CIIR@LiveRAG 2025: Optimizing Multi-Agent Retrieval Augmented Generation through Self-Training

2025-06-12 · Alireza Salemi, Mukta Maddipatla, Hamed Zamani

This paper presents mRAG, a multi-agent retrieval-augmented generation (RAG) framework composed of specialized agents for subtasks such as planning, searching, reasoning, and coordination. Our system uses a self-training paradigm with reward-guided trajectory sampling to optimize inter-agent collaboration and enhance response generation. Evaluated on DataMorgana-derived datasets during the SIGIR 2025 LiveRAG competition, mRAG outperforms conventional RAG baselines. We further analyze competition outcomes and showcase the framework's strengths with case studies, demonstrating its efficacy for complex, real-world RAG tasks.

📄 PDF Abstract BibTeX arXiv:2506.10844

Code (1)

muktac5/ciir-liverag 공식 구현 pytorch

Tasks

RAG Response Generation RetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge

2025-06-17 · Kun Ran, Shuoqi Sun, Khoi Nguyen Dinh Anh, Damiano Spina 외

This paper presents the RMIT--ADM+S participation in the SIGIR 2025 LiveRAG Challenge. Our Generation-Retrieval-Augmented Generation (GRAG) approach relies on generating a hypothetical answer that is used in the retrieva…

Answer Generation Language Modeling Language Modelling Large Language Model+3

SIGIR 2025 -- LiveRAG Challenge Report

2025-07-07 · David Carmel, Simone Filice, Guy Horowitz, Yoelle Maarek 외 arxiv

The LiveRAG Challenge at SIGIR 2025, held between March and May 2025, provided a competitive platform for advancing Retrieval-Augmented Generation (RAG) technologies. Participants from academia and industry were invited …

RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition

2025-06-17 · Tim Cofala, Oleh Astappiev, William Xion, Hailay Teklehaymanot

Retrieval-Augmented Generation (RAG) enriches Large Language Models (LLMs) by combining their internal, parametric knowledge with external, non-parametric sources, with the goal of improving factual correctness and minim…

Answer Generation RAG Retrieval-augmented Generation

LiveRAG: A diverse Q&A dataset with varying difficulty level for RAG evaluation

2025-11-18 · David Carmel, Simone Filice, Guy Horowitz, Yoelle Maarek 외 arxiv

With Retrieval Augmented Generation (RAG) becoming more and more prominent in generative AI solutions, there is an emerging need for systematically evaluating their effectiveness. We introduce the LiveRAG benchmark, a pu…

SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation

2026-06-29 · Zhiyuan Ma, Zhengfeng Shi, Yuning An, Peize Li 외 hf

While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic alignment and logical reasoning required for scientific imagery. …

Logical Reasoning Image Generation