13 items with this tag.Aug 31, 2026AI agent landmark readingsai-agentlandmark-readingspaper-readingAug 31, 2026ReAct: connecting reasoning and action through environmental feedbackai-agentlandmark-readingsagent-loopAug 31, 2026Toolformer: learning when and how to call toolsai-agentlandmark-readingstool-useAug 31, 2026Generative Agents: memory, reflection, and planning for long-term coherenceai-agentlandmark-readingsmemoryAug 31, 2026Reflexion: learning from failure through verbal feedbackai-agentlandmark-readingsreflectionAug 31, 2026Voyager: automatic curriculum, skill library, and verifiable open-ended learningai-agentlandmark-readingsembodied-agentAug 31, 2026AutoGen: expressing multi-agent applications as programmable conversationsai-agentlandmark-readingsmulti-agentAug 31, 2026MCP launch article: turning model connectivity into an open protocolai-agentlandmark-readingsmcpAug 31, 2026SWE-bench: evaluating coding agents with real issues, patches, and testsai-agentlandmark-readingsevaluationAug 31, 2026SWE-agent: why the Agent-Computer Interface changes performanceai-agentlandmark-readingscoding-agentAug 31, 2026Building Effective Agents: from composable workflows to autonomous agentsai-agentlandmark-readingsagent-designAug 31, 2026Effective Context Engineering: managing an agent's limited attentionai-agentlandmark-readingscontext-engineeringAug 31, 2026Harness Engineering: designing a legible, testable environment for coding agentsai-agentlandmark-readingsharness-engineering