{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XNZKFRXSYVVT2ZHHGF7HSCTEAN","short_pith_number":"pith:XNZKFRXS","schema_version":"1.0","canonical_sha256":"bb72a2c6f2c56b3d64e7317e790a640342a2d632b5ef4ff9742c4546e0ca6907","source":{"kind":"arxiv","id":"2606.17838","version":1},"attestation_state":"computed","paper":{"title":"Environment-Grounded Automated Prompt Optimization for LLM Game Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lukas Fehring, Marius Lindauer, Matthias Feurer, Rean Clive Fernandes, Theresa Eimer","submitted_at":"2026-06-16T12:06:27Z","abstract_excerpt":"LLM agents in interactive environments are highly sensitive to their prompts, yet prompt engineering remains a manual, task-specific process. We introduce an automated prompt optimization framework for LLM agents that decomposes the observation-to-action pipeline into a goal-conditioned descriptor agent and an action selection agent, and iteratively refines each module's prompt through an LLM-driven evolutionary loop guided by environment returns. We propose a behavior analyzer to attribute episode outcomes to specific prompt components, and a mutator to propose targeted revisions to the promp"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.17838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T12:06:27Z","cross_cats_sorted":[],"title_canon_sha256":"a3e33bc970ce83bd6d308266fe08832ff89244801859c0f62717bab474ae719d","abstract_canon_sha256":"d413e7f01c3241e94c182fa0cf916c2dfa0d69ce159daa2acc453eae2d865784"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:41.025669Z","signature_b64":"Z95xU3y+l9Bh/LO8hkgPePIkfE5kmp0OelEP54fOV+DUE9Die/b6oLE6Fodb75Pe9mT86HI7KxZ+/Tk1ky5BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb72a2c6f2c56b3d64e7317e790a640342a2d632b5ef4ff9742c4546e0ca6907","last_reissued_at":"2026-06-19T16:10:41.025243Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:41.025243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Environment-Grounded Automated Prompt Optimization for LLM Game Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lukas Fehring, Marius Lindauer, Matthias Feurer, Rean Clive Fernandes, Theresa Eimer","submitted_at":"2026-06-16T12:06:27Z","abstract_excerpt":"LLM agents in interactive environments are highly sensitive to their prompts, yet prompt engineering remains a manual, task-specific process. We introduce an automated prompt optimization framework for LLM agents that decomposes the observation-to-action pipeline into a goal-conditioned descriptor agent and an action selection agent, and iteratively refines each module's prompt through an LLM-driven evolutionary loop guided by environment returns. We propose a behavior analyzer to attribute episode outcomes to specific prompt components, and a mutator to propose targeted revisions to the promp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17838","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.17838/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.17838","created_at":"2026-06-19T16:10:41.025306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17838v1","created_at":"2026-06-19T16:10:41.025306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17838","created_at":"2026-06-19T16:10:41.025306+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNZKFRXSYVVT","created_at":"2026-06-19T16:10:41.025306+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNZKFRXSYVVT2ZHH","created_at":"2026-06-19T16:10:41.025306+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNZKFRXS","created_at":"2026-06-19T16:10:41.025306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN","json":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN.json","graph_json":"https://pith.science/api/pith-number/XNZKFRXSYVVT2ZHHGF7HSCTEAN/graph.json","events_json":"https://pith.science/api/pith-number/XNZKFRXSYVVT2ZHHGF7HSCTEAN/events.json","paper":"https://pith.science/paper/XNZKFRXS"},"agent_actions":{"view_html":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN","download_json":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN.json","view_paper":"https://pith.science/paper/XNZKFRXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17838&json=true","fetch_graph":"https://pith.science/api/pith-number/XNZKFRXSYVVT2ZHHGF7HSCTEAN/graph.json","fetch_events":"https://pith.science/api/pith-number/XNZKFRXSYVVT2ZHHGF7HSCTEAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN/action/storage_attestation","attest_author":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN/action/author_attestation","sign_citation":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN/action/citation_signature","submit_replication":"https://pith.science/pith/XNZKFRXSYVVT2ZHHGF7HSCTEAN/action/replication_record"}},"created_at":"2026-06-19T16:10:41.025306+00:00","updated_at":"2026-06-19T16:10:41.025306+00:00"}