[7/7] Ablations: (1) Understanding: dropping semantics hurts function-level localization most; dropping dependencies also lowers retrieval. (2) Reconstruction: removing file/function metadata collapses hierarchy, reducing code volume and pass rate. RPG still beats docs.

[6 / 7] To analyze agent behavior, we see a “search-then-zoom” pattern: traverse RPG first, then fetch details. To diagnose failures, we sample failed runs and group errors (tool/execution, search, reasoning, context) to pinpoint breakpoints.

[5 / 7] To analyze representational efficiency, we report Steps, Cost, and Eff.=Acc@5/Cost on SWE-bench Verified. RPG-Encoder is most cost-effective: ~6–7 steps, $0.18–$0.22 per task, best Eff. (4.63 on GPT-4.1; 4.15 on GPT-5), suggesting less redundant exploration.

4/7] To study RPG evolution, we compare full reconstruction against diff-based incremental updates across repository commits. To our finding, incremental maintenance reduces overhead by 95.7% while keeping the representation lightweight as the repo evolves.

[3/7](1) Repo understanding: evaluated on SWE-bench Verified/Live; 93.7% Acc@5 (Verified) and >+10% over best baseline (Live), showing stronger repo-scale localization. (2) Repo reconstruction: evaluated on RepoCraft; 98.5% coverage, showing RPG is a faithful semantic blueprint.

[2/7] building on RPG/ZeroRepo, we generalize RPG into RPG-Encoder. (i) Encode: code → RPG, fusing lifted semantics + static dependencies. (ii) Evolve: incrementally update graph topology from diffs. (iii) Operate: unify search/fetch/explore for repo-scale navigation.

[1/7] Today's repo agents rely on fragmented artifacts (flat context, docs, partial graphs), losing global consistency. This makes repo-scale navigation/planning brittle—motivating one actionable representation for the whole pipeline.

🔥Stop repo agents from reasoning on fragmented docs/graphs. Building on prior RPG/ZeroRepo, we propose RPG-Encoder: a unified repository planning graph that integrates semantic intent with static structure into one navigable representation.

🔥 Breaking: we just beat Claude Code on repo-level generation. Today we’re releasing Repository Planning Graph (RPG) — a unified graph linking requirements → files → dataflows → functions, for controllable & verifiable repo-scale codegen. 📄 arxiv.org/abs/2509.16198

🎉"FEA-Bench" is accepted at ACL 2025! We introduce a new benchmark of repo-level code generation for feature implementation. LLMs still struggle at, but models like R1 show promise. 📄 arxiv.org/abs/2503.06680 🔗 github.com/microsoft/FEA-Ben… 🤗 huggingface.co/datasets/micr… #LLM #ACL2025

🚀 Introducing EpiCoder: a hierarchical feature tree-based framework for diverse and intricate code generation. 🔍 Outperforming benchmarks, it handles everything from simple functions to multi-file projects deftly. 📢 Open source release soon! 🔗 arxiv.org/abs/2501.04694

🌊🌊🌊Introduce WaveCoder-Ultra-6.7B with the closest capabilities to GPT-4 so far. Arxiv:arxiv.org/abs/2312.14187 WaveCoder-Ultra-6.7B is the newest SOTA open-source Code LLM on mutiple tasks.