ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following

As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruction itself, especially the latent reasoning structure embedded between the lines, is crucial for improving instruction following. Therefore we target complex instructions that involve implicit reasoning, intricate logical relations, and multiconstraint dependencies. We propose ImpRIF, a method to enhance LLMs' understanding of implicit reasoning instructions, thereby improving its ability to follow complex instructions. We formalize such instructions as verifiable reasoning graphs, enabling programmatic verification and graph-driven chain-of-thought reasoning. Based on this formulation, we synthesize large-scale single-and multi-turn data, propose fine-tuning with graph reasoning, and apply reinforcement learning to explicitly train models to reason along the graph. On five complex instruction following benchmarks, our models substantially outperform their base models. These results demonstrate that enhancing implicit reasoning capabilities can significantly improve complex instruction following. * Equal Contributions † Corresponding Authors Complex Instruction Complex Implicit Reasoning Instruction Multi-hop Reasoning Constraints ... Use subheadings (level 2 headings) ... ; Use at least 2 analogies; Avoid absolute wording (such as "certainly ..."), and if used, add qualifying conditions; ... shall not appear in the full text.