Related papers: Q-Star Meets Scalable Posterior Sampling: Bridging…
Reinforcement learning (RL) is a framework to optimize a control policy using rewards that are revealed by the system as a response to a control action. In its standard form, RL involves a single agent that uses its policy to accomplish a…
Reinforcement Learning (RL) is an area of machine learning concerned with enabling an agent to navigate an environment with uncertainty in order to maximize some notion of cumulative long-term reward. In this paper, we implement and analyze…
Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored to specific benchmarks, relying on carefully tuned hyperparameters and algorithmic choices. Recently,…
We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel and aggregated into a final response. While such scaling has proven effective for…
Learning tabula rasa, that is without any prior knowledge, is the prevalent workflow in reinforcement learning (RL) research. However, RL systems, when applied to large-scale settings, rarely operate tabula rasa. Such large-scale systems…
Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved…
Despite the fact that deep reinforcement learning (RL) has surpassed human-level performances in various tasks, it still has several fundamental challenges. First, most RL methods require intensive data from the exploration of the…
Deep Reinforcement Learning (RL) techniques can benefit greatly from leveraging prior experience, which can be either self-generated or acquired from other entities. Action advising is a framework that provides a flexible way to transfer…
Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To enhance search capabilities for complex tasks, most…
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images…
Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as…
Several algorithms have been proposed to sample non-uniformly the replay buffer of deep Reinforcement Learning (RL) agents to speed-up learning, but very few theoretical foundations of these sampling schemes have been provided. Among…
Agentic multimodal models have garnered significant attention for their ability to leverage external tools to tackle complex tasks. However, it is observed that such agents often meet premature interaction collapse, caused by two primary…
We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be violated. We show how to exploit the typically smooth dynamics…
Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behaviors exist widely, such as over-search (retrieving…
Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially…
While Large Language Model (LLM) agents show promise in automated trading, they still face critical limitations. Prominent multi-agent frameworks often suffer from inefficiency, produce inconsistent signals, and lack the end-to-end…
Controlling desktop applications via software remains a fundamental yet under-served problem. Existing multi-modal large language models (MLLMs) ingest screenshots and task instructions to generate keystrokes and mouse events, but they…
Recent advancements in deep reinforcement learning (RL) have demonstrated notable progress in sample efficiency, spanning both model-based and model-free paradigms. Despite the identification and mitigation of specific bottlenecks in prior…
Coagent networks for reinforcement learning (RL) [Thomas and Barto, 2011] provide a powerful and flexible framework for deriving principled learning rules for arbitrary stochastic neural networks. The coagent framework offers an alternative…