Repository Issue Activity (beta)

#133 Two v2 bugs (F11 VLM whitelist rejection, F13 UnboundLocalError on pdf_path) reproduce in 24/24 biomedical-prompt runs at SHA 96bd51617

#41 Error in using --load-code

#125 `find_pdf_path_for_review` raises UnboundLocalError when no reflection PDF exists, crashing the run at the final review step

#127 Stage summaries are only persisted after all 4 stages finish — interrupted runs leave complete journals but no summaries, blocking the writeup stage

#126 Plot aggregator asks the LLM to guess experiment_data.npy structure → empty figure sets that 5 reflection rounds cannot fix; attach a real data-structure manifest to the prompt

#124 Writeup: retries delete previously produced PDFs, the returned success flag is unreliable, and the final reflection can leave a corrupted template.tex that no longer matches the emitted PDF

#123 End-of-run cleanup SIGTERMs unrelated processes machine-wide (substring match on "python"/"torch"/"mp" cmdlines)

#122 Tree search: a single failed worker node aborts the entire run (`raise` in result-collection loop of `ParallelAgent.step`)

#119 RFC: optional add-ons for reproducibility, token cost, and cross-run memory (happy to PR in small pieces)

#117 Order of experimentation stages

#111 Feature request: official Claude Code / Codex compatibility

#115 “Kepemimpinan Perempuan dalam TPQ Nurul Karomah, Umbulsari Jember: Agama sebagai Infrastruktur Budaya dan Arena Negosiasi Gender”

#101 求问如何使用本地部署的大模型

#105 Error HTTPError: 403 Client Error: Forbidden for url: https://api.semanticscholar.org/graph/v1/paper/search?query=

#106 BMAL1 alleviates esophageal ischemia-reperfusion injury following anterior cervical spinal surgery by activating the SIRT1/PGC-1α axis: evidence from vitro studies

#104 Agentic tree search for scientific discovery!

#103 💡 Resources for reaching ML practitioners beyond the research community

#102 Request: Support Chinese LLMs & APIs like Z.AI, Kilo, MiniMax, OpenCode Go/Zen, OpenRouter, etc

#100 RFC: Behavioral consistency monitoring across BFTS phases to detect silent context drift

#42 Error in overall_summarize function

#8 Does the v2 version project still support DeepSeek?

#96 [Question] Support for unlisted SOTA models (gemini-3.1-pro, gpt-5.4) currently hardcoded in llm.py?

#94 [email protected]

#85 SakanaAI/AI-Scientist-v2 has a Nerq Trust Score of 81.9/100 — verified badge available

#49 Notes on AlphaEvolve