llm-as-a-verifier

LLM-as-a-Verifier for DeepSeek Harness: continuous reward signals via select / compare / track

DeepSeek Harness plugin that validates and ranks 3/5 independent coding-agent patches before approval-gated apply.

LLM-as-a-Verifier (arXiv:2607.05391) as a dsh plugin — Best-of-N conversation mode: give DeepSeek V4 Flash test-time scaling. Bo5 self-verification hits 88% on Terminal-Bench 2.1, beating some frontier models at a fraction of the cost. Fine-grained logprob-expectation scoring, PPT tournament, zero-config.

LLM-as-a-Verifier plugin for DeepSeek Harness — fine-grained reward tools (verify_compare / verify_select / verify_track) with Probabilistic Pivot Tournament, plus a Best-of-N conversation mode with a Web settings panel.

Three-plane probabilistic verifier for DeepSeek Harness: tiered logprob/sample/template judges, seeded tournament best-of-N, layered context reflux.