arXiv AI

Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control

Mimir is a physics‑grounded large language model agent designed for long‑horizon irrigation control. It operates on two timescales: a fast scale that uses a structured physical interface and deterministic simulator to validate and refine LLM proposals before execution, and a slow scale that consolidates recurrent failure patterns into persistent contextual principles. Across multiple sites, crops, and years, Mimir achieves the lowest aggregate control cost and reduces irrigation usage by about 51% compared to historical schedules, while ablation studies confirm the importance of forward simulation, verified revision, and persistent context.

arXiv AI

Sep 15

Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks?

The paper investigates whether large language model (LLM) agents can autonomously manage long‑horizon physical tasks without human intervention. It proposes a multi‑agent framework that combines planning, tool calling, observation, and verification, and tests it on agricultural tasks under varying weather conditions. Results show that zero‑shot LLM agents match reinforcement learning (RL) agents in the same environment and outperform RL when the environment shifts, suggesting a viable path for self‑adaptive physical AI.

By Varun Kaushik, Yayun Tan, Xiaofan Yu

llms agents reinforcement-learning

arXiv Machine Learning

Jul 30

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents

arXiv:2607. 26865v1 Announce Type: cross Abstract: LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, and control of physical AI systems.

By Amirmohammad Farzaneh, Osvaldo Simeone

llms agents nlp robotics benchmarks

arXiv AI

Sep 23

Human-guided physics-constrained AI agents construct an auditable model of soil-plug evolution

arXiv:2609.23360v1 Announce Type: cross Abstract: Engineering predictions require physical mechanisms to be translated consistently into equations, discretization, code, and validation, yet errors ca...

By Jie Shi, Yimin Lu, Zhongkun Ouyang

agents

arXiv AI

Jun 15

SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model

arXiv:2606. 14574v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments.

By Xiaoxin Lu, Ranran Haoran Zhang, Rui Zhang

llms agents benchmarks

arXiv AI

Jul 8

Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents

arXiv:2510. 19771v4 Announce Type: replace Abstract: LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve them autonomously.

By Gil Pasternak, Dheeraj Rajagopal, Julia White, Dhruv Atreja, Matthew Thomas, George Hurn-Maloney, Ash Lewis

llms agents benchmarks

arXiv AI

Aug 11

Reflex First, Reflect Later: Latency-Aware Embodied LLM Agents for Dynamic Response

arXiv:2506. 07223v2 Announce Type: replace Abstract: Large language models (LLMs) have substantially improved the planning capabilities of embodied agents, enabling their deployment in dynamic and safety-critical environments.

By Yangqing Zheng, Shunqi Mao, Dingxin Zhang, Weidong Cai

llms agents reinforcement-learning robotics efficiency safety

arXiv AI

Sep 24

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

The paper introduces the Agent-Editing World Model (AEWM), a new approach that models how reasoning and actions influence future task progress instead of simulating tool responses. AEWM includes an Action Judge that classifies decisions as Critical, Exploratory, or Noisy, and a State Revision mechanism that edits noisy reasoning–action continuations from the same observed history. The integrated system, EditAct, directly updates the underlying state during real execution, leading to significant performance gains across multiple benchmarks and agent backbones.

By Shuang Sun, Guoxin Chen, Fanzhe Meng, Jia Deng, Huatong Song, Jinhao Jiang, Wayne Xin Zhao, Hongteng Xu, Ji-Rong Wen

llms agents fine-tuning benchmarks

arXiv AI

Jun 6

VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents

arXiv:2606. 05395v1 Announce Type: cross Abstract: Reusable robot skills are becoming the basic units through which embodied agents turn open-ended instructions into long-horizon physical behavior.

By Yunhao Yang, Neel P. Bhatt, Kevin Wang, Samuel Tetteh, Zhangyang Wang, Ufuk Topcu

llms agents robotics fine-tuning safety

arXiv AI

3d ago

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

arXiv:2609.40306v1 Announce Type: cross Abstract: Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and phys...

By Haoyuan Deng, Jiebin Liu, Tengxiao Zhang, Langning Yan, Hongye Cao, Ziwei Wang

agents robotics

arXiv AI

Jul 13

Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls

arXiv:2607. 09076v1 Announce Type: new Abstract: Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, exposing the limitations of traditional rule-based monitoring in industrial IoT environments.

By Saroj Gopali, Bipin Chhetri, Deepika Giri, Sima Siami-Namini, Akbar Siami Namin

llms agents diffusion safety

arXiv AI

Jul 14

AgentAbstain: Do LLM Agents Know When Not to Act?

arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.

By Xun Liu, Yi Evie Zhang, Vira Kasprova, Parisa Rabbani, Pardis Sadat Zahraei, Tianyu Zhang, Ali Ebrahimpour-Boroojeny, Varun Chandrasekaran

llms agents benchmarks

arXiv AI

Aug 10

Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution

arXiv:2608. 06811v1 Announce Type: cross Abstract: Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation, and verification.

By Jiahao Zhang, Yifan Zhang, Yu Huang

llms agents benchmarks

Related stories