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.
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...
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).
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...
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...
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."
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...
The paper introduces CogMem, a cognitive memory architecture for long‑term dialogue agents that uses a PEC$^2$F graph schema to separate claims, facts, and events. Dialogue turns are incrementally turned into provenance‑aware graph records, consolidated into higher‑level facts, and reconciled into temporally scoped claim views when conflicting updates arise. Retrieval is performed by a rule‑based controller that applies deterministic graph operators—anchoring, traversal, intersection, and evidence grounding—guided by LLM intent parsing, achieving strong performance on multi‑hop, temporal, and knowledge‑update tasks in LoCoMo and LongMemEval benchmarks.
FedV-KGQA addresses multi‑hop question answering over vertically partitioned knowledge graphs where each silo holds disjoint relation types. The system trains local embeddings, concatenates silo‑specific entity views, anchors questions at a topic entity, and ranks candidates without sharing raw triples. Experiments show federated fusion nearly matches centralized accuracy, that anchoring and enrichment are more critical than embedding choice, and that the cheapest encoder depends on target accuracy.
KGFR introduces a Knowledge Graph Foundation Retriever that collaborates with large language models to enhance knowledge‑intensive question answering. By encoding relations with LLM‑generated descriptions and initializing entities from question roles, KGFR enables zero‑shot generalization to unseen knowledge graphs. Its Asymmetric Progressive Propagation technique efficiently handles large graphs, while a controllable reasoning loop allows the LLM to request candidate answers, supporting facts, and reasoning paths.
The paper introduces collaborative learning for large language models, where a single large model is replaced by smaller, heterogeneous models—called model slices—under a comparable parameter budget. By enabling prior reasoning to be reassessed across different model parameterizations and employing pyramid supervision that blends protocol distillation with step‑level supervision, the authors refine reasoning and interaction decisions during collaboration. Experiments on multi‑hop question answering, mathematical reasoning, code generation, and open‑ended constrained generation show that the trained heterogeneous models match or surpass the performance of the original large model and established multi‑agent baselines, while also achieving higher inference efficiency and exhibiting task‑specific collaboration patterns.
The paper introduces ParallaxRAG, a multi-view retrieval-augmented generation framework that addresses multi-hop reasoning challenges in large language models over knowledge graphs. It identifies that transformer attention heads specialize in distinct semantic relations across reasoning stages, forming a hop-aligned relay pattern, and proposes decoupling queries and KGs into head-specific semantic spaces to enforce relational diversity. Experiments on WebQSP, CWQ, and BioASQ show state‑of‑the‑art performance, reduced hallucination, and strong generalization.
arXiv:2609.14066v1 Announce Type: cross Abstract: Although existing multi-agent Retrieval-Augmented Generation (RAG) systems have demonstrated promise on complex multimodal reasoning tasks, they rema...