method · first seen 23 Oct 2026
execution-grounded evaluation
Benchmarking approach that verifies agent outcomes by checking the actual resulting state of executed actions.
Mentions per week
PapersCodeDiscussion
Earliest sources
- CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise EnvironmentsPapers · 23 Oct 2026 · Monojit Banerjee, Zhujun Lan, Defu Cao
- TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM AgentsPapers · 30 Oct 2026 · Xiangyu Kong, Ruirui Yang, Xia Hou
Latest sources
- TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM AgentsPapers · 30 Oct 2026 · Xiangyu Kong, Ruirui Yang, Xia Hou
- CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise EnvironