{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QC25BQBJB2YJ7IODOML6YMEXOC","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":"76f53ab048b8ff64c74e2e4d88df62e9368db69dde90fabff38bbae5b769bd35","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-21T14:26:14Z","title_canon_sha256":"bd243b8466d2fabf124502b6b763299384c1e6bdd81ae8f7671f297a6e610adc"},"schema_version":"1.0","source":{"id":"2512.18746","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.18746","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2512.18746v1","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.18746","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"QC25BQBJB2YJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QC25BQBJB2YJ7IOD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QC25BQBJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c80a5714e0d8ba9f03eaae39e7884c83884f9c001382c3221a7b5e4012d5ae6c","target":"graph","created_at":"2026-05-17T23:38:49Z","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":"MemEvolve achieves substantial performance gains, improving frameworks such as SmolAgent and Flash-Searcher by up to 17.06%, and demonstrates strong cross-task and cross-LLM generalization by designing transferable memory architectures."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The modular decomposition of memory systems into encode/store/retrieve/manage components in EvolveLab is assumed to be expressive enough to support meaningful meta-evolution without omitting critical architectural variations present in real deployments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MemEvolve jointly evolves agent experiential knowledge and memory architectures via a modular codebase, delivering up to 17% gains on agent benchmarks with cross-task and cross-model generalization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MemEvolve lets LLM agents evolve both their stored experience and the memory architecture that organizes it."}],"snapshot_sha256":"57899ac1c4aa6fd45c9516b9ce9930aa1cf4e8fe2c996865d10c9579d00cad89"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"5a54ef018ffb4565c1e52d6717a5f4e60e4953e8aff7e18ec3fe9dde67d2b868"},"paper":{"abstract_excerpt":"Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill experience, and synthesize reusable tools, enabling agents to evolve on the fly within environment interactions. However, this paradigm is fundamentally constrained by the staticity of the memory system itself: while memory facilitates agent-level evolving, the underlying memory architecture cannot be meta-adapted to diverse task contexts. To address this ga","authors_text":"Chong Zhan, Guibin Zhang, Haotian Ren, He Zhu, Junhao Wang, Shuicheng Yan, Wangchunshu Zhou, Zhenhong Zhou","cross_cats":["cs.MA"],"headline":"MemEvolve lets LLM agents evolve both their stored experience and the memory architecture that organizes it.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-21T14:26:14Z","title":"MemEvolve: Meta-Evolution of Agent Memory Systems"},"references":{"count":39,"internal_anchors":6,"resolved_work":39,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Pang, X., Peng, J., Peng, R., Qiao, Y., Qiu, J., Qu, X., Qu, Y., Ren, Y., Shang, F., Shao, W., Shen, J., Shen, S., Song, C., Song, D., Song, D., Su, C., Su, W., Sun, W., Sun, Y., Tan, Q., Tang, C., Ta","work_id":"d2409ab5-cd99-4101-9dc4-7a600b8552b5","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Cai, Y., Cai, S., Shi, Y., Xu, Z., Chen, L., Qin, Y., Tan, X., Li, G., Li, Z., Lin, H., Mao, Y., Li, K., and Sun, X. (2025). Training-free group relative policy optimization","work_id":"ecbee6e5-09f8-4c75-929a-d83b88c51014","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Yin, Z., Ma, Z., and Mo, Z. (2025). xbench: Tracking agents productivity scaling with profession-aligned real-world evaluations","work_id":"a61aa60a-83bd-47dc-ba3c-34d113d1865c","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"L., Ni, J., Xu, L., Li, M., Tian, N., Chen, R","work_id":"8752a0f9-492b-4319-b95b-4be4887cf061","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Du, M., Xu, B., Zhu, C., Wang, X., and Mao, Z. (2025). Deepresearch bench: A comprehensive benchmark for deep research agents","work_id":"a4aaa5f6-24d6-49ea-a536-4dc8a2cce6c6","year":2025}],"snapshot_sha256":"ab43d975e92f5dc7a914a55cbbe92ffc48e0420e6d38b10cfad24ae728c7e0c8"},"source":{"id":"2512.18746","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T22:14:51.431154Z","id":"1a74b3af-db31-4219-b191-18408780f518","model_set":{"reader":"grok-4.3"},"one_line_summary":"MemEvolve jointly evolves agent experiential knowledge and memory architectures via a modular codebase, delivering up to 17% gains on agent benchmarks with cross-task and cross-model generalization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MemEvolve lets LLM agents evolve both their stored experience and the memory architecture that organizes it.","strongest_claim":"MemEvolve achieves substantial performance gains, improving frameworks such as SmolAgent and Flash-Searcher by up to 17.06%, and demonstrates strong cross-task and cross-LLM generalization by designing transferable memory architectures.","weakest_assumption":"The modular decomposition of memory systems into encode/store/retrieve/manage components in EvolveLab is assumed to be expressive enough to support meaningful meta-evolution without omitting critical architectural variations present in real deployments."}},"verdict_id":"1a74b3af-db31-4219-b191-18408780f518"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0c2038e21702a670cbab4582a0c9e7ff5f15f24a8b8031ebb092e8c4a1552d8e","target":"record","created_at":"2026-05-17T23:38:49Z","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":"76f53ab048b8ff64c74e2e4d88df62e9368db69dde90fabff38bbae5b769bd35","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-21T14:26:14Z","title_canon_sha256":"bd243b8466d2fabf124502b6b763299384c1e6bdd81ae8f7671f297a6e610adc"},"schema_version":"1.0","source":{"id":"2512.18746","kind":"arxiv","version":1}},"canonical_sha256":"80b5d0c0290eb09fa1c37317ec309770a51af5cbe95fd4b633139aaac439093c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80b5d0c0290eb09fa1c37317ec309770a51af5cbe95fd4b633139aaac439093c","first_computed_at":"2026-05-17T23:38:49.966891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.966891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WEaarVyF+2QLsx7lZ+Lvw4t0nW/02xiPJkuTyce26b0Dqvxf4uTOT5YMAj7iYBBjpBl1zeLDz9OyMLdrXOQxDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.967357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.18746","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c2038e21702a670cbab4582a0c9e7ff5f15f24a8b8031ebb092e8c4a1552d8e","sha256:c80a5714e0d8ba9f03eaae39e7884c83884f9c001382c3221a7b5e4012d5ae6c"],"state_sha256":"8b468b2f37a5cf1844c5fce360aeffc5e2dcd803fe6ce10e1e9e6551bfc24a10"}