{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MEMTMOH2I65U2UFU73PRCDTNND","short_pith_number":"pith:MEMTMOH2","schema_version":"1.0","canonical_sha256":"61193638fa47bb4d50b4fedf110e6d68c480f1a8a063af6dd2f694bf8a957766","source":{"kind":"arxiv","id":"2604.17931","version":3},"attestation_state":"computed","paper":{"title":"LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A lite virtual world mirroring real searches lets a 4B agent master deep research via scalable RL.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bince Qu, Bo Pan, Bo Zhang, Jianyu Zhang, Pan Zhang, Wanli Li, Wei Chen, Zheng Liu","submitted_at":"2026-04-20T08:11:09Z","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"},"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":"2604.17931","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-20T08:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"ac7556e0f8c53b366181318e144fcfab277bb2e89ef313070b6db69cdfe1a841","abstract_canon_sha256":"99d9257e1d274090de3f46c6fdec73c9ae36b346baa271cb3d244ecb792ba3fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:24.678429Z","signature_b64":"dOBFJ46UGXqSIWK2BJBQ1DDtVOfeLdaKlEM5xga2a+lSbUqXZCaWKBst93bzgPYoAkhTNuCb7OlmdG9KV/vQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61193638fa47bb4d50b4fedf110e6d68c480f1a8a063af6dd2f694bf8a957766","last_reissued_at":"2026-07-01T01:18:24.677761Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:24.677761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A lite virtual world mirroring real searches lets a 4B agent master deep research via scalable RL.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bince Qu, Bo Pan, Bo Zhang, Jianyu Zhang, Pan Zhang, Wanli Li, Wei Chen, Zheng Liu","submitted_at":"2026-04-20T08:11:09Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A lite virtual world mirroring real searches lets a 4B agent master deep research via scalable RL.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3dcad5dc9b11949a3f06bc4197da4aacc986fe1e742b31e10fed41217ef75527"},"source":{"id":"2604.17931","kind":"arxiv","version":3},"verdict":{"id":"01bc0000-bce8-4f17-ab84-7cf860515925","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T04:18:00.687817Z","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.","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","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.","pith_extraction_headline":"A lite virtual world mirroring real searches lets a 4B agent master deep research via scalable RL."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17931/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T04:35:54.579286Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"bcd52858755c8ccc6bc12aac2e5e6baefaca77b9c8ed724e5ea7e223ec4b80ef"},"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":"2604.17931","created_at":"2026-07-01T01:18:24.677834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.17931v3","created_at":"2026-07-01T01:18:24.677834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17931","created_at":"2026-07-01T01:18:24.677834+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEMTMOH2I65U","created_at":"2026-07-01T01:18:24.677834+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEMTMOH2I65U2UFU","created_at":"2026-07-01T01:18:24.677834+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEMTMOH2","created_at":"2026-07-01T01:18:24.677834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.05943","citing_title":"SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19893","citing_title":"MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03963","citing_title":"AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND","json":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND.json","graph_json":"https://pith.science/api/pith-number/MEMTMOH2I65U2UFU73PRCDTNND/graph.json","events_json":"https://pith.science/api/pith-number/MEMTMOH2I65U2UFU73PRCDTNND/events.json","paper":"https://pith.science/paper/MEMTMOH2"},"agent_actions":{"view_html":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND","download_json":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND.json","view_paper":"https://pith.science/paper/MEMTMOH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.17931&json=true","fetch_graph":"https://pith.science/api/pith-number/MEMTMOH2I65U2UFU73PRCDTNND/graph.json","fetch_events":"https://pith.science/api/pith-number/MEMTMOH2I65U2UFU73PRCDTNND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND/action/storage_attestation","attest_author":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND/action/author_attestation","sign_citation":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND/action/citation_signature","submit_replication":"https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND/action/replication_record"}},"created_at":"2026-07-01T01:18:24.677834+00:00","updated_at":"2026-07-01T01:18:24.677834+00:00"}