Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models

arXiv:2603.16654 · cs.CL, cs.AI, cs.LG · Submitted 2026-03-17 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-03-17

Updated: 2026-08-25

Comments: EMNLP 2026 Findings

Code: https://github.com/XiaojieGu/Omanic

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 36× in this paper · explained in 1 episode
• Benchmark — 24× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 10× in this paper · explained in 3 episodes
• Core — 8× in this paper · explained in 2 episodes
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Consistency — 6× in this paper · explained in 3 episodes
• Exact Match — 4× in this paper
• Adam — 3× in this paper · explained in 2 episodes
• GRPO — 3× in this paper · explained in 6 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Knowledge Graph — 2× in this paper · explained in 7 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Multiple-Choice Question — 2× in this paper
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Transferability — 2× in this paper · explained in 4 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought (CoT) Prompting — 1× in this paper · explained in 3 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes

Sources

• Qwen3 Technical Report
• Training Verifiers to Solve Math Word Problems
• MoreHopQA: More Than Multi-hop Reasoning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
• Measuring Mathematical Problem Solving With the MATH Dataset
• The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
• OpenAI GPT-5 System Card

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering