paper / douwekiela / May 27 / failedBlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs
paper / douwekiela / May 15 / failedBLITZRANK: Principled Zero-shot Ranking Agents with Tournament Graphs
paper / douwekiela / May 15 / failedExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extraction
paper / douwekiela / May 15 / failedSingle-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
paper / douwekiela / May 15 / failedReflective Context Learning: Studying the Optimization Primitives of Context Space