Related papers: OPERA: A Reinforcement Learning--Enhanced Orchestr…

Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning. To bridge this gap, traditional process supervision relies on learned reward models requiring costly training…

Operations Research (OR) relies on expert-driven modeling-a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization models, existing…

Offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance by leveraging historical interaction data collected from other policies. Evaluating a new policy online without a…

Vision-language retrieval-augmented generation (RAG) has become an effective approach for tackling Knowledge-Based Visual Question Answering (KB-VQA), which requires external knowledge beyond the visual content presented in images. The…

Retrieval-augmented generation (RAG), which combines large language models (LLMs) with retrievals from external knowledge databases, is emerging as a popular approach for reliable LLM serving. However, efficient RAG serving remains an open…

Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and mitigate hallucination. However, dense retrievers often become the bottleneck of RAG systems due to…

Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. It presents two key challenges: generating correct reasoning paths in response to the complex user queries, and accurately retrieving essential…

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most…

Group Relative Policy Optimization (GRPO), which is widely adopted by R1-like reasoning models, has advanced mathematical reasoning. Nevertheless, GRPO faces challenges in reward sparsity, verbosity, and inadequate focus on problem…

Retrieval-Augmented Generation (RAG) systems are increasingly diverse, yet many suffer from monolithic designs that tightly couple core functions like query reformulation, retrieval, reasoning, and verification. This limits their…

Large Language Models (LLMs) have been increasingly employed for query expansion. However, their generative nature often undermines performance on complex multi-hop retrieval tasks by introducing irrelevant or noisy information. To address…

Recent advancements in QA with LLM, like GPT-4, have shown limitations in handling complex multi-hop queries. We propose AT-RAG, a novel multistep RAG incorporating topic modeling for efficient document retrieval and reasoning. Using…

Given the growing trend of many organizations integrating Retrieval Augmented Generation (RAG) into their operations, we assess RAG on domain-specific data and test state-of-the-art models across various optimization techniques. We…

Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two…

Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However, traditional RAG systems are limited by static workflows…

Retrieval-augmented generation (RAG) has been widely adopted to ground large language models (LLMs) in external knowledge, yet it remains largely underexplored for improving reasoning. Existing methods either rely on online exploration…

There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and…

In AI research, synthesizing a plan of action has typically used descriptive models of the actions that abstractly specify what might happen as a result of an action, and are tailored for efficiently computing state transitions. However,…

Optimization modeling and solving are fundamental to the application of Operations Research (OR) in real-world decision making, yet the process of translating natural language problem descriptions into formal models and solver code remains…

Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…