Kun Luo

CANVAS: Continuity-Aware Narrative Generation via Visual Agentic Storyboarding . Findings of Empirical Methods in Natural Language Processing , 2026.

FALCA: Falsification-Aware Reinforcement Learning with Hierarchical Credit Assignment for Long-Horizon Deep Search Agents

FALCA is proposed, a falsification-aware framework that formulates deep search as a propose-falsify process and improves long-horizon deep search performance over backbone and harness ablations, while reducing confirmation bias and error accumulation through more effective falsification and research-state revision.

AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

Results show that long-horizon reflective data is an effective route toward self-improving agents, and synthesize long-horizon improvement trajectories from machine learning and algorithmic programming tasks, two domains that offer verifiable feedback and reward sustained iteration.

AREX: Towards a Recursively Self-Improving Agent for Deep Research

This work introduces AREX, a family of Recursively Self-Improving (RSI) deep research agents that substantially outperforms comparable-scale baselines and remains competitive with models using substantially more activated parameters.