{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SNWMJTQWZMYCX52XETUAPFKUK3","short_pith_number":"pith:SNWMJTQW","schema_version":"1.0","canonical_sha256":"936cc4ce16cb302bf75724e807955456ea6c866cccf408a089117df7ed474cea","source":{"kind":"arxiv","id":"2507.02004","version":1},"attestation_state":"computed","paper":{"title":"STELLA: Self-Evolving LLM Agent for Biomedical Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.AI","authors_text":"Le Cong, Mengdi Wang, Ruofan Jin, Zaixi Zhang","submitted_at":"2025-07-01T20:52:01Z","abstract_excerpt":"The rapid growth of biomedical data, tools, and literature has created a fragmented research landscape that outpaces human expertise. While AI agents offer a solution, they typically rely on static, manually curated toolsets, limiting their ability to adapt and scale. Here, we introduce STELLA, a self-evolving AI agent designed to overcome these limitations. STELLA employs a multi-agent architecture that autonomously improves its own capabilities through two core mechanisms: an evolving Template Library for reasoning strategies and a dynamic Tool Ocean that expands as a Tool Creation Agent aut"},"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":"2507.02004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-01T20:52:01Z","cross_cats_sorted":["cs.CL","q-bio.BM"],"title_canon_sha256":"674b3e3221b37412da6aea8dc64dc7a46877a33ce353a757b5b0196562c9d182","abstract_canon_sha256":"ddb69571a18b09367b8fc0244919c0eafe54b1707f13685438db7ebe3a3cfae2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:10.314360Z","signature_b64":"wo14vYrHksCZzz5nqMuTUNX63zwWyAw0lenQy5JjvzA3WrxySDInwWuDGkZoJaOsa4z2MsdlXRYI1PX5Skd2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"936cc4ce16cb302bf75724e807955456ea6c866cccf408a089117df7ed474cea","last_reissued_at":"2026-07-05T11:31:10.313869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:10.313869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STELLA: Self-Evolving LLM Agent for Biomedical Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.AI","authors_text":"Le Cong, Mengdi Wang, Ruofan Jin, Zaixi Zhang","submitted_at":"2025-07-01T20:52:01Z","abstract_excerpt":"The rapid growth of biomedical data, tools, and literature has created a fragmented research landscape that outpaces human expertise. While AI agents offer a solution, they typically rely on static, manually curated toolsets, limiting their ability to adapt and scale. Here, we introduce STELLA, a self-evolving AI agent designed to overcome these limitations. STELLA employs a multi-agent architecture that autonomously improves its own capabilities through two core mechanisms: an evolving Template Library for reasoning strategies and a dynamic Tool Ocean that expands as a Tool Creation Agent aut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02004","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/2507.02004/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":"2507.02004","created_at":"2026-07-05T11:31:10.313927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02004v1","created_at":"2026-07-05T11:31:10.313927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02004","created_at":"2026-07-05T11:31:10.313927+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNWMJTQWZMYC","created_at":"2026-07-05T11:31:10.313927+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNWMJTQWZMYCX52X","created_at":"2026-07-05T11:31:10.313927+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNWMJTQW","created_at":"2026-07-05T11:31:10.313927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11150","citing_title":"ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09365","citing_title":"Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04494","citing_title":"Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21516","citing_title":"Harnesses for Inference-Time Alignment over Execution Trajectories","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23986","citing_title":"TusoAI: Agentic Optimization for Scientific Methods","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20425","citing_title":"AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15766","citing_title":"BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15461","citing_title":"DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15588","citing_title":"\"Excuse me, may I say something...\" CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16922","citing_title":"ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3","json":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3.json","graph_json":"https://pith.science/api/pith-number/SNWMJTQWZMYCX52XETUAPFKUK3/graph.json","events_json":"https://pith.science/api/pith-number/SNWMJTQWZMYCX52XETUAPFKUK3/events.json","paper":"https://pith.science/paper/SNWMJTQW"},"agent_actions":{"view_html":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3","download_json":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3.json","view_paper":"https://pith.science/paper/SNWMJTQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02004&json=true","fetch_graph":"https://pith.science/api/pith-number/SNWMJTQWZMYCX52XETUAPFKUK3/graph.json","fetch_events":"https://pith.science/api/pith-number/SNWMJTQWZMYCX52XETUAPFKUK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3/action/storage_attestation","attest_author":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3/action/author_attestation","sign_citation":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3/action/citation_signature","submit_replication":"https://pith.science/pith/SNWMJTQWZMYCX52XETUAPFKUK3/action/replication_record"}},"created_at":"2026-07-05T11:31:10.313927+00:00","updated_at":"2026-07-05T11:31:10.313927+00:00"}