SOURCE-LINKED INTELLIGENCE

Recursive Agentic Reasoning

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Test-time reasoning methods such as iterative refinement, decomposition, and repeated sampling are often evaluated in isolation, making their gains difficult to compare across models, benchmarks, and evaluation pipelines. We introduce a unified view of these methods as recursion operators over an agent's reasoning trace: GROW, which deepens a single reasoning path; PRUNE, which decomposes and recomposes the problem; and BRANCH, which samples alternative reasoning paths and selects among them. We evaluate all three operators against a single-pass chain-of-thought baseline under a shared harness

Read original source ↗ Open in workspace

recordType

paper

region

Global