# Knowledge- and tool-augmented reasoning

Area: [LLM reasoning](https://mlsanity.com/lr/index.md). HTML: https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/

## Key facts

- Knowledge- and tool-augmented reasoning: 1,305 papers on arXiv since 2021 (data through 14 Oct 2026).
- 143 of its 1,305 mapped papers (11%) cite “Retrieval-Augmented Generation for Large Language Models: A Survey” (2023, arXiv 2312.10997).
- 123 of its 1,305 mapped papers (9%) cite “Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions” (2022, arXiv 2212.10509).
- 35 new papers 17 Sep–14 Oct.

## Most cited here

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023), cited by 143 papers here
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022), cited by 123 papers here
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025), cited by 108 papers here
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023), cited by 96 papers here
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023), cited by 89 papers here
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025), cited by 73 papers here
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025), cited by 66 papers here
- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024), cited by 51 papers here
- [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025), cited by 47 papers here
- [UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph](https://mlsanity.com/paper/2212.00959/) (2022), cited by 41 papers here

## New (17 Sep–14 Oct)

- [Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains](https://mlsanity.com/paper/2610.20328/) (2026-10-14)
- [Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces](https://mlsanity.com/paper/2610.18606/) (2026-10-13)
- [Label-Centric Knowledge Retrieval for Zero-Shot Text Classification](https://mlsanity.com/paper/2610.16182/) (2026-10-12)
- [Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving](https://mlsanity.com/paper/2610.16133/) (2026-10-12)
- [CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition](https://mlsanity.com/paper/2610.15298/) (2026-10-11)
- [Enhancing Legal Reasoning in Pre-trained Language Models via Knowledge Graph-Guided Multi-Task Pre-training](https://mlsanity.com/paper/2610.13722/) (2026-10-09)
- [Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph](https://mlsanity.com/paper/2610.13695/) (2026-10-09)
- [SEEDS: Preview-Guided Evidence Admission for Search Agents](https://mlsanity.com/paper/2610.12932/) (2026-10-09)
- [Intent Graph: Navigating the Analytical Reasoning Space for Exploratory Data Analysis](https://mlsanity.com/paper/2610.11025/) (2026-10-08)
- [Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents](https://mlsanity.com/paper/2610.08452/) (2026-10-06)
- [Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering](https://mlsanity.com/paper/2610.08388/) (2026-10-06)
- [From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search](https://mlsanity.com/paper/2610.07960/) (2026-10-06)
- [LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search](https://mlsanity.com/paper/2610.05119/) (2026-10-04)
- [Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning](https://mlsanity.com/paper/2610.01936/) (2026-10-01)
- [MemFit: Efficient Long-Term Agentic Memory](https://mlsanity.com/paper/2610.00872/) (2026-10-01)
- [Ontology-Grounded, Reasoner-Verified Benchmarks for Evaluating LLM Reasoning in Scientific AI](https://mlsanity.com/paper/2610.00682/) (2026-09-30)
- [Explore-on-Graph: Hybrid Embedding-LLM Reasoning for Knowledge Graph Question Answering under Incompleteness](https://mlsanity.com/paper/2609.39786/) (2026-09-30)
- [Does Learning Protein Folding Generalize to Broader Reasoning?](https://mlsanity.com/paper/2609.38879/) (2026-09-30)
- [GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics](https://mlsanity.com/paper/2609.38798/) (2026-09-30)
- [REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing](https://mlsanity.com/paper/2609.36984/) (2026-09-29)
- [SRJudge: Empowering Large Language Models with Selective Reasoning for Fine-Grained Knowledge Concept Tagging](https://mlsanity.com/paper/2609.36982/) (2026-09-29)
- [Evidence-Inference Reconstruction: When The Evidence Is Recalled But The Reasoning Goes Wrong](https://mlsanity.com/paper/2609.33778/) (2026-09-27)
- [Beyond Memory Construction: Rethinking Memory Access for LLM-based Conversational Agents](https://mlsanity.com/paper/2609.33226/) (2026-09-27)
- [HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning](https://mlsanity.com/paper/2609.32327/) (2026-09-26)
- [QReason: Query-Focused Decoupled Chain-of-Thought for Efficient Passage Reranking](https://mlsanity.com/paper/2609.30904/) (2026-09-25)
- [Asymmetric Dynamic Routing: Balancing Reasoning Depth and Computational Efficiency in Hypergraph RAG](https://mlsanity.com/paper/2609.29282/) (2026-09-24)
- [Dual-Hypergraph Indexing: Bridging Knowledge Islands for Multi-Hop Reasoning in Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.28108/) (2026-09-23)
- [Large Knowledge Model: From Papers to a Scientific Reasoning Landscape](https://mlsanity.com/paper/2609.27297/) (2026-09-23)
- [LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning](https://mlsanity.com/paper/2609.27009/) (2026-09-22)
- [LADDER: Graph-Guided Diffusion Language Models for Efficient Multi-Hop Reasoning](https://mlsanity.com/paper/2609.24346/) (2026-09-21)