ARCHER: From Rationale Imitation to Executable Reasoning in Small Language Models
ARCHER is a two-stage framework for training small language models to produce executable, auditable reasoning trajectories for mathematical tasks. The first stage compiles free-form chain-of-thought rationales into typed action traces with reasoning steps, calculator calls, runtime observations, verification actions, and answers. The second stage refines the policy using asymmetric hierarchical reinforcement learning with grouped and conditionally gated trajectory rewards. Across five sub-10B backbones, ARCHER reportedly improves macro-average accuracy by 5.51 percentage points over the strongest tool-augmented baseline, including gains on MATH-500, AIME-2024, and AIME-2025.
It presents a concrete training method with reported benchmark gains for making small language models more reliable at tool-grounded mathematical reasoning.
Comments & Questions (0)
No comments yet
Be the first to comment!