{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LEQP4T6R5R7RYECHFH66GN6O3R","short_pith_number":"pith:LEQP4T6R","schema_version":"1.0","canonical_sha256":"5920fe4fd1ec7f1c104729fde337cedc5682662c931bbe56e061db3ef0793b0b","source":{"kind":"arxiv","id":"2507.03254","version":1},"attestation_state":"computed","paper":{"title":"CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bruce Yang, David Hsu, Huan Gao, Xiaofan Li, Xinfeng He, Yifan Cao","submitted_at":"2025-07-04T02:20:19Z","abstract_excerpt":"Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often evaluate performance solely based on task accuracy - overlooking critical factors such as token efficiency, modularity, and scalability in multi-agent environments. To address these limitations, we introduce CodeAgents, a prompting framework that codifies multi-agent reasoning and enables structured, token-efficient planning in multi-agent systems. In CodeA"},"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":"2507.03254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-04T02:20:19Z","cross_cats_sorted":[],"title_canon_sha256":"5647af804d5be1dbd0c3df6ce823fa3426faeb2298cd780851ff3277e63b4709","abstract_canon_sha256":"f1d180be32d6128dc63d67fdd0df4526b1643757b9e55e9c45f45ab12c412476"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:55.688971Z","signature_b64":"27uuYNTmOPz0QylOzt2ZHPz6oI0PyMKd6RTlUVnzbjj5moONPVC9lHm9cTSHg8NuTqP6atcHVOmluYpM/srsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5920fe4fd1ec7f1c104729fde337cedc5682662c931bbe56e061db3ef0793b0b","last_reissued_at":"2026-07-05T11:31:55.688199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:55.688199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bruce Yang, David Hsu, Huan Gao, Xiaofan Li, Xinfeng He, Yifan Cao","submitted_at":"2025-07-04T02:20:19Z","abstract_excerpt":"Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often evaluate performance solely based on task accuracy - overlooking critical factors such as token efficiency, modularity, and scalability in multi-agent environments. To address these limitations, we introduce CodeAgents, a prompting framework that codifies multi-agent reasoning and enables structured, token-efficient planning in multi-agent systems. In CodeA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03254","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/2507.03254/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":"2507.03254","created_at":"2026-07-05T11:31:55.688298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03254v1","created_at":"2026-07-05T11:31:55.688298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03254","created_at":"2026-07-05T11:31:55.688298+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEQP4T6R5R7R","created_at":"2026-07-05T11:31:55.688298+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEQP4T6R5R7RYECH","created_at":"2026-07-05T11:31:55.688298+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEQP4T6R","created_at":"2026-07-05T11:31:55.688298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":236,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09104","citing_title":"Token Economics for LLM Agents: A Dual-View Study from Computing and Economics","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R","json":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R.json","graph_json":"https://pith.science/api/pith-number/LEQP4T6R5R7RYECHFH66GN6O3R/graph.json","events_json":"https://pith.science/api/pith-number/LEQP4T6R5R7RYECHFH66GN6O3R/events.json","paper":"https://pith.science/paper/LEQP4T6R"},"agent_actions":{"view_html":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R","download_json":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R.json","view_paper":"https://pith.science/paper/LEQP4T6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03254&json=true","fetch_graph":"https://pith.science/api/pith-number/LEQP4T6R5R7RYECHFH66GN6O3R/graph.json","fetch_events":"https://pith.science/api/pith-number/LEQP4T6R5R7RYECHFH66GN6O3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R/action/storage_attestation","attest_author":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R/action/author_attestation","sign_citation":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R/action/citation_signature","submit_replication":"https://pith.science/pith/LEQP4T6R5R7RYECHFH66GN6O3R/action/replication_record"}},"created_at":"2026-07-05T11:31:55.688298+00:00","updated_at":"2026-07-05T11:31:55.688298+00:00"}