{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MEMTMOH2I65U2UFU73PRCDTNND","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":"99d9257e1d274090de3f46c6fdec73c9ae36b346baa271cb3d244ecb792ba3fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-20T08:11:09Z","title_canon_sha256":"ac7556e0f8c53b366181318e144fcfab277bb2e89ef313070b6db69cdfe1a841"},"schema_version":"1.0","source":{"id":"2604.17931","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17931","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17931v3","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17931","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"pith_short_12","alias_value":"MEMTMOH2I65U","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"pith_short_16","alias_value":"MEMTMOH2I65U2UFU","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"pith_short_8","alias_value":"MEMTMOH2","created_at":"2026-07-01T01:18:24Z"}],"graph_snapshots":[{"event_id":"sha256:b1f6bbf7fcc253f30e43c75b83831be6253d83cf5816faeefdda8eb71e8b4360","target":"graph","created_at":"2026-07-01T01:18:24Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"LiteResearcher is a training framework that makes Agentic RL scalable: by constructing a lite virtual world that mirrors real-world search dynamics, we enable a continuously improving training recipe that empowers a tiny search agent to outperform large-scale open-source and commercial models (e.g., Tongyi DeepResearch and Claude-4.5 Sonnet). Specifically, on common benchmarks such as GAIA and Xbench, our LiteResearcher-4B achieves open-source state-of-the-art results of 71.3% and 78.0% respectively."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The lite virtual world accurately captures the essential dynamics of real-world search so that capabilities learned inside it transfer to genuine research tasks without introducing simulation-specific artifacts or instability."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LiteResearcher uses a lite virtual world to make agentic RL training scalable and stable, enabling a 4B model to achieve 71.3% on GAIA and 78.0% on Xbench, outperforming larger open-source and commercial systems."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A lite virtual world mirroring real searches lets a 4B agent master deep research via scalable RL."}],"snapshot_sha256":"3dcad5dc9b11949a3f06bc4197da4aacc986fe1e742b31e10fed41217ef75527"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T04:35:54.579286Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.17931/integrity.json","findings":[],"snapshot_sha256":"bcd52858755c8ccc6bc12aac2e5e6baefaca77b9c8ed724e5ea7e223ec4b80ef","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains constrained by two coupled challenges: hand-crafted synthetic data fails to elicit genuine real-world search capabilities, and real-world search dependency during RL training introduces instability and prohibitive cost, which limits the scalability of Agentic RL. LiteResearcher is a training framework that makes Agentic RL scalable: by constructing a lite virtual world that mirrors real-world search dynamics, we enable a continuously improving trai","authors_text":"Bince Qu, Bo Pan, Bo Zhang, Jianyu Zhang, Pan Zhang, Wanli Li, Wei Chen, Zheng Liu","cross_cats":[],"headline":"A lite virtual world mirroring real searches lets a 4B agent master deep research via scalable RL.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-20T08:11:09Z","title":"LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.17931","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T04:18:00.687817Z","id":"01bc0000-bce8-4f17-ab84-7cf860515925","model_set":{"reader":"grok-4.3"},"one_line_summary":"LiteResearcher uses a lite virtual world to make agentic RL training scalable and stable, enabling a 4B model to achieve 71.3% on GAIA and 78.0% on Xbench, outperforming larger open-source and commercial systems.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A lite virtual world mirroring real searches lets a 4B agent master deep research via scalable RL.","strongest_claim":"LiteResearcher is a training framework that makes Agentic RL scalable: by constructing a lite virtual world that mirrors real-world search dynamics, we enable a continuously improving training recipe that empowers a tiny search agent to outperform large-scale open-source and commercial models (e.g., Tongyi DeepResearch and Claude-4.5 Sonnet). Specifically, on common benchmarks such as GAIA and Xbench, our LiteResearcher-4B achieves open-source state-of-the-art results of 71.3% and 78.0% respectively.","weakest_assumption":"The lite virtual world accurately captures the essential dynamics of real-world search so that capabilities learned inside it transfer to genuine research tasks without introducing simulation-specific artifacts or instability."}},"verdict_id":"01bc0000-bce8-4f17-ab84-7cf860515925"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a7a5d0dbbd6eaf4404ea16c47997194b366df3a3c68a2b62246413ab0bd10570","target":"record","created_at":"2026-07-01T01:18:24Z","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":"99d9257e1d274090de3f46c6fdec73c9ae36b346baa271cb3d244ecb792ba3fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-20T08:11:09Z","title_canon_sha256":"ac7556e0f8c53b366181318e144fcfab277bb2e89ef313070b6db69cdfe1a841"},"schema_version":"1.0","source":{"id":"2604.17931","kind":"arxiv","version":3}},"canonical_sha256":"61193638fa47bb4d50b4fedf110e6d68c480f1a8a063af6dd2f694bf8a957766","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61193638fa47bb4d50b4fedf110e6d68c480f1a8a063af6dd2f694bf8a957766","first_computed_at":"2026-07-01T01:18:24.677761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:24.677761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dOBFJ46UGXqSIWK2BJBQ1DDtVOfeLdaKlEM5xga2a+lSbUqXZCaWKBst93bzgPYoAkhTNuCb7OlmdG9KV/vQDQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:24.678429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.17931","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7a5d0dbbd6eaf4404ea16c47997194b366df3a3c68a2b62246413ab0bd10570","sha256:b1f6bbf7fcc253f30e43c75b83831be6253d83cf5816faeefdda8eb71e8b4360"],"state_sha256":"7461764a64e25223c94d61e2f818d474e8bd047be431dbb138aff17cbc4e71bc"}