ResearchCodified Context Three-Component Infrastructure for Agent CodingarXiv·high signalXBlueskyLinkedInCopy linkHot memory + 19 agents + cold knowledge base. Evaluated across 283 sessions on 108K-line codebase. Open-source.SourceSource pagearXiv↳ Follow the threadPolicy dependency / Stack layerPRAXIS harvests undocumented business rules by simulating developer workflows, then indexes them on the dependency grapharXiv 2608.19784Policy dependency / Stack layerSAPO Shares One Autoregressive Backbone for Policy and Value, Beating PPO by 15.1 Points With No Separate CriticarXiv 2608.19842Policy dependency / Stack layerPolicyGuide Compiles Policy Into a Workflow Graph and Lifts tau^2-bench Pass^4 From 0.42 to 0.62arXiv 2608.19861Stack layer / ContrastEvaluation Context Protocol proposes a JSON-RPC contract layer for agent evals across frameworksarXivStack layer / ContrastFirst Provable Skill-Selection Algorithm Hits 0.73 Task Success Against 0.20-0.52 for Released Skill Routers, on 28% Fewer TokensarXiv 2608.19993Stack layer / ContrastSafety Nets Shrink Certifiable Aviation Neural Networks by Three Orders of Magnitude With 100% Correct Runtime BehaviorarXiv 2608.20053Stack layer / ContrastCoding Agents Spend 60.5% of Their Documentation Time on Instruction Files and Notes, Not Your DocsarXiv 2608.20195Policy dependency / Stack layerBreakGuard Catches 30.3% of Real Dependency Breaking Changes at About $0.90 EacharXiv 2608.20167