Running Repro: From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training ๐ฏ
Running Repro: Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information ๐ณ Browse and sync experiment logbook with an AI agent
Running Repro: Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning ๐ Track experiments and sync findings with an AI agent
Running Repro: Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation (ROSA2) ๐ Collaborate on a shared logbook with your coding agent
Running Repro: #11927 โ CoEvol-NO: State and Coordinate Co-Evolution with an Error-Driven Predictor-Corrector Paradigm for Neural Operator Transformer ๐ฏ Browse and collaborate on project logbooks online
Running Repro: Persistent Semantic Entities in Tool-Augmented LLM Systems ๐ฏ Browse and collaborate on AI agent logbook entries