Tag
DeReAct decomposes ReAct-style agents into a task-solving Brain plus two gating policies (a Critic for action validation and a Context Manager for completion certification), improving Pass@1 on GAIA and SWE-bench Verified especially for weaker models like Qwen3-Coder-480B and Claude Sonnet 4.5.
A tweet recommending the paper ReAct: Synergizing Reasoning and Acting in Language Models by Shunyu Yao et al., which introduced a simple yet foundational approach for building AI agents that reason and act iteratively.
This paper introduces GraphReAct, a framework that extends reasoning-acting paradigms to graph-structured data for multi-step inference. It combines topological and semantic retrieval with context refinement to improve performance on graph learning benchmarks.