Kai-Wei Chang

Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory

Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards

Long-horizon agents have drawn growing attention for their ability to work autonomously -- from hours to days -- on economically valuable tasks, a capability essential to automated discovery and recursive self-improvement (RSI). Yet open-source models still struggle on long-horizon tasks, largely for lack of both train...

Planned Test-Time Scaling with Coordinated Reasoning Paths

Planned Test-Time Scaling (PTTS) provides a general framework for improving test-time scaling by coordinating reasoning branches, with zero-shot and trainable instantiations that yield substantial performance gains.

PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback

MTPaperBananaBench, a benchmark for multi-turn diagram generation containing 292 images annotated with 3,518 user requirements, is presented and PaperBanana-Interact, a multi-agent system that refines diagrams via an internal critique-and-refine loop is introduced.