KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents

arXiv cs.AISeptember 4, 2026en

arXiv:2609.03588v1 Announce Type: new Abstract: As LLMs increasingly act through tools, they must reconcile user instructions, parametric knowledge, and dynamic environmental observations before taking actions. We introduce KC-Bench, a controlled multi-turn benchmark for measuring this capability across world-knowledge conflicts, input inconsistencies, and multi-source temporal conflicts. Its 238 tasks are manually screened from more than 1,000 generated candidates and combine a user simulator, stateful tools, deterministic environment assertions, an open-source natural-language evaluator, and human trajectory verification. Evaluation of nine models, including DeepSeek-V4-Flash, GLM-5.2, and

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• DeepSeek
• Verktyg
• Forskning
• Agenter