Related papers: REX: Rapid Exploration and eXploitation for AI Age…
Existing value-based online reinforcement learning (RL) algorithms suffer from slow policy exploitation due to ineffective exploration and delayed policy updates. To address these challenges, we propose an algorithm called Instant…
AI agents, empowered by Large Language Models (LLMs) and communication protocols such as MCP and A2A, have rapidly evolved from simple chatbots to autonomous entities capable of executing complex, multi-step tasks, demonstrating great…
In this work, we benchmark various graph-based retrieval-augmented generation (RAG) systems across a broad spectrum of query types, including OLTP-style (fact-based) and OLAP-style (thematic) queries, to address the complex demands of…
Search agents powered by Large Language Models (LLMs) have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement learning (RL) has emerged as a powerful paradigm for training these agents to perform…
Code Search is a key task that many programmers often have to perform while developing solutions to problems. Current methodologies suffer from an inability to perform accurately on prompts that contain some ambiguity or ones that require…
Retrieval-augmented generation (RAG) has been extensively employed to mitigate hallucinations in large language models (LLMs). However, existing methods for multi-hop reasoning tasks often lack global planning, increasing the risk of…
Embodied agents operating in complex and uncertain environments face considerable challenges. While some advanced agents handle complex manipulation tasks with proficiency, their success often hinges on extensive training data to develop…
Standard Retrieval Augmented Generation (RAG) is poorly matched to agent memory. Unlike large heterogeneous corpora, agent memory forms a bounded and coherent interaction stream in which many spans are highly correlated or near duplicates.…
We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity…
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-step reasoning. Agentic RAG addresses this by enabling LLMs…
We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to new instantiations of themselves recursively. Recursive agents implement an…
A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…
On-policy reinforcement learning (RL) algorithms have demonstrated great potential in robotic control, where effective exploration is crucial for efficient and high-quality policy learning. However, how to encourage the agent to explore the…
Retrieval-augmented generation systems often assume that one fixed retrieval pipeline is sufficient across heterogeneous tasks, yet factoid question answering, multi-hop reasoning, and scientific verification exhibit different retrieval…
World models are increasingly pivotal in interpreting and simulating the rules and actions of complex environments. Genie, a recent model, excels at learning from visually diverse environments but relies on costly human-collected data. We…
Query optimization is a crucial component for the efficacy of Retrieval-Augmented Generation (RAG) systems. While reinforcement learning (RL)-based agentic and reasoning methods have recently emerged as a promising direction on query…
Providing Reinforcement Learning (RL) agents with human feedback can dramatically improve various aspects of learning. However, previous methods require human observer to give inputs explicitly (e.g., press buttons, voice interface),…
Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison:…
Multi-agent Retrieval-Augmented Generation (RAG), wherein each agent takes on a specific role, supports hard queries that require multiple steps and sources, or complex reasoning. Existing approaches, however, rely on static agent behaviors…
Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate…