{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFJDEBFSRSEJVAXFN7O4SPLYCZ","short_pith_number":"pith:XFJDEBFS","schema_version":"1.0","canonical_sha256":"b9523204b28c889a82e56fddc93d781671e68357f0a6aba22d5e6d2f990b8627","source":{"kind":"arxiv","id":"2412.10425","version":3},"attestation_state":"computed","paper":{"title":"Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Rithvik Prakki","submitted_at":"2024-12-10T16:34:47Z","abstract_excerpt":"This paper introduces a novel approach to creating adaptive language agents by integrating active inference with large language models (LLMs). While LLMs demonstrate remarkable capabilities, their reliance on static prompts limits adaptation to new information and changing environments. We address this by implementing an active inference framework that acts as a cognitive layer above an LLM-based agent, dynamically adjusting prompts and search strategies through principled information-seeking behavior. Our framework models the environment using three state factors (prompt, search, and informat"},"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":"2412.10425","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T16:34:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cdde3215625a4b44274c5586b8133ff6e6e3ad8ab9601dda41b23cca54ea1836","abstract_canon_sha256":"a20bbb7ac92d68c0a6be62ef9de3b0d6fabdca9cbc527950d689248177cf4dca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:21.276765Z","signature_b64":"94Bpq7c+Z7JFnvJDQFSl44uttb5PhutujY7tERenpOuBtqhPx+41fACipQmy7oD+IFm2/FE809QRr4fjJsAaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9523204b28c889a82e56fddc93d781671e68357f0a6aba22d5e6d2f990b8627","last_reissued_at":"2026-07-05T09:59:21.276339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:21.276339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Rithvik Prakki","submitted_at":"2024-12-10T16:34:47Z","abstract_excerpt":"This paper introduces a novel approach to creating adaptive language agents by integrating active inference with large language models (LLMs). While LLMs demonstrate remarkable capabilities, their reliance on static prompts limits adaptation to new information and changing environments. We address this by implementing an active inference framework that acts as a cognitive layer above an LLM-based agent, dynamically adjusting prompts and search strategies through principled information-seeking behavior. Our framework models the environment using three state factors (prompt, search, and informat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10425","kind":"arxiv","version":3},"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/2412.10425/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":"2412.10425","created_at":"2026-07-05T09:59:21.276401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10425v3","created_at":"2026-07-05T09:59:21.276401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10425","created_at":"2026-07-05T09:59:21.276401+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFJDEBFSRSEJ","created_at":"2026-07-05T09:59:21.276401+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFJDEBFSRSEJVAXF","created_at":"2026-07-05T09:59:21.276401+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFJDEBFS","created_at":"2026-07-05T09:59:21.276401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16325","citing_title":"Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ","json":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ.json","graph_json":"https://pith.science/api/pith-number/XFJDEBFSRSEJVAXFN7O4SPLYCZ/graph.json","events_json":"https://pith.science/api/pith-number/XFJDEBFSRSEJVAXFN7O4SPLYCZ/events.json","paper":"https://pith.science/paper/XFJDEBFS"},"agent_actions":{"view_html":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ","download_json":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ.json","view_paper":"https://pith.science/paper/XFJDEBFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10425&json=true","fetch_graph":"https://pith.science/api/pith-number/XFJDEBFSRSEJVAXFN7O4SPLYCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XFJDEBFSRSEJVAXFN7O4SPLYCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ/action/storage_attestation","attest_author":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ/action/author_attestation","sign_citation":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ/action/citation_signature","submit_replication":"https://pith.science/pith/XFJDEBFSRSEJVAXFN7O4SPLYCZ/action/replication_record"}},"created_at":"2026-07-05T09:59:21.276401+00:00","updated_at":"2026-07-05T09:59:21.276401+00:00"}