MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

TL;DR

This paper introduces MiroThinker-1.7 and H1, advanced research agents with enhanced reasoning and verification capabilities, achieving state-of-the-art results in complex, multi-step research tasks across various domains.

Contribution

The paper presents MiroThinker-1.7 and H1, novel research agents with structured planning, verification, and multi-step reasoning, improving reliability and performance in complex tasks.

Findings

Achieves state-of-the-art performance on research benchmarks.

Improves multi-step reasoning reliability through structured planning.

Incorporates verification for coherent evidence chains.

Abstract

We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends the agent with heavy-duty reasoning capabilities for more reliable multi-step problem solving. In particular, MiroThinker-1.7 improves the reliability of each interaction step through an agentic mid-training stage that emphasizes structured planning, contextual reasoning, and tool interaction. This enables more effective multi-step interaction and sustained reasoning across complex tasks. MiroThinker-H1 further incorporates verification directly into the reasoning process at both local and global levels. Intermediate reasoning decisions can be evaluated and refined during inference, while the overall reasoning trajectory is audited to ensure that final answers are supported by coherent chains of evidence. Across benchmarks covering open-web research, scientific reasoning, and financial analysis, MiroThinker-H1 achieves state-of-the-art performance on deep research tasks while maintaining strong results on specialized domains. We also release MiroThinker-1.7 and MiroThinker-1.7-mini as open-source models, providing competitive research-agent capabilities with significantly improved efficiency.