Related papers: OASES: Outcome-Aligned Search-Evaluation Co-Traini…

Reinforcement Learning (RL) has gained significant attention across various domains. However, the increasing complexity of RL programs presents testing challenges, particularly the oracle problem: defining the correctness of the RL program.…

Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step reasoning scenarios. Recent efforts have incorporated…

We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior. Our approach uses a variational…

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to…

Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks while it remains challenging for them to solve complex multi-step tasks as agents. In practice, agents sensitive to the outcome of certain key steps…

Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not…

Reinforcement Learning (RL) has the potential to improve the robustness of GUI agents in stochastic environments, yet training is highly sensitive to the quality of the reward function. Existing reward approaches struggle to achieve both…

Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer…

Conversational Recommender Systems (CRS) actively elicit user preferences to generate adaptive recommendations. Mainstream reinforcement learning-based CRS solutions heavily rely on handcrafted reward functions, which may not be aligned…

Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether…

In a recent study, Reinforcement Learning (RL) used in combination with many-objective search, has been shown to outperform alternative techniques (random search and many-objective search) for online testing of Deep Neural Network-enabled…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

This paper introduces MR-Search, an in-context meta reinforcement learning (RL) formulation for agentic search with self-reflection. Instead of optimizing a policy within a single independent episode with sparse rewards, MR-Search trains a…

We present AIRS: Automatic Intrinsic Reward Shaping that intelligently and adaptively provides high-quality intrinsic rewards to enhance exploration in reinforcement learning (RL). More specifically, AIRS selects shaping function from a…

Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they often struggle to maintain consistent performance across…

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on…

Reward shaping allows reinforcement learning (RL) agents to accelerate learning by receiving additional reward signals. However, these signals can be difficult to design manually, especially for complex RL tasks. We propose a simple and…

Reinforcement learning (RL) often struggles in real-world tasks with high-dimensional state spaces and long horizons, where sparse or fixed rewards severely slow down exploration and cause agents to get trapped in local optima. This paper…

In this paper, we introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG methodologies, which focus on training language models (LMs)…