[ { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Scalar-Score Search", "name": "APE", "key": "zhou2023large" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Scalar-Score Search", "name": "OPRO", "key": "yang2024large" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Textual-Gradient Critique", "name": "ProTeGi", "key": "pryzant2023automatic" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Textual-Gradient Critique", "name": "TextGrad", "key": "yuksekgonul2025textgrad" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Textual-Gradient Critique", "name": "GEPA", "key": "agrawal2026gepa" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Textual-Gradient Critique", "name": "Trace", "key": "cheng2024trace" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Textual-Gradient Critique", "name": "metaTextGrad", "key": "xu2025metatextgrad" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Textual-Gradient Critique", "name": "EGO-Prompt", "key": "zhao2025egoprompt" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Textual-Gradient Critique", "name": "SePO", "key": "tao2026sepo" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Self-Referential Mutation", "name": "Promptbreeder", "key": "fernando2024promptbreeder" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Self-Referential Mutation", "name": "DelvePO", "key": "tao2025delvepo" }, { "branch": "Interpreted Update Targets", "sub": "Prompts & Instructions", "mechanism": "Self-Referential Mutation", "name": "DEEVO", "key": "nair2025deevo" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "Reflexion", "key": "shinn2023reflexion" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "ExpeL", "key": "zhao2024expel" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "AWM", "key": "wang2025workflow" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "Agent KB", "key": "tang2025agentkb" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "ReasoningBank", "key": "ouyang2026reasoningbank" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "EvoRepair", "key": "hu2026evorepair" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "SWE-Exp", "key": "chen2025sweexp" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "MemCoder", "key": "deng2026memcoder" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Experience Mining", "name": "Memory Transfer", "key": "kim2026memorytransfer" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "Trace2Skill", "key": "ni2026trace2skill" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "SkillClaw", "key": "ma2026skillclaw" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "CodeSkill", "key": "li2026codeskill" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "GSkill", "key": "tan2026gskill" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "GSE", "key": "yang2026gse" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "MUSE-Autoskill", "key": "lin2026muse" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "MemP", "key": "fang2026memp" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "Skill Consumption", "key": "huang2026consumption" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Procedural Skillbooks", "name": "SkillForge", "key": "liu2026skillforge" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "Dynamic Cheatsheet", "key": "suzgun2026dynamic" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "ACE", "key": "zhang2026agentic" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "SkillOpt", "key": "yang2026skillopt" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "SkillOpt-Lite", "key": "shen2026skilloptlite" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "Janus", "key": "chen2026prologue" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "VALVE", "key": "wang2026valve" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "TACO", "key": "ren2026taco" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "SkillMOO", "key": "gong2026skillmoo" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "EffiSkill", "key": "wang2026effiskill" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "VASO", "key": "yang2026vaso" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "Memory Management", "key": "xiong2026memorymgmt" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "MCE", "key": "ye2026meta" }, { "branch": "Interpreted Update Targets", "sub": "Memory & Procedures", "mechanism": "Gated Consolidation", "name": "Living-Harness", "key": "du2026livingharness" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Fixed-Pipeline Compilation", "name": "DSPy", "key": "khattab2024dspy" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Fixed-Pipeline Compilation", "name": "MIPRO", "key": "opsahlong2024optimizing" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Graph & Topology Search", "name": "GPTSwarm", "key": "zhuge2024gptswarm" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Graph & Topology Search", "name": "Mass", "key": "zhou2026multiagent" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Graph & Topology Search", "name": "MaAS", "key": "zhang2025supernet" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Graph & Topology Search", "name": "AFlow", "key": "zhang2025aflow" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Graph & Topology Search", "name": "AgentSquare", "key": "shang2025agentsquare" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Feedback-Driven Workflow Revision", "name": "SEW", "key": "liu2025sew" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Feedback-Driven Workflow Revision", "name": "JudgeFlow", "key": "ma2026judgeflow" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Feedback-Driven Workflow Revision", "name": "RHI", "key": "lee2026rhi" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Feedback-Driven Workflow