arXiv AI

Exploration and Exploitation Errors Are Measurable for Language Model Agents

The paper introduces a policy‑agnostic metric that distinguishes exploration and exploitation errors in language model agents operating on partially observable 2D grid maps with unknown symbolic task DAGs. By attributing errors to either exploration or exploitation based on the current state’s potential for productive action, the authors evaluate 35 LM agents and find that both types of errors strongly correlate with task success (R² ≈ 0.88). The metric also uncovers differing exploration/exploitation strategies among agents with similar success rates and demonstrates its applicability to a Minecraft‑style video game.

arXiv Computation and Language

Aug 28

MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft

MineExplorer is a benchmark designed to assess the open‑world exploration abilities of multimodal large language models (MLLMs) in Minecraft. It filters out tasks that rely heavily on Minecraft‑specific knowledge, organizes tasks into ReAct‑style capabilities, and composes atomic tasks into implicit multi‑hop challenges. A multi‑agent synthesis workflow creates reliable task graphs, sandbox scenes, and rule‑based milestone evaluators, and human evaluation confirms its superiority over a single‑agent baseline. Experiments show that while advanced MLLMs can handle many single‑hop tasks, they struggle with longer trajectories that require coordinating hidden prerequisites, and larger models or different thinking modes do not consistently improve performance.

By Tianjie Ju, Yueqing Sun, Zheng Wu, Wei Zhang, Yaqi Huo, Xi Su, Qi Gu, Xunliang Cai, Gongshen Liu, Zhuosheng Zhang

llms agents robotics multimodal benchmarks

arXiv AI

Jun 30

SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon CivRealm Strategy Planning

arXiv:2606. 29932v1 Announce Type: new Abstract: Long-horizon strategic planning in complex strategy games demands concurrent reasoning across multiple decision domains under imperfect information and sparse reward.

By Tianyu Jin, Shuo Chen, Yida Wang, Liuyu Xiang, Yingzhuo Liu, Zhiyao Jiang, Yexin Li, Zhaofeng He

llms agents benchmarks

arXiv AI

Jul 16

OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3

arXiv:2607. 01531v2 Announce Type: replace Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks.

By David Courtis, Wenhao Li, Scott Sanner

llms agents benchmarks

arXiv AI

Jun 9

Language-based Trial and Error Falls Behind in the Era of Experience

arXiv:2601. 21754v3 Announce Type: replace Abstract: While Large Language Models (LLMs) excel in language-based agentic tasks, their applicability to unseen, nonlinguistic environments (e.

By Haoyu Wang, Guozheng Ma, Shugang Cui, Yilun Kong, Haotian Luo, Li Shen, Mengya Gao, Yichao Wu, Xiaogang Wang, Dacheng Tao

llms agents reinforcement-learning fine-tuning

arXiv AI

Jul 13

Prompt-Driven Exploration

arXiv:2607. 08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers.

By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong

llms reinforcement-learning robotics multimodal

arXiv AI

Jul 16

Experience Memory Graph: One-Shot Error Correction for Agents

arXiv:2607. 13884v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations.

By Wenjun Wang, Yuchen Fang, Fengrui Liu, Zibo Liang, Kai Zheng

llms agents benchmarks

arXiv AI

Jul 3

OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration

arXiv:2607. 01531v1 Announce Type: new Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks.

By David Courtis, Wenhao Li, Scott Sanner

llms agents benchmarks

arXiv AI

Sep 21

Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning

arXiv:2607.08837v4 Announce Type: replace-cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject...

By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong

llms reinforcement-learning robotics multimodal

arXiv AI

Jul 17

SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon Strategy Game Planning

arXiv:2606. 29932v3 Announce Type: replace Abstract: Long-horizon strategic planning in complex strategy games requires coordinating tightly coupled decision domains, including technology, economy, diplomacy, and military, across hundreds of turns under imperfect information.

By Tianyu Jin, Shuo Chen, Yida Wang, Liuyu Xiang, Yingzhuo Liu, Zhiyao Jiang, Yexin Li, Peipei Li, Zhaofeng He

llms agents benchmarks

arXiv AI

Jun 30

Demonstration-Free Robotic Control via LLM Agents

arXiv:2601. 20334v2 Announce Type: replace-cross Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task-specific demonstrations and fine-tuning, and often generalize poorly under domain shift.

By Brian Y. Tsui, Alan Y. Fang, Tiffany J. Hwu

llms agents robotics fine-tuning multimodal benchmarks

arXiv AI

Jul 2

AGI Maze as a Benchmark Framework for World-Modeling Agents

arXiv:2607. 00627v1 Announce Type: new Abstract: Large language models (LLMs) are powerful pattern-completion systems, but their default operating mode - predicting the next token from a static context - does not reliably produce persistent, manipulable representations of an external world.

By Alexey Potapov

llms agents benchmarks

arXiv AI

Oct 21

Policy Search in Code Space for Multi-Agent Pathfinding

arXiv:2610.25946v2 Announce Type: replace-cross Abstract: Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific re...

By Matthias Eder, Pantelis Emmanouil, Vivek Farias, Fabian Fischer, Adam Jozefiak, Tianyi Peng, Thomas Ulz, Raphael Watschinger, Fangyu Wu, Andrew Zheng

agents reinforcement-learning robotics efficiency benchmarks safety

Related stories