Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
TabClaw's combination of transparent, editable execution plans with a self-evolving skill and memory system directly addresses the transparency and adaptability gaps the paper identifies in current LLM-based data-analysis agents.
Teams building agentic coding pipelines for real-world software engineering — where public test cases don't exist before implementation — can use DryRUN's approach to achieve competitive code generation quality without the manual overhead of authoring input-output examples.
Teams building AI-powered web development tools can use WebGen-R1's RL approach and multimodal reward design as a blueprint for training small, efficient models to handle full project-level code generation without relying on expensive proprietary APIs.
AI/coding practitioners building or evaluating biological ML pipelines can use AblateCell to automate the otherwise manual, error-prone process of reproducing baselines and identifying which model components actually drive performance gains.