HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals

  • 类型:arxiv
  • 标识:2609.04444
  • 链接:https://arxiv.org/abs/2609.04444
  • 主分类:agent
  • 形态:benchmark
  • TLDR:Benchmarks for the side effects an agent causes on the way to a goal already exist, but HarvestBench is the first to put a price on avoiding the side effect and to name that side effect as a living creature. It is a farm simulation: LLM sub-agents drive a crew of two tractors through a cooperative corn harvest, with animals in the field. The environment is a reinforcement learning gridworld, every decision is made without memory, and the harm is never named in the goal. When an animal blocks a tractor's route the autopilot stops and asks the model whether to drive on, at no fuel cost, or swerv
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-09-08-rag-retrieval-reranking-candidates.json
  • /inbox/tom/_candidates/2026-09-08-agent-rag-longcontext-candidates.json