3 papers indexed here
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.
Recursive self-improvement (RSI) of agent harnesses has emerged as an effective approach to enhancing the capabilities of large language model (LLM) agents. By searching the harness space for a specific LLM on a given dataset, RSI can discover a harness tailored to the capabilities and behavioral characteristics of tha...
High renewable energy penetration significantly increases source-side uncertainty and makes power and energy balancing more difficult under carbon emission constraints. To improve the multi-time-scale power and energy balance of highly uncertain power systems, this paper proposes a low-carbon coordinated optimization m...
This work proposes Ecdysis, which aggregates failure evidence across task instances before promoting recurring failure patterns into persistent harness evolution, biasing evolution toward repairs that are more likely to generalize beyond individual model behaviors.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
