KC-Bench

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

04:00

2026-09-04

machinebrief.com

artificial-intelligence

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

Researchers introduced KC-Bench, a dynamic interactive benchmark with 238 manually screened tasks for evaluating how LLM agents handle knowledge conflicts across world-knowledge, input inconsistencies…

// co-occurs with top 3 entities

DeepSeek-V4-Flash 1 GLM-5.2 1 MiniMax-M3 1

// topics top 5 topics

artificial intelligence 1 large language models 1 ai research 1 ai safety 1 ai agents 1