The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a perv…

COMAP introduces a novel co-evolutionary framework that simultaneously updates textual world models and agent policies through closed-loop interaction, significantly improving long-horizon decision-ma…

The paper introduces MineExplorer, a new benchmark in Minecraft, to evaluate the sustained open-world exploration capabilities of MLLM agents, finding that long-horizon coordination remains a signific…

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance acro…

The paper develops an optimistic maximum-likelihood algorithm that achieves $ ilde{O}(\sqrt{T})$ policy regret for sequential decision-making in partially observable Markov games against adaptive oppo…

TraceGraph introduces a graph-based framework to map agent decision-making across pooled trajectories, revealing hidden differences in agent behavior and improving performance by targeting known failu…

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

This paper investigates the robustness of world models in vision-based quadrotor navigation and identifies factors governing their quality.

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learni…

This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

This paper theoretically justifies the strong performance of linear recurrent neural networks as memory units in partially observable reinforcement learning by constructing specific linear filters tha…

This paper surveys the risks associated with world models, proposing a unified threat model and demonstrating adversarial attacks that show world models require rigorous safety standards comparable to…

The JAMEL framework addresses the challenge of effective exploration in open-ended environments by jointly training agent memory and exploration policies using natural, novelty-driven signals.

The paper introduces WorldCoder-Bench, a comprehensive benchmark and evaluation protocol for testing LLMs' ability to autonomously generate complex, physically grounded, and interactive 3D web worlds.