Related papers: OpenTable-R1: A Reinforcement Learning Augmented T…

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized…

This paper proposes KB-InfoBot -- a multi-turn dialogue agent which helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to…

Generating complex, logically-sound SPARQL queries for multi-hop questions remains a critical bottleneck for Knowledge Graph Question Answering, as the brittle nature of one-shot generation by Large Language Models (LLMs) hinders reliable…

This work reframes the Text-to-SQL task as a pathway for teaching large language models (LLMs) to reason over and manipulate tabular data--moving beyond the traditional focus on query generation. We propose a two-stage framework that…

Retrieval-augmented question-answering systems combine retrieval techniques with large language models to provide answers that are more accurate and informative. Many existing toolkits allow users to quickly build such systems using…

Research Agents enable models to gather information from the web using tools to answer user queries, requiring them to dynamically interleave internal reasoning with tool use. While such capabilities can in principle be learned via…

Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…

Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal…

Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains…

The performance gap between closed-source and open-source large language models (LLMs) is largely attributed to disparities in access to high-quality training data. To bridge this gap, we introduce a novel framework for the automated…

This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy…

Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself,…

Recent advances in large language models (LLMs) have propelled research in natural language interfaces to databases. However, most state-of-the-art text-to-SQL systems still depend on complex, multi-stage pipelines. This work proposes a…

Temporal Knowledge Graph Question Answering (TKGQA) is inherently challenging, as it requires sophisticated reasoning over dynamic facts with multi-hop dependencies and complex temporal constraints. Existing methods rely on fixed workflows…

Tool-integrated agents that interleave reasoning with API calls are promising for complex tasks, yet aligning them for high-stakes, domain-specific deployment remains challenging: existing reinforcement learning approaches rely on coarse…

Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically…

This work presents a novel four-stage open-domain QA pipeline R2-D2 (Rank twice, reaD twice). The pipeline is composed of a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final…

Repository-level software engineering tasks require large language models (LLMs) to efficiently navigate and extract information from complex codebases through multi-turn tool interactions. Existing approaches face significant limitations:…

Large language models (LLMs) can face factual limitations when responding to time-sensitive queries about recent events that arise after their knowledge thresholds in the training corpus. Existing search-augmented approaches fall into two…

Transformer based architectures are recently used for the task of answering questions over tables. In order to improve the accuracy on this task, specialized pre-training techniques have been developed and applied on millions of open-domain…