{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YE4JDEPLSYQI6EAXDWXAOLBLWS","short_pith_number":"pith:YE4JDEPL","schema_version":"1.0","canonical_sha256":"c1389191eb96208f10171dae072c2bb4a317fdc33fdbbfbd568b613d1887fdb3","source":{"kind":"arxiv","id":"2403.17674","version":1},"attestation_state":"computed","paper":{"title":"Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CR","authors_text":"Keman Huang, Yaolun Zhang, Yikuan Yan","submitted_at":"2024-03-26T13:02:46Z","abstract_excerpt":"Integrating LLM and reinforcement learning (RL) agent effectively to achieve complementary performance is critical in high stake tasks like cybersecurity operations. In this study, we introduce SecurityBot, a LLM agent mentored by pre-trained RL agents, to support cybersecurity operations. In particularly, the LLM agent is supported with a profile module to generated behavior guidelines, a memory module to accumulate local experiences, a reflection module to re-evaluate choices, and an action module to reduce action space. Additionally, it adopts the collaboration mechanism to take suggestions"},"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":"2403.17674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-03-26T13:02:46Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"54bea7c973f971ff23d23cd6cd387ba1d42201c447b54029f8bb12ba6debcb75","abstract_canon_sha256":"bc108e14383c93d3b4f14bfa16e9c0b8029b115a83ac8ecc5fd499d0a97fd566"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:54.149651Z","signature_b64":"oyIYumOLOn2mMQwHE0HzQWl8PQiCOYS6omvDszwyA3G02X05f8ZbEhp0nbIDRTxKwmJ5ETTE8F5QCBKpVGgACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1389191eb96208f10171dae072c2bb4a317fdc33fdbbfbd568b613d1887fdb3","last_reissued_at":"2026-07-05T08:00:54.149266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:54.149266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CR","authors_text":"Keman Huang, Yaolun Zhang, Yikuan Yan","submitted_at":"2024-03-26T13:02:46Z","abstract_excerpt":"Integrating LLM and reinforcement learning (RL) agent effectively to achieve complementary performance is critical in high stake tasks like cybersecurity operations. In this study, we introduce SecurityBot, a LLM agent mentored by pre-trained RL agents, to support cybersecurity operations. In particularly, the LLM agent is supported with a profile module to generated behavior guidelines, a memory module to accumulate local experiences, a reflection module to re-evaluate choices, and an action module to reduce action space. Additionally, it adopts the collaboration mechanism to take suggestions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17674","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/2403.17674/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":"2403.17674","created_at":"2026-07-05T08:00:54.149320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17674v1","created_at":"2026-07-05T08:00:54.149320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17674","created_at":"2026-07-05T08:00:54.149320+00:00"},{"alias_kind":"pith_short_12","alias_value":"YE4JDEPLSYQI","created_at":"2026-07-05T08:00:54.149320+00:00"},{"alias_kind":"pith_short_16","alias_value":"YE4JDEPLSYQI6EAX","created_at":"2026-07-05T08:00:54.149320+00:00"},{"alias_kind":"pith_short_8","alias_value":"YE4JDEPL","created_at":"2026-07-05T08:00:54.149320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30479","citing_title":"COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15163","citing_title":"Adaptive Network Security Policies via Belief Aggregation and Rollout","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS","json":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS.json","graph_json":"https://pith.science/api/pith-number/YE4JDEPLSYQI6EAXDWXAOLBLWS/graph.json","events_json":"https://pith.science/api/pith-number/YE4JDEPLSYQI6EAXDWXAOLBLWS/events.json","paper":"https://pith.science/paper/YE4JDEPL"},"agent_actions":{"view_html":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS","download_json":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS.json","view_paper":"https://pith.science/paper/YE4JDEPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17674&json=true","fetch_graph":"https://pith.science/api/pith-number/YE4JDEPLSYQI6EAXDWXAOLBLWS/graph.json","fetch_events":"https://pith.science/api/pith-number/YE4JDEPLSYQI6EAXDWXAOLBLWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS/action/storage_attestation","attest_author":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS/action/author_attestation","sign_citation":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS/action/citation_signature","submit_replication":"https://pith.science/pith/YE4JDEPLSYQI6EAXDWXAOLBLWS/action/replication_record"}},"created_at":"2026-07-05T08:00:54.149320+00:00","updated_at":"2026-07-05T08:00:54.149320+00:00"}