ArXiv ID: 2603.20105
Summary: LLMs used as reasoners are often bottlenecked by fixed context windows. Recursive Language Models (RLMs) address this by solving subproblems recursively. λ-RLM is a framework for long-context reasoning that replaces free-form recursive code generation with a typed functional runtime grounded in λ-calculus. It turn recursive reasoning into a structured functional program with explicit control flow and formal guarantees, including termination and closed-form cost bounds.