{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D7KPWI3OTACBQW4M5BDXTGXADR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"61873fce3a172bfadfbe24e9838f2ddd05478d1248091518b6f34a455c87c70c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T09:45:40Z","title_canon_sha256":"f8052cc4a6c07db718fd936de2a05be0f91193f9fed808082289408116cca96f"},"schema_version":"1.0","source":{"id":"2505.07903","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07903","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07903v1","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07903","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"D7KPWI3OTACB","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"D7KPWI3OTACBQW4M","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"D7KPWI3O","created_at":"2026-07-05T11:01:59Z"}],"graph_snapshots":[{"event_id":"sha256:eaa48c4c09296f03d61608f9dff07f0623bdbd2e68dcc9875e7b93cc5296cbe7","target":"graph","created_at":"2026-07-05T11:01:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.07903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models(LLMs) have demonstrated their capabilities not only in reasoning but also in invoking external tools, particularly search engines. However, teaching models to discern when to invoke search and when to rely on their internal knowledge remains a significant challenge. Existing reinforcement learning approaches often lead to redundant search behaviors, resulting in inefficiencies and over-cost. In this paper, we propose SEM, a novel post-training reinforcement learning framework that explicitly trains LLMs to optimize search usage. By constructing a ba","authors_text":"Shiwen Cui, Weiqiang Wang, Zeyang Sha","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T09:45:40Z","title":"SEM: Reinforcement Learning for Search-Efficient Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07903","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b261cd5e22021bd320fa098a35d4b39ab77e3c651a56353c238d067fa757f4d","target":"record","created_at":"2026-07-05T11:01:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"61873fce3a172bfadfbe24e9838f2ddd05478d1248091518b6f34a455c87c70c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T09:45:40Z","title_canon_sha256":"f8052cc4a6c07db718fd936de2a05be0f91193f9fed808082289408116cca96f"},"schema_version":"1.0","source":{"id":"2505.07903","kind":"arxiv","version":1}},"canonical_sha256":"1fd4fb236e9804185b8ce847799ae01c7611d135c13e0c04191798deddd7efa5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fd4fb236e9804185b8ce847799ae01c7611d135c13e0c04191798deddd7efa5","first_computed_at":"2026-07-05T11:01:59.296595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:59.296595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b1u987fQbRYgaXAM24gjBPotw2+e3Le+zl6dEjRxoXYh9rQXbegyRqbsmUQzJQAiFbXTltTF36NM4xe4ywV9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:59.297102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07903","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b261cd5e22021bd320fa098a35d4b39ab77e3c651a56353c238d067fa757f4d","sha256:eaa48c4c09296f03d61608f9dff07f0623bdbd2e68dcc9875e7b93cc5296cbe7"],"state_sha256":"953d379c652f2f2498bd83020df6df5c28eb1fc58e9a7ec402614bcae32174d8"}