Related papers: Same Signal, Opposite Meaning: Direction-Informed …

Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent…

Effective training-time guidance is central to multi-agent reinforcement learning (MARL), yet remains difficult in sparse-reward settings where weak supervision limits coordination and policy improvement, and existing methods often require…

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely…

Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate human behavior remains a significant challenge. An effective simulator must expose the failure…

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Continuous-action policies trained on a single demonstrated trajectory per scene suffer from mode collapse: samples cluster around the demonstrated maneuver and the policy cannot represent semantically distinct alternatives. Under…

Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for…

Imitation learning algorithms learn viable policies by imitating an expert's behavior when reward signals are not available. Generative Adversarial Imitation Learning (GAIL) is a state-of-the-art algorithm for learning policies when the…

This paper proposes a novel inverse reinforcement learning framework using a diffusion-based adaptive lookahead planner (IRL-DAL) for autonomous vehicles. Training begins with imitation from an expert finite state machine (FSM) controller…

The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and…

As machine learning(ML) systems evolve to continual adaptation, each re-training cycle uses compute, annotation, and energy. We introduce TIMEGATE, a policy layer managing adaptation by budgeting time, labeling, training, and evaluation.…

Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. The guide achieves this by providing the agent with discrete messages in an emerged language…

Recent work in multi-agent reinforcement learning has investigated inter agent communication which is learned simultaneously with the action policy in order to improve the team reward. In this paper, we investigate independent Q-learning…

Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not…

While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and…

We study inverse mechanism learning: recovering an unknown incentive-generating mechanism from observed strategic interaction traces of self-interested learning agents. Unlike inverse game theory and multi-agent inverse reinforcement…

In cooperative multi-agent reinforcement learning (MARL), how to design a suitable reward signal to accelerate learning and stabilize convergence is a critical problem. The global reward signal assigns the same global reward to all agents…

Understanding an agent's goals from its behavior is fundamental to aligning AI systems with human intentions. Existing goal recognition methods typically rely on an optimal goal-oriented policy representation, which may differ from the…

Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision. While finer-grained credit assignment is promising for…