TechniqueRLHF / Alignment4 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→29 May 2026Beyond Recall: Behavioral Specification as an Interpretive Layer for AI PersonalizationarXiv:2605.28969v1 Announce Type: cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how f→15 Jul 2026Wiki Lint Report — 2026-07-15Automated lint: 26 errors, 6728 warnings, 3 info
TechniqueRAG4 recent entries8 Apr 2026Great paper on improving memory for AI agents.Great paper on improving memory for AI agents. NEW paper: Memory Intelligence Agent (MIA) MIA boosts GPT-5.4 by up to 9% on LiveVQA. Quick summary: Most memory-augmented agents treat memory as a stati→11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→15 Jul 2026Wiki Lint Report — 2026-07-15Automated lint: 26 errors, 6728 warnings, 3 info→19 Jul 2026Wiki Lint Report — 2026-07-19Automated lint: 20 errors, 8743 warnings, 3 info
TechniqueAgents8 recent entries19 Jul 2026Wiki Lint Report — 2026-07-19Automated lint: 20 errors, 8743 warnings, 3 info→7 Aug 2026FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial WorkflowsarXiv:2608.06144v1 Announce Type: new Abstract: Most agent benchmarks evaluate tasks independently and cannot measure whether experience from one task helps with later tasks. Existing self-evolution b→17 Aug 2026LettaLetta's agent-memory SDK supports persistent agent memory across managed cloud, self-hosted App Server or local deployment, according to Letta.→19 Aug 2026ZepZep offers a knowledge graph for persistent user memory and shared organisational context through MCP, according to Zep.→16 Sept 2026Mem0Mem0 provides persistent user memory and agent memory; its vendor describes fact extraction, contradiction handling and relevant recall.→24 Sept 2026Harness as a Language: A Minimalist Agent Framework With Maximal ExpressivityarXiv:2609.26891v1 Announce Type: new Abstract: Modern language-model agents are built around the extit{agent loop}, where the LLM is placed in an environment exposing a set of tools, and the LLM has →26 Sept 2026Keep your agent harness minimal, folks. This paper from MIT CSAIL shows why. (bookmark it) While being very minimal it looks effective and p…Keep your agent harness minimal, folks. This paper from MIT CSAIL shows why. (bookmark it) While being very minimal it looks effective and promising for building self-improving agents. They present JA→30 Sept 2026Vulnerability Discovery and Exploitation Trends in the AI EraWritten by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact
TechniqueFine-tuning4 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→11 Apr 2026Hot take: I can't see any startup building their critical core operations on Claude Managed Agents or any proprietary harness as investable.…Hot take: I can't see any startup building their critical core operations on Claude Managed Agents or any proprietary harness as investable. The past weeks have shown why it's critical to build on top→15 Jul 2026Wiki Lint Report — 2026-07-15Automated lint: 26 errors, 6728 warnings, 3 info→19 Jul 2026Wiki Lint Report — 2026-07-19Automated lint: 20 errors, 8743 warnings, 3 info
TechniqueMultimodal3 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→15 Jul 2026Wiki Lint Report — 2026-07-15Automated lint: 26 errors, 6728 warnings, 3 info→19 Jul 2026Wiki Lint Report — 2026-07-19Automated lint: 20 errors, 8743 warnings, 3 info
TechniqueSafety6 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→28 Apr 2026ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI SystemsarXiv:2604.23878v1 Announce Type: new Abstract: Despite a century of empirical memory research, existing AI agent memory systems rely on system-engineering metaphors (virtual-memory paging, flat LLM s→15 Jul 2026Wiki Lint Report — 2026-07-15Automated lint: 26 errors, 6728 warnings, 3 info→19 Jul 2026Wiki Lint Report — 2026-07-19Automated lint: 20 errors, 8743 warnings, 3 info→24 Sept 2026Harness as a Language: A Minimalist Agent Framework With Maximal ExpressivityarXiv:2609.26891v1 Announce Type: new Abstract: Modern language-model agents are built around the extit{agent loop}, where the LLM is placed in an environment exposing a set of tools, and the LLM has →30 Sept 2026Vulnerability Discovery and Exploitation Trends in the AI EraWritten by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact