We have 4 of 10 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Early experiment shows rule distillation from a single model's failures underperforms the baseline cheat sheet on non-source model families, which motivates Robust Failure, Conservative Repair (RFCR), a textual distillation procedure that derives rules from failures shared across models, sharpens their application boun...
The results suggest that multi-agent performance depends less on the number of agents than on the information they exchange, and interaction helps only when agents share the right information at the right time.
The EM generalization metric is extended from a scalar distance to a dataset-specific generalization direction, which robustly predicts EM models'evilness under semantics-preserving prompt perturbations including appending random tokens and paraphrasing, where other methods do not reliably generalize.
This work presents VERITAS, a domain-agnostic replication framework built around CLI coding agents, which achieves state-of-the-art performance and leads on every metric on both benchmarks.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
