{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PBBSJDENTVBM6VDINGHLHO77ZF","short_pith_number":"pith:PBBSJDEN","schema_version":"1.0","canonical_sha256":"7843248c8d9d42cf5468698eb3bbffc96b71a252ec818fb6950feac45868352a","source":{"kind":"arxiv","id":"2601.14192","version":2},"attestation_state":"computed","paper":{"title":"Toward Efficient Agents: Memory, Tool learning, and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Daizong Liu, Heng Zhou, Jing Shao, Lijun Li, Li Kang, Ning Ding, Qianshan Wei, Qi Li, Rui Ye, Siheng Chen, Tong Zhu, Xiaofang Yang, Xiaoye Qu, Yiran Qin, Yuchen Fan","submitted_at":"2026-01-20T17:51:56Z","abstract_excerpt":"Recent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has continued to improve, efficiency, which is crucial for real-world deployment, has often been overlooked. This paper therefore investigates efficiency from three core components of agents: memory, tool learning, and planning, considering costs such as latency, tokens, steps, etc. Aimed at conducting comprehensive research addressing the efficiency of the agentic system itself, we review a broad range of recent approaches that differ in implementation yet"},"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":"2601.14192","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-20T17:51:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"aaf21e5136791f2b66b8ac9c8bee647a3e8ffa5b70d11a8591e2eaa548bdfdd4","abstract_canon_sha256":"abebf4bd928d10775d1b4215ae3f22ee4c719264b59ca8027f389ff6d4903f8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:04.435520Z","signature_b64":"pF8gMA6qZnGeUzXUSrPcNf7FF0R4t8gHUtI1w9coAJzm5PXX89cPr1lOgRcYYKim8da8NEZVI746+dF/luGjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7843248c8d9d42cf5468698eb3bbffc96b71a252ec818fb6950feac45868352a","last_reissued_at":"2026-07-07T01:16:04.434683Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:04.434683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Efficient Agents: Memory, Tool learning, and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Daizong Liu, Heng Zhou, Jing Shao, Lijun Li, Li Kang, Ning Ding, Qianshan Wei, Qi Li, Rui Ye, Siheng Chen, Tong Zhu, Xiaofang Yang, Xiaoye Qu, Yiran Qin, Yuchen Fan","submitted_at":"2026-01-20T17:51:56Z","abstract_excerpt":"Recent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has continued to improve, efficiency, which is crucial for real-world deployment, has often been overlooked. This paper therefore investigates efficiency from three core components of agents: memory, tool learning, and planning, considering costs such as latency, tokens, steps, etc. Aimed at conducting comprehensive research addressing the efficiency of the agentic system itself, we review a broad range of recent approaches that differ in implementation yet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14192","kind":"arxiv","version":2},"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/2601.14192/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":"2601.14192","created_at":"2026-07-07T01:16:04.434784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.14192v2","created_at":"2026-07-07T01:16:04.434784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14192","created_at":"2026-07-07T01:16:04.434784+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBBSJDENTVBM","created_at":"2026-07-07T01:16:04.434784+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBBSJDENTVBM6VDI","created_at":"2026-07-07T01:16:04.434784+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBBSJDEN","created_at":"2026-07-07T01:16:04.434784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2606.10794","citing_title":"READER: Robust Evidence-based Authorship Decoding via Extracted Representations","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09252","citing_title":"LLM Agents Already Know When to Call Tools -- Even Without Reasoning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19285","citing_title":"Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09942","citing_title":"HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09252","citing_title":"LLM Agents Already Know When to Call Tools -- Even Without Reasoning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06753","citing_title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05719","citing_title":"Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing","ref_index":127,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF","json":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF.json","graph_json":"https://pith.science/api/pith-number/PBBSJDENTVBM6VDINGHLHO77ZF/graph.json","events_json":"https://pith.science/api/pith-number/PBBSJDENTVBM6VDINGHLHO77ZF/events.json","paper":"https://pith.science/paper/PBBSJDEN"},"agent_actions":{"view_html":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF","download_json":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF.json","view_paper":"https://pith.science/paper/PBBSJDEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.14192&json=true","fetch_graph":"https://pith.science/api/pith-number/PBBSJDENTVBM6VDINGHLHO77ZF/graph.json","fetch_events":"https://pith.science/api/pith-number/PBBSJDENTVBM6VDINGHLHO77ZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF/action/storage_attestation","attest_author":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF/action/author_attestation","sign_citation":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF/action/citation_signature","submit_replication":"https://pith.science/pith/PBBSJDENTVBM6VDINGHLHO77ZF/action/replication_record"}},"created_at":"2026-07-07T01:16:04.434784+00:00","updated_at":"2026-07-07T01:16:04.434784+00:00"}