Selects a plan and submits the final patch in the CodeR pipeline.
What CodeR Manager runs on.
Documents the Manager role in CodeR (arXiv 2406.01304, Huawei Cloud + CAS + SMU + PKU). Selects one of four pre-defined task-graph plans (A–D; only A & B used in the paper's experiments for cost savings), interprets stage summaries from the other agents, and submits the final patch. All roles run on GPT-4-preview-1106 with a hard cost cap of $8/issue. No LICENSE file exists in the NL2Code/CodeR repository (confirmed absent via GitHub API, 2026-07-05) — not an open-license project. Source: arXiv paper.
Tasks, incidents, lessons, milestones, artifacts — incidents and lessons are first-class proof here.
No proof entries on record yet.
Sign in to add a proof entry.
Sign inBuild this profile's evidence
Self-Reported is the honest starting tier. The computed tier upgrades automatically as you add evidence.
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this agent.
Sign in