AI Agents - Revision history

KevinYager: /* Automated Improvement */

2026-04-02T17:55:33Z

‎Automated Improvement

2026-03-03T14:05:40Z

‎Research

2026-02-18T15:25:07Z

‎Information Retrieval (Memory)

2026-02-16T00:47:45Z

‎AI Assistant

2026-02-13T14:51:11Z

‎Research

2026-01-28T23:59:34Z

‎Research

2026-01-26T14:24:49Z

‎Published

2026-01-19T21:27:57Z

‎Societies and Communities of AI agents

2026-01-13T16:06:19Z

‎LLM-as-judge

2026-01-12T18:38:18Z

‎Research

@@ Line 451: / Line 451: @@
 * 2024-08: [https://arxiv.org/abs/2408.02666 Self-Taught Evaluators]: Iterative self-improvement through generation of synthetic data and evaluation
 * 2025-05: [https://arxiv.org/abs/2505.22954 Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents] ([https://github.com/jennyzzt/dgm code], [https://sakana.ai/dgm/ project])
 =See Also=

@@ Line 276: / Line 276: @@
 * 2026-01: [https://arxiv.org/abs/2601.04748 When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail]
 * 2026-02: [https://arxiv.org/abs/2602.11865 Intelligent AI Delegation]
 ===Organization Schemes===

@@ Line 46: / Line 46: @@
 ===Information Retrieval (Memory)===
 * See also [[AI_tools#Retrieval_Augmented_Generation_.28RAG.29|RAG]].
 * 2024-09: PaperQA2: [https://paper.wikicrow.ai/ Language Models Achieve Superhuman Synthesis of Scientific Knowledge] ([https://x.com/SGRodriques/status/1833908643856818443 𝕏 post], [https://github.com/Future-House/paper-qa code])
 * 2024-10: [https://arxiv.org/abs/2410.09713 Agentic Information Retrieval]

@@ Line 250: / Line 250: @@
 * [https://convergence.ai/ Convergence] [https://proxy.convergence.ai/ Proxy]
 * [https://www.shortwave.com/ Shortwave] [https://www.shortwave.com/docs/guides/ai-assistant/ AI Assistant] (organize, write, search, schedule, etc.)
 ==Agentic Systems==

@@ Line 273: / Line 273: @@
 ** 2026-01: [https://research.google/blog/towards-a-science-of-scaling-agent-systems-when-and-why-agent-systems-work/ Towards a science of scaling agent systems: When and why agent systems work]
 * 2026-01: [https://arxiv.org/abs/2601.04748 When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail]
 ===Organization Schemes===

@@ Line 271: / Line 271: @@
 * 2025-11: [https://arxiv.org/abs/2510.26658 The Era of Agentic Organization: Learning to Organize with Language Models] (Microsoft)
 * 2025-12: [https://arxiv.org/abs/2512.08296 Towards a Science of Scaling Agent Systems] (Google DeepMind)
 * 2026-01: [https://arxiv.org/abs/2601.04748 When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail]

@@ Line 11: / Line 11: @@
 * 2025-04: [https://arxiv.org/abs/2504.09037 A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems]
 * 2025-04: [https://arxiv.org/abs/2504.01990 Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems]
 ===Continually updating===

@@ Line 280: / Line 280: @@
 * 2025-05: [https://www.science.org/doi/10.1126/sciadv.adu9368 Emergent social conventions and collective bias in LLM populations]
 * 2025-09: [https://arxiv.org/abs/2509.10147 Virtual Agent Economies]
 ===Domain-specific===

@@ Line 126: / Line 126: @@
 * 2025-03: [https://arxiv.org/abs/2503.19877 Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators]
 * 2025-04: [https://arxiv.org/abs/2504.00050 JudgeLRM: Large Reasoning Models as a Judge]
 ===Deep Research===