arXiv Computation and Language November 2, 2026 By Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang

Ctrl-G: Controlling Structural and Interaction Exposure in Knowledge Graph Augmented LLM Reasoning

Read the original on arXiv Computation and Language →

Ctrl‑G is a knowledge‑graph augmented retrieval‑augmented generation (KG‑RAG) framework that jointly limits structural and interaction exposure when sending graph evidence to a remote large language model (LLM). It constructs query‑conditioned sanitized views via structural aggregation and pruning, and uses a hierarchical controller to prune exploration paths while verifying evidence against the original KG. By reusing abstract, verified reasoning traces in local memory, Ctrl‑G reduces repeated disclosure across questions and achieves the highest accuracy on five of six benchmarks, outperforming the strongest baseline by up to 13.8 points.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Computation and Language

Oct 1

Explore-on-Graph: Hybrid Embedding-LLM Reasoning for Knowledge Graph Question Answering under Incompleteness

arXiv:2609.39786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based...

By Ola El Khatib, Djellel Difallah

llms rag nlp benchmarks

arXiv AI

Jul 2

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning

arXiv:2607. 00341v1 Announce Type: cross Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT).

By Hengyu Fu, Tianyu Guo, Zixuan Wang, Hanlin Zhu, Jason D. Lee, Jiantao Jiao, Stuart Russell, Song Mei

llms rag benchmarks

arXiv AI

Oct 7

Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

arXiv:2610.08388v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on kno...

By Yang Hong, Yajun Yang, Xin Wang, Liping Jing, Qinghua Hu

llms rag nlp efficiency benchmarks safety

arXiv AI

5d ago

ImplicitHop: Evaluating knowledge integration across context and memory

arXiv:2610.41169v1 Announce Type: new Abstract: The ability to integrate new information and deduce its consequences is central to learning, understanding, and reasoning in large language models (LLM...

By Alexander Detkov, Dashiel Karish, Matthew Oleynikov, Matt Thomson

llms agents benchmarks

arXiv AI

Sep 24

The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA

The paper investigates how small language models (SLMs) perform in knowledge graph question answering (KGQA) when evaluated on the reasoning paths they take, rather than just the final answer. Using the THESEUS navigation and traceability framework, the authors test frozen, off‑the‑shelf SLMs as local action policies that choose graph actions and decide when to stop, without any task‑specific training or free‑form answer generation. By measuring both Hits@1 and Path Edit Distance (PED) across the Kinship and MQuAKE‑ST datasets, the study finds that models vary significantly in both answer accuracy and path fidelity, and that prompting can either help or hurt navigation depending on the model. "whyItMatters":"The results show that evaluating SLMs solely on endpoint accuracy can be misleading, highlighting the need to assess reasoning path fidelity in KGQA tasks."

By Eduin E. Hernandez, Sergio A. Diaz, Luis F. Garcia, Nurassyl Askar, Stefano Rini

llms nlp

arXiv AI

Oct 27

GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning

arXiv:2602.02518v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many knowledge sources on the Web, such as sc...

By Yuyang Bai, Zhuofeng Li, Ping Nie, Jianwen Xie, Yu Wang, Yu Zhang

llms agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Explore-on-Graph: Hybrid Embedding-LLM Reasoning for Knowledge Graph Question Answering under Incompleteness

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning

Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

ImplicitHop: Evaluating knowledge integration across context and memory

The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA

GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning