Entity trail

OpenCoder

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-11 / skill-finderDeterministic rule-guided dispatch beats autonomous code-review agents by 2.17x SEM-F1 on 5–15x fewer tokensOpenCodeReview (arXiv 2608.09290, Aug 10) argues LLM code reviewers fail on two axes — non-determinism from unbounded tool use, and context locality that caps issue depth at the diff — and fixes both by injecting structure at three pipeline points rather than maximizing autonomy. A multi-layer rule system deterministically selects which files get reviewed and against which criteria, grounded per-file review runs on a curated toolset, parallel subagents recover cross-file dependencies, and an Independent Reflection stage applies a falsification-first filter under an asymmetric information boundary to strip hallucinated comments. On 200 real pull requests across 10 languages with 1,505 expert-verified comments it hit 25.10% SEM-F1 versus 11.57% for baseline agents while consuming 5–15x fewer tokens — the pattern generalizes: put the triage in rules, spend the model budget on grounded reading.
2026-07-29 / skill-finderAn uncertainty-aware RAG framework hit 78.13% on repo-level code gen — and a plain verify-and-repair loop matched itOpenCoder estimates source-specific uncertainty across API knowledge, repository context, and similar-code evidence, then uses it to filter and rank evidence and to guide generation, verification, and repair. On an expanded 32-task RepoExec-inline evaluation it lifts GPT selected-output correctness from 56.25% to 78.13%, and target-aware API refinement substantially improves API-set retrieval. The authors report honestly that it merely matches a verification-and-repair control and that the Gemini improvement is not statistically supported — a factorial analysis also found no universal ranking of evidence sources, only cross-source interactions that depend on the backend. Build the cheap verify-and-repair loop first.

Graph relationships

BENCHMARKED AGAINST
GPT
OpenCoder improved GPT selected-output correctness from 56.25% to 78.13% on RepoExec-inline evaluation.
Source finding

Source trail

arXiv 2608.09290 — OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review arXiv 2607.24884 — Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…