Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a promising approach for enhancing performance. Recent advancements, particularly in web environments, face a critical limitation: their performance will reach a stagnation point during autonomous learning cycles, hindering further improvement. We argue that this stems from limited exploration of the web environment and insufficient exploitation of pre-trained web knowledge in LLMs. To improve the performance of self-improvement, we propose a novel framework that introduces a co-evolving World Model LLM. This world model predicts the next observation based on the current observation and action within the web environment. Leveraging LLMs' pretrained knowledge of abundant web content, the World Model serves dual roles: (1) as a virtual web server generating self-instructed training data to continuously refine the agent's policy, and (2) as an imagination engine during inference, enabling look-ahead simulation to guide action selection for the agent LLM. Experiments in real-world web environments (Mind2Web-Live, WebVoyager, and GAIA-web) show a 10% performance gain over existing self-evolving agents, demonstrating the efficacy and generalizability of our approach, without using any distillation from more powerful close-sourced models. Our work establishes the necessity of integrating world models into autonomous agent frameworks to unlock sustained adaptability. Code is available at https://github.com/Tencent/SelfEvolvingAgent

Embodied navigation (EN) advances traditional navigation by enabling robots to perform complex egocentric tasks through sensing, social, and motion intelligence. In contrast to classic methodologies that rely on explicit localization and pre-defined maps, EN leverages egocentric perception and human-like interaction strategies. This survey introduces a comprehensive EN formulation structured into five stages: Transition, Observation, Fusion, Reward-policy construction, and Action (TOFRA). The TOFRA framework serves to synthesize the current state of the art, provide a critical review of relevant platforms and evaluation metrics, and identify critical open research challenges. A list of studies is available at https://github.com/Franky-X/Awesome-Embodied-Navigation.

Bayesian optimization is a methodology to optimize black-box functions.

Precise and comprehensive situational awareness is a critical capability of modern autonomous systems. Deep neural networks that perceive task-critical details from rich sensory signals have become ubiquitous; however, their black-box behavior and sensitivity to environmental uncertainty and distribution shifts make them challenging to verify formally. Abstraction-based verification techniques for vision-based autonomy produce safety guarantees contingent on rigid assumptions, such as bounded errors or known unique distributions. Such overly restrictive and inflexible assumptions limit the validity of the guarantees, especially in diverse and uncertain test-time environments. We propose a methodology that unifies the verification models of perception with their offline validation. Our methodology leverages interval MDPs and provides a flexible end-to-end guarantee that adapts directly to the out-of-distribution test-time conditions. We evaluate our methodology on a synthetic perception Markov chain with well-defined state estimation distributions and a mountain car benchmark. Our findings reveal that we can guarantee tight yet rigorous bounds on overall system safety.

Modal testing plays a critical role in structural analysis by providing essential insights into dynamic behaviour across a wide range of engineering industries. In practice, designing an effective modal test campaign involves complex experimental planning, comprising a series of interdependent decisions that significantly influence the final test outcome. Traditional approaches to test design are typically static-focusing only on global tests without accounting for evolving test campaign parameters or the impact of such changes on previously established decisions, such as sensor configurations, which have been found to significantly influence test outcomes. These rigid methodologies often compromise test accuracy and adaptability. To address these limitations, this study introduces an agent-based decision support framework for adaptive sensor placement across dynamically changing modal test environments. The framework formulates the problem using an underspecified partially observable Markov decision process, enabling the training of a generalist reinforcement learning agent through a dual-curriculum learning strategy. A detailed case study on a steel cantilever structure demonstrates the efficacy of the proposed method in optimising sensor locations across frequency segments, validating its robustness and real-world applicability in experimental settings.

Partially observable Markov decision processes (POMDPs) model specific environments in sequential decision-making under uncertainty. Critically, optimal policies for POMDPs may not be robust against perturbations in the environment. Hidden-model POMDPs (HM-POMDPs) capture sets of different environment models, that is, POMDPs with a shared action and observation space. The intuition is that the true model is hidden among a set of potential models, and it is unknown which model will be the environment at execution time. A policy is robust for a given HM-POMDP if it achieves sufficient performance for each of its POMDPs. We compute such robust policies by combining two orthogonal techniques: (1) a deductive formal verification technique that supports tractable robust policy evaluation by computing a worst-case POMDP within the HM-POMDP, and (2) subgradient ascent to optimize the candidate policy for a worst-case POMDP. The empirical evaluation shows that, compared to various baselines, our approach (1) produces policies that are more robust and generalize better to unseen POMDPs, and (2) scales to HM-POMDPs that consist of over a hundred thousand environments.

Multi-robot navigation and path planning in continuous state and action spaces with uncertain environments remains an open challenge. Deep Reinforcement Learning (RL) is one of the most popular paradigms for solving this task, but its real-world application has been limited due to sample inefficiency and long training periods. Moreover, the existing works using RL for multi-robot navigation lack formal guarantees while designing the environment. In this paper, we introduce an efficient and highly customizable environment for continuous-control multi-robot navigation, where the robots must visit a set of regions of interest (ROIs) by following the shortest paths. The task is formally modeled as a Markov Decision Process (MDP). We describe the multi-robot navigation task as an optimization problem and relate it to finding an optimal policy for the MDP. We crafted several variations of the environment and measured the performance using both gradient and non-gradient based RL methods: A2C, PPO, TRPO, TQC, CrossQ and ARS. To show real-world applicability, we deployed our environment to a 3-D agricultural field with uncertainties using the CoppeliaSim robot simulator and measured the robustness by running inference on the learned models. We believe our work will guide the researchers on how to develop MDP-based environments that are applicable to real-world systems and solve them using the existing state-of-the-art RL methods with limited resources and within reasonable time periods.

However, strikingly, this measure is independent of rewards and is a function of only the transitions.