{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SUBCKG74ED35BKLBYLJPYEIZHC","short_pith_number":"pith:SUBCKG74","schema_version":"1.0","canonical_sha256":"9502251bfc20f7d0a961c2d2fc111938b25317c22f94f83c0362526a156a1e90","source":{"kind":"arxiv","id":"2606.01416","version":1},"attestation_state":"computed","paper":{"title":"Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adarsh Agrawal, Rahul Suresh Babu","submitted_at":"2026-05-31T19:27:22Z","abstract_excerpt":"Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery. In these systems, failures arise not only from model errors, but also from orchestration-level issues such as tool timeouts, malformed arguments, stale context, contradictory evidence, retry loops, and unverified intermediate outputs. This paper presents a self-healing agentic orchestrator that treats reliability as a bounded runtime control problem. The orchestrator maps observable failure signals to inferred failure classes, sel"},"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":"2606.01416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T19:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"d08e5cc3237108c002cacedafb5398d5dc047d5d486f2c0cd4008ede9e248252","abstract_canon_sha256":"2461709c6969e6633598f731cce2d7a13e1b7780673ec3c101697985335885fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:32.712487Z","signature_b64":"QvWZatNjV0OwZ9HKJqPpXETljHkXyDe2RjPLoWbx99sZmmCeiLWXTZBQbUGBKOuf8OZLi0y0qUFF6r52aWHYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9502251bfc20f7d0a961c2d2fc111938b25317c22f94f83c0362526a156a1e90","last_reissued_at":"2026-06-02T02:04:32.712149Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:32.712149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adarsh Agrawal, Rahul Suresh Babu","submitted_at":"2026-05-31T19:27:22Z","abstract_excerpt":"Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery. In these systems, failures arise not only from model errors, but also from orchestration-level issues such as tool timeouts, malformed arguments, stale context, contradictory evidence, retry loops, and unverified intermediate outputs. This paper presents a self-healing agentic orchestrator that treats reliability as a bounded runtime control problem. The orchestrator maps observable failure signals to inferred failure classes, sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01416","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/2606.01416/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":"2606.01416","created_at":"2026-06-02T02:04:32.712206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01416v1","created_at":"2026-06-02T02:04:32.712206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01416","created_at":"2026-06-02T02:04:32.712206+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUBCKG74ED35","created_at":"2026-06-02T02:04:32.712206+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUBCKG74ED35BKLB","created_at":"2026-06-02T02:04:32.712206+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUBCKG74","created_at":"2026-06-02T02:04:32.712206+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/SUBCKG74ED35BKLBYLJPYEIZHC","json":"https://pith.science/pith/SUBCKG74ED35BKLBYLJPYEIZHC.json","graph_json":"https://pith.science/api/pith-number/SUBCKG74ED35BKLBYLJPYEIZHC/graph.json","events_json":"https://pith.science/api/pith-number/SUBCKG74ED35BKLBYLJPYEIZHC/events.json","paper":"https://pith.science/paper/SUBCKG74"},"agent_actions":{"view_html":"https://pith.science/pith/SUBCKG74ED35BKLBYLJPYEIZHC","download_json":"https://pith.science/pith/SUBCKG74ED35BKLBYLJPYEIZHC.json","view_paper":"https://pith.science/paper/SUBCKG74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01416&json=true","fetch_graph":"https://pith.science/api/pith-number/SUBCKG74ED35BKLBYLJPYEIZHC/graph.json","fetch_events":"https://pith.science/api/pith-number/SUBCKG74ED35BKLBYLJPYEIZHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUBCKG74ED35BKLBYLJPYEIZHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUBCKG74ED35BKLBYLJPYEIZHC/action/storage_attestation","attest_author":"https://pith.science/pith/SUBCKG74ED35BKLBYLJPYEIZHC/action/author_attestation","sign_citation":"https://pith.science/pith/SUBCKG74ED35BKLBYLJPYEIZHC/action/citation_signature","submit_replication":"https://pith.science/pith/SUBCKG74ED35BKLBYLJPYEIZHC/action/replication_record"}},"created_at":"2026-06-02T02:04:32.712206+00:00","updated_at":"2026-06-02T02:04:32.712206+00:00"}