Tagged articles

Multi-hop QA

6 articles · Page 1 of 1

Jun 18, 2026 · Artificial Intelligence

How FlowRAG Evolves GraphRAG to Let Evidence Chains Flow Automatically

The article examines FlowRAG, a new variant of GraphRAG that shifts retrieval from similarity‑based text chunk ranking to constructing explicit, frequency‑aware reasoning paths, detailing its three‑step design, benchmark improvements, efficiency gains, and ablation results that reveal how it mitigates entity sparsity and noise propagation.

Dual-Granularity ActivationFlowRAGFrequency-aware weighting

0 likes · 8 min read

How FlowRAG Evolves GraphRAG to Let Evidence Chains Flow Automatically

PaperAgent

Mar 19, 2026 · Artificial Intelligence

How MDER‑DR Boosts Multi‑Hop KG QA with Entity‑Centric Summaries

The article presents the MDER‑DR two‑stage framework that tackles semantic loss in knowledge‑graph triple indexing by generating context‑aware entity summaries and using an LLM‑driven decompose‑parse retrieval loop, achieving up to 66% performance gains on multi‑hop question answering benchmarks.

Entity SummarizationKG QALLM

0 likes · 5 min read

How MDER‑DR Boosts Multi‑Hop KG QA with Entity‑Centric Summaries

Machine Learning Algorithms & Natural Language Processing

Mar 3, 2026 · Artificial Intelligence

Enabling Search Agents to Think While Waiting: Diffusion LLMs Deliver 15% Faster Inference Without Accuracy Loss

The paper introduces DLLM‑Searcher, which equips diffusion large language models with a two‑stage training pipeline and a P‑ReAct inference scheme, allowing the model to issue tool calls while simultaneously reasoning, yielding 14‑22% end‑to‑end speedup and matching or surpassing traditional autoregressive agents on multi‑hop QA benchmarks.

Diffusion LLMMulti-hop QAP-ReAct

0 likes · 10 min read

Enabling Search Agents to Think While Waiting: Diffusion LLMs Deliver 15% Faster Inference Without Accuracy Loss

Machine Learning Algorithms & Natural Language Processing

Feb 15, 2026 · Artificial Intelligence

Embedding Error Correction into the Policy Space: How Search‑R2 Redefines Search‑Enhanced Reasoning

The Search‑R2 framework integrates error detection, localization, and correction into a reinforcement‑learning loop for search‑enhanced reasoning, achieving notably larger accuracy gains on difficult multi‑hop QA tasks than baseline methods, even when those baselines receive higher sampling budgets.

Agentic AIError CorrectionMulti-hop QA

0 likes · 15 min read

Embedding Error Correction into the Policy Space: How Search‑R2 Redefines Search‑Enhanced Reasoning

PaperAgent

Feb 3, 2026 · Artificial Intelligence

Relink: Turning GraphRAG into a Dynamic, Query‑Driven Knowledge Graph

Relink introduces a ‘reason‑and‑construct’ paradigm that builds knowledge‑graph paths during inference, combining a high‑precision factual graph with a high‑recall potential‑relation pool, using query‑driven dynamic path expansion and contrastive alignment to markedly improve multi‑hop QA performance and robustness to sparse knowledge.

Dynamic RetrievalGraphRAGLLM

0 likes · 8 min read

Relink: Turning GraphRAG into a Dynamic, Query‑Driven Knowledge Graph

PaperAgent

Jan 9, 2026 · Artificial Intelligence

Why Traditional RAG Breaks the Chain and How SentGraph Fixes It

The article explains why traditional retrieval‑augmented generation fails in multi‑hop scenarios due to overly large chunks, introduces SentGraph’s sentence‑level graph that trims retrieval units and encodes logical relations, details offline construction and online inference steps, and shows experimental gains and remaining limitations.

LLMMulti-hop QARAG

0 likes · 7 min read

Why Traditional RAG Breaks the Chain and How SentGraph Fixes It