alphaXiv(@askalphaxiv):“AREX: Towards a Recursively Self-Improving Agent for Deep Research” Deep research agents often fail not because they need more search, but because they don’t know which parts of an answer are already verified and which constraints are still unresolved. This paper turns research into a recursive loop: answer, verify constraint-by-constraint, preserve evidence, then refine only the weak parts. AREX adds learned context updates and step-aware RL, achieving extremely strong results with 4B and 122B-A10B models across various agentic benchmarks.

2026.07.28 18:57

“AREX: Towards a Recursively Self-Improving Agent for Deep Research” Deep research agents often fail not because they need more search, but because they don’t know which parts of an answer are already verified and which constraints are still unresolved. This paper turns research into a recursive loop: answer, verify constraint-by-constraint, preserve evidence, then refine only the weak parts. AREX adds learned context updates and step-aware RL, achieving extremely strong results with 4B and 122B-A10B models across various agentic benchmarks.