{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFSDAILYPBLI4SIXLRXPEBUYYK","short_pith_number":"pith:XFSDAILY","schema_version":"1.0","canonical_sha256":"b96430217878568e49175c6ef20698c2bd8d0938eff97db8594faf0a4d898bd5","source":{"kind":"arxiv","id":"2404.14387","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Self-Evolution of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Fei Huang, Hangyu Li, Jingren Zhou, Ting-En Lin, Xiancai Chen, Yongbin Li, Yuchuan Wu, Zhengwei Tao, Zhi Jin","submitted_at":"2024-04-22T17:43:23Z","abstract_excerpt":"Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. However, current LLMs that learn from human or external model supervision are costly and may face performance ceilings as task complexity and diversity increase. To address this issue, self-evolution approaches that enable LLM to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing. This new training paradigm inspired by the human experiential learning process offers the potential to scale LLMs towards superintelligence. In this wo"},"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":"2404.14387","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T17:43:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f9aeba464e0fd699532feb86f301dbaf9c7acdab0157087fe4a0f0f2d3b6698","abstract_canon_sha256":"8b4a7eb340b698b56bfdf215063f9459a49d98249cb332d42873ac1fb444847e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:23.781767Z","signature_b64":"2lK7FqgH4ZSw87aTcLLAd2+45bK0KqMAiKnz/4WN/QcR39oBk3HLQ5vd8Vn0jPlrg9YLnjy4bSnX2GjscrdtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b96430217878568e49175c6ef20698c2bd8d0938eff97db8594faf0a4d898bd5","last_reissued_at":"2026-07-05T08:26:23.781326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:23.781326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Self-Evolution of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Fei Huang, Hangyu Li, Jingren Zhou, Ting-En Lin, Xiancai Chen, Yongbin Li, Yuchuan Wu, Zhengwei Tao, Zhi Jin","submitted_at":"2024-04-22T17:43:23Z","abstract_excerpt":"Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. However, current LLMs that learn from human or external model supervision are costly and may face performance ceilings as task complexity and diversity increase. To address this issue, self-evolution approaches that enable LLM to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing. This new training paradigm inspired by the human experiential learning process offers the potential to scale LLMs towards superintelligence. In this wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14387","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/2404.14387/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":"2404.14387","created_at":"2026-07-05T08:26:23.781384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14387v2","created_at":"2026-07-05T08:26:23.781384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14387","created_at":"2026-07-05T08:26:23.781384+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFSDAILYPBLI","created_at":"2026-07-05T08:26:23.781384+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFSDAILYPBLI4SIX","created_at":"2026-07-05T08:26:23.781384+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFSDAILY","created_at":"2026-07-05T08:26:23.781384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23075","citing_title":"Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10457","citing_title":"Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08671","citing_title":"SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04703","citing_title":"Rethinking Continual Experience Internalization for Self-Evolving LLM Agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03108","citing_title":"EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31561","citing_title":"What Am I Missing? Question-Answering as Hidden State Probing","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14733","citing_title":"Video-Zero: Self-Evolution Video Understanding","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23019","citing_title":"PACE: Two-Timescale Self-Evolution for Small Language Model Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16299","citing_title":"ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21931","citing_title":"EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20189","citing_title":"SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21463","citing_title":"Mem-$\\pi$: Adaptive Memory through Learning When and What to Generate","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16299","citing_title":"ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17037","citing_title":"D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15301","citing_title":"Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":262,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07248","citing_title":"DarwinTOD: LLM-driven Lifelong Self-evolution for Task-oriented Dialog Systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26805","citing_title":"Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09959","citing_title":"G-Zero: Self-Play for Open-Ended Generation from Zero Data","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26805","citing_title":"Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK","json":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK.json","graph_json":"https://pith.science/api/pith-number/XFSDAILYPBLI4SIXLRXPEBUYYK/graph.json","events_json":"https://pith.science/api/pith-number/XFSDAILYPBLI4SIXLRXPEBUYYK/events.json","paper":"https://pith.science/paper/XFSDAILY"},"agent_actions":{"view_html":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK","download_json":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK.json","view_paper":"https://pith.science/paper/XFSDAILY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14387&json=true","fetch_graph":"https://pith.science/api/pith-number/XFSDAILYPBLI4SIXLRXPEBUYYK/graph.json","fetch_events":"https://pith.science/api/pith-number/XFSDAILYPBLI4SIXLRXPEBUYYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK/action/storage_attestation","attest_author":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK/action/author_attestation","sign_citation":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK/action/citation_signature","submit_replication":"https://pith.science/pith/XFSDAILYPBLI4SIXLRXPEBUYYK/action/replication_record"}},"created_at":"2026-07-05T08:26:23.781384+00:00","updated_at":"2026-07-05T08:26:23.781384+00:00"}