ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following

arXiv:2602.21228v2 Announce Type: replace Abstract: 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 multi-constraint 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.

Related

• Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch
• From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs
• Do LLMs Encode Functional Importance of Reasoning Tokens?
• Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models
• Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms

Source: arXiv cs.CL | 2026-04-21