Revision", "name": "Meta-Team", "key": "hao2026evolveteam" }, { "branch": "Interpreted Update Targets", "sub": "Workflows & Topologies", "mechanism": "Feedback-Driven Workflow Revision", "name": "Symbolic Learning", "key": "ou2025symbolic" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Callable Tool Synthesis", "name": "Voyager", "key": "wang2024voyager" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Callable Tool Synthesis", "name": "PolySkill", "key": "yu2025polyskill" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Callable Tool Synthesis", "name": "FlowEvo", "key": "ren2026flowevo" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Callable Tool Synthesis", "name": "Live-SWE-agent", "key": "xia2025liveswe" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Callable Tool Synthesis", "name": "RoboPhD", "key": "borthwick2026robophd" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "Self-Harness", "key": "zhang2026selfharness" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "HarnessCompass", "key": "zhang2026harnesscompass" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "AHE", "key": "lin2026agentic" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "HarnessFix", "key": "chen2026harnessfix" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "ReCreate", "key": "hao2026recreate" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "AutoSaddler", "key": "park2026autosaddler" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "CHASE", "key": "zhu2026badgenius" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "Evo-Harness", "key": "wei2026evoharness" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "HarnessBank", "key": "luo2026harnessbank" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "Ecdysis", "key": "yue2026ecdysis" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "MemEvolve", "key": "zhang2025memevolve" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "GUI-HARVEST", "key": "yang2026guiharvest" }, { "branch": "Executable Update Targets", "sub": "Tools & Code Patches", "mechanism": "Evidence-Grounded Component Patching", "name": "Harness Ceiling", "key": "tian2026ceiling" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Whole-Control-Program Search", "name": "ADAS", "key": "hu2025automated" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Whole-Control-Program Search", "name": "Meta-Harness", "key": "lee2026metaharness" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Whole-Control-Program Search", "name": "RRSI", "key": "xia2026rrsi" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Whole-Control-Program Search", "name": "VERSE", "key": "wang2026verse" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "SICA", "key": "robeyns2025selfimproving" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "DGM", "key": "zhang2026darwin" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "DarwinX", "key": "zhang2026darwinx" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "HGM", "key": "wang2025huxley" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "Group-Evolving Agents", "key": "weng2026gea" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "MOSS", "key": "cai2026moss" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "Ouroboros", "key": "razzhigaev2026ouroboros" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "AgentDevel", "key": "zhang2026agentdevel" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "Repository Revision", "name": "EvolveNet", "key": "nie2026evolvenet" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "In-Process Patching", "name": "Gödel Agent", "key": "yin2025godel" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "In-Process Patching", "name": "TTHE", "key": "nie2026tthe" }, { "branch": "Executable Update Targets", "sub": "Repository & Runtime Logic", "mechanism": "In-Process Patching", "name": "Life-Harness", "key": "xu2026lifeharness" }, { "branch": "Executable Update Targets", "sub": "Everything Is a Plugin", "mechanism": "Contract-Driven Hooks", "name": "HarnessX", "key": "chen2026harnessx" }, { "branch": "Executable Update Targets", "sub": "Everything Is a Plugin", "mechanism": "Contract-Driven Hooks", "name": "Argus", "key": "li2026argus" }, { "branch": "Executable Update Targets", "sub": "Everything Is a Plugin", "mechanism": "Microkernel Platforms", "name": "DeepSeek Harness", "key": "deepseek2026harness" }, { "branch": "Executable Update Targets", "sub": "Everything Is a Plugin", "mechanism": "Microkernel Platforms", "name": "Autogenesis", "key": "zhang2026autogenesis" }, { "branch": "Executable Update Targets", "sub": "Everything Is a Plugin", "mechanism": "Microkernel Platforms", "name": "ModularRSI", "key": "wu2026modularrsi" }, { "branch": "Executable Update Targets", "sub": "Everything Is a Plugin", "mechanism": "Microkernel Platforms", "name": "Cordis / Spatiotemporal Composability", "key": "shi2026programming" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Selection & Oracle Integrity", "name": "RSEA", "key": "nguyen2026rsea" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Selection & Oracle Integrity", "name": "Anytime Certificates", "key": "sengupta2026sea" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Selection & Oracle Integrity", "name": "HarnessOpt-Bench", "key": "ursekar2026harnessoptbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Selection & Oracle Integrity", "name": "Phantom Guardrails", "key": "wang2026phantom" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Selection & Oracle Integrity", "name": "Harness Tampering", "key": "wang2026tampering" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Selection & Oracle Integrity", "name": "Self-Authored Verification", "key": "guo2026selfverification" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Selection & Oracle Integrity", "name": "SWE-bench+", "key": "aleithan2024swebenchplus" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Runtime Activation", "name": "SkillsBench", "key": "li2026skillsbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Runtime Activation", "name": "Harness Updating ≠ Harness Benefit", "key": "lin2026updating" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Runtime Activation", "name": "Skill Revisions", "key": "wang2026skillrevisions" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Agents That Matter", "key": "kapoor2025matter" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Token Cost", "key": "bai2026agentcost" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "MLE-bench", "key": "chan2025mlebench" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "HAL", "key": "kapoor2026holistic" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Claw-Eval", "key": "ye2026claweval" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "AgentRewardBench", "key": "lu2025agentrewardbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Judge Inflation", "key": "pan2024spontaneous" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Memory Reward Inflation", "key": "asadolahi2026inflation" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Who Grades the Grader", "key": "zhang2026gradergrader" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Don't Blame the LLM", "key": "bensghaier2026blame" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Scaffold Effect", "key": "vats2026scaffold" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Rethinking Harness Evaluation", "key": "wang2026rethinking" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Attribution Controls", "name": "Model–Harness Fit", "key": "li2026rightfit" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Generalization & Retention", "name": "HarnessDev", "key": "wu2026harnessdev" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Generalization & Retention", "name": "GDPevo", "key": "zhou2026gdpevo" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Generalization & Retention", "name": "EvoHarnessBench", "key": "ke2026evoharnessbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Generalization & Retention", "name": "PATH-Bench", "key": "yang2026pathbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Generalization & Retention", "name": "Agent Plasticity", "key": "singh2026plasticity" }, { "branch": "Evaluation & Benchmarks", "sub": "Claim-Specific Evidence", "mechanism": "Generalization & Retention", "name": "Skill Generalization", "key": "piao2026skillgeneralize" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Active-Set Integrity", "name": "Ratchet", "key": "zhang2026ratchet" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Active-Set Integrity", "name": "SkillsVote", "key": "liu2026skillsvote" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Active-Set Integrity", "name": "Library Drift", "key": "zhang2026librarydrift" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Active-Set Integrity", "name": "Pre-Commit Gating", "key": "shang2026backfires" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Active-Set Integrity", "name": "EVOMAL", "key": "wu2026evomal" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Synthesized Boundary Tasks", "name": "Benchmark Self-Evolving", "key": "wang2024benchmarkselfevolving" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Synthesized Boundary Tasks", "name": "StressEval", "key": "chen2026stresseval" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Temporal Streams", "name": "LiveBench", "key": "white2025livebench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Temporal Streams", "name": "LiveCodeBench", "key": "jain2024livecodebench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Temporal Streams", "name": "LiveMedBench", "key": "yan2026livemedbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Temporal Streams", "name": "SWE-rebench", "key": "badertdinov2025swerebench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Temporal Streams", "name": "SWE-bench Live", "key": "zhang2025swebenchlive" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Adversarial Play", "name": "MathDuels", "key": "xu2026mathduels" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Adversarial Play", "name": "Red Queen Gödel Machine", "key": "iacob2026redqueen" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "LifelongAgentBench", "key": "zheng2025lifelongagentbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "PAST-Bench", "key": "xue2026pastbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "SEA-Eval", "key": "jiang2026seaeval" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "FinEvo-Bench", "key": "deng2026finevobench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "ContinualSkillBench", "key": "guan2026continualskillbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "SkillFlow", "key": "zhang2026skillflow" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "SkillLearnBench", "key": "zhong2026skilllearnbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "MemoryArena", "key": "he2026memoryarena" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "Evo-Memory", "key": "wei2025evomemory" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "Tool-Genesis", "key": "xia2026toolgenesis" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "SWE-EVO", "key": "le2025sweevo" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "CL-Bench", "key": "asawa2026clbench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "SEABench", "key": "das2026seabench" }, { "branch": "Evaluation & Benchmarks", "sub": "Longitudinal & Dynamic Evidence", "mechanism": "Lifelong Testbeds", "name": "ServeLearnBench", "key": "zheng2026servelearnbench" } ]