms fixed prompts, while reflection-based feedback fails to provide systematic gains across regime-specific equity studies and multiple LLM families.","one_line_summary":"ATLAS is a multi-agent LLM trading system that employs Adaptive-OPRO for real-time prompt optimization using stochastic feedback, outperforming fixed prompts in equity regime studies across multiple model families.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That real-time stochastic feedback from trading outcomes, despite arriving late and being obscured by market noise, can be effectively incorporated into prompt adaptation to produce systematic performance gains over time.","pith_extraction_headline":"Adaptive prompt optimization lets LLM trading agents improve over time using noisy market feedback"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.15949/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}