paper-with-me

홈 › Papers

State and Memory is All You Need for Robust and Reliable AI Agents

2025-06-30 · Matthew Muhoberac, Atharva Parikh, Nirvi Vakharia, Saniya Virani, Aco Radujevic, Savannah Wood, Meghav Verma, Dimitri Metaxotos, Jeyaraman Soundararajan, Thierry Masquelin, Alexander G. Godfrey, Sean Gardner, Dobrila Rudnicki, Sam Michael, Gaurav Chopra

Large language models (LLMs) have enabled powerful advances in natural language understanding and generation. Yet their application to complex, real-world scientific workflows remain limited by challenges in memory, planning, and tool integration. Here, we introduce SciBORG (Scientific Bespoke Artificial Intelligence Agents Optimized for Research Goals), a modular agentic framework that allows LLM-based agents to autonomously plan, reason, and achieve robust and reliable domain-specific task execution. Agents are constructed dynamically from source code documentation and augmented with finite-state automata (FSA) memory, enabling persistent state tracking and context-aware decision-making. This approach eliminates the need for manual prompt engineering and allows for robust, scalable deployment across diverse applications via maintaining context across extended workflows and to recover from tool or execution failures. We validate SciBORG through integration with both physical and virtual hardware, such as microwave synthesizers for executing user-specified reactions, with context-aware decision making and demonstrate its use in autonomous multi-step bioassay retrieval from the PubChem database utilizing multi-step planning, reasoning, agent-to-agent communication and coordination for execution of exploratory tasks. Systematic benchmarking shows that SciBORG agents achieve reliable execution, adaptive planning, and interpretable state transitions. Our results show that memory and state awareness are critical enablers of agentic planning and reliability, offering a generalizable foundation for deploying AI agents in complex environments.

📄 PDF Abstract BibTeX arXiv:2507.00081

Code (0)

등록된 구현이 없습니다.

Tasks

AllBenchmarkingDecision MakingNatural Language UnderstandingPrompt Engineering

Similar Papers 제목 키워드 기반

From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents

2026-06-30 · Yashar Talebirad, Eden Redman, Ali Parsaee, Osmar R. Zaiane arxiv

How do two agents invent a shared language from scratch? In a Lewis signaling game, a sender and receiver must coordinate on a code using only their interaction history. We study five memory architectures across varying …

What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States

2026-06-30 · Chen Liu, Ling Chen, Hanzhang Zhou, Xu Zhang 외 arxiv

Mobile GUI agents increasingly face long-horizon tasks that require reading, updating, and reusing task-relevant data across pages and applications. Existing methods treat memory largely as passive storage, where past ob…

Reinforcement Learning

AI Agents Need Memory Control Over More Context

2026-01-15 · Fouad Bousetouane arxiv

AI agents are increasingly used in long, multi-turn workflows in both research and enterprise settings. As interactions grow, agent behavior often degrades due to loss of constraint focus, error accumulation, and memory-…

MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents

2026-08-31 · Vernon Toh, Navonil Majumder, Zhengyuan Liu, Nancy F. Chen 외 hf

AI agents in partially observable environments need to coordinate active sensing with working memory to maintain an evolving perceptual state. However, existing benchmarks struggle to isolate this perceptual-state constr…

VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents

2026-03-25 · Yuhao Chen, Yi Xu, Xinyun Ding, Xiang Fang 외 arxiv

With the growing demand for intelligent in-vehicle experiences, vehicle-based agents are evolving from simple assistants to long-term companions. This evolution requires agents to continuously model multi-user preference…