LLM Evaluation
Brendon.BOT has curated 3 items on llm evaluation across 2 shelves (blog, papers), with available analysis and source links. Historical and pinned items may not have a current quality assessment.
Papers (2)
-
AgentSWE: Can Coding Agents Build the Agent You Actually Want?
arXiv
AgentSWE tests whether a built agent meets the requirement on held-out cases, beyond the builder’s demo.
-
Learning to Discover Interesting Mathematics
A proof-length objective guides theorem generation; its novelty measure is limited to the evaluated formal library.