{"slug": "nesyfs-a-neuro-symbolic-fast-slow-thinking-framework-for-llm-agent-under-partial", "title": "NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability", "summary": "Researchers propose NeSyFS, a neuro-symbolic fast-slow thinking framework for LLM agents under partial observability, using a knowledge graph for belief state representation and a twisted sequential Monte Carlo algorithm for uncertainty-aware planning. Experiments on ALFWorld, Webshop, and ScienceWorld show significant advantages over prior methods.", "body_md": "arXiv:2607.28942v1 Announce Type: new\nAbstract: Recently Large Language Models (LLMs) have been increasingly deployed as autonomous agents in applications such as self-reflection, retrieval-augmented generation, and scientific discovery. In these settings, agents must act based on limited observations rather than full environmental states, leading to partial observability. This introduces several key challenges: belief state inference, task objective misalignment, and planning under uncertainty. Prior approaches typically condition actions on full or summarized action-observation histories whose redundant and irrelevant information can mislead the decision making of LLM agent. Inspired by human cognition, we propose a novel neuro-symbolic fast-slow thinking (NeSyFS) framework for LLM agent, addressing the challenges introduced by partial observability in a unified approach. We use a knowledge graph (KG) to represent the belief state, providing triplets as context for every module of NeSyFS. The fast-thinking module performs reactive action, while slow-thinking conducts a new uncertainty-aware planning by following the high-level structure of twisted sequential Monte Carlo (TSMC) algorithm. To mitigate the misalignment of task objective, a reflection module is used to reflect fast-thinking actions, and also switches to the slow-thinking module whenever reactive actions repeatedly fail. Experiments on three representative benchmarks, i.e. ALFWorld, Webshop, and ScienceWorld, demonstrate significant advantages over previous methods.", "url": "https://wpnews.pro/news/nesyfs-a-neuro-symbolic-fast-slow-thinking-framework-for-llm-agent-under-partial", "canonical_source": "https://arxiv.org/abs/2607.28942", "published_at": "2026-08-03 04:00:00+00:00", "updated_at": "2026-08-03 04:13:51.445707+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["NeSyFS", "LLM", "ALFWorld", "Webshop", "ScienceWorld"], "alternates": {"html": "https://wpnews.pro/news/nesyfs-a-neuro-symbolic-fast-slow-thinking-framework-for-llm-agent-under-partial", "markdown": "https://wpnews.pro/news/nesyfs-a-neuro-symbolic-fast-slow-thinking-framework-for-llm-agent-under-partial.md", "text": "https://wpnews.pro/news/nesyfs-a-neuro-symbolic-fast-slow-thinking-framework-for-llm-agent-under-partial.txt", "jsonld": "https://wpnews.pro/news/nesyfs-a-neuro-symbolic-fast-slow-thinking-framework-for-llm-agent-under-partial.jsonld"}}