. . . . "R2-KG: General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphs" . . . . . . . "KG-GPT" . . "https://github.com/ekrxjwh2009/R2-KG.git"^^ . . "This method proposes a novel dual-agent system where LLMs (Operator for evidence collection, Supervisor for judgment) iteratively interact with a Knowledge Graph to perform general-purpose, reliable reasoning. It synergizes LLM's reasoning abilities with KG's knowledge by treating LLMs as agents navigating and interpreting KG evidence, addressing tasks like QA and fact verification." . "R2-KG: General-Purpose Dual-Agent Framework" . . . "https://github.com/ekrxjwh2009/R2-KG.git"^^ . . "This is a cost-effective variant of the R2-KG dual-agent framework. It uses a single LLM (Operator) for both KG exploration and answer generation, enhancing reliability through a strict self-consistency strategy across multiple trials, maintaining the synergized reasoning approach with the KG." . "R2-KG Single-Agent Version with Strict Self-Consistency" . . . "Think-on-Graph (ToG)" . . . "2026-02-26T15:36:09.967Z"^^ . . . "LLM-KG assessment for paper 10.48550/arXiv.2502.12767" . "RSA" . "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB" . "Tp3A4ujArO/3hiB3G6LocRVEOZnhluFNUEmTGnPcU32BMiKuTmgVhox5shCabje1E9/QdvHoS0w4lqtYB8P9tv41xWjLcddcFT7sfR1Lc8wjqrUXp7o2uuGWD6mA1kTmmhDFxac1ZRn85A79SqFV4ZC0b7TR6pmOVxqln2jq1hzCU0Pj+6mfJ0U/P8g10islA6ZKa8KS+l6oC24UhT+z6s4/bnUV+WjgP6gRCDUOQW2bnin3Bvp3eJeL7ckO8Cjzf50fCAFmdkx/q8G6tldO9eM8LeSxX+1yg9n9ejSfASuWB2DuS9JmwedY8imV79PS7/4aFEmGUvFV+wdygan78A==" . . .