arXiv AI
SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 2
LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
The article surveys LLM-based agentic reasoning frameworks, presenting a unified formal language that categorizes them into single-agent, tool-based, and multi-agent methods. It reviews application scenarios in scientific discovery, healthcare, software engineering, society, economics, and general-purpose tasks, and compares the distinct features and evaluation strategies of each category. The survey highlights the rapid development of complex agentic systems in real-world contexts.
arXiv Computation and Language
Sep 23
Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
arXiv:2604.13706v2 Announce Type: replace Abstract: Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reas...
arXiv AI
Sep 1
RACER: Reinforced Agent Collaboration for Explainable Reasoning on Knowledge Graphs
arXiv:2608.29263v1 Announce Type: new Abstract: Large Language Models (LLMs) often suffer from hallucination and struggle with complex reasoning tasks requiring multi-hop domain knowledge. While inte...
arXiv AI
Oct 21
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
arXiv:2610.28578v1 Announce Type: new Abstract: In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adapti...
arXiv AI
Aug 14
ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification
arXiv:2608. 12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains highly challenging.
arXiv AI
1d ago
MIND: AI Co-Scientist for Material Research
MIND is an LLM-driven framework that automates hypothesis validation in materials research by structuring the discovery process into hypothesis refinement, experimentation, and debate-based validation within a multi-agent pipeline. It incorporates Machine Learning Interatomic Potentials, notably SevenNet-Omni, to perform scalable in‑silico experiments and offers a web-based interface for automated hypothesis testing. The modular design allows integration of additional experimental modules, making the framework adaptable to broader scientific workflows.