研究人员发布了KC-Bench基准，专门测试AI智能体如何处理知识冲突，九个主流模型测试结果都不理想。
KC-Bench是一个多轮交互基准，包含238个手动筛选的任务，用于评估大语言模型智能体处理知识冲突的能力。该基准测试了DeepSeek-V4-Flash、GLM-5.2和MiniMax-M3等九个模型，结果显示没有模型能在所有场景下可靠处理事实纠正、身份一致性检查和时间冲突解决。在模拟环境中，未解决的知识冲突可能导致工具调用错误或合成受保护数据流动。
KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents
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 MiniMax-M3, shows substantial cross-domain variation: no model handles factual correction, identity consistency checking, and temporal conflict resolution reliably across all settings. In the simulated environments, missed conflicts can propagate to tool calls or synthetic protected-data flows. KC-Bench isolates this model-level behavior rather than ranking complete agent frameworks, and provides a reproducible diagnostic for developing conflict-aware reasoning and execution safeguards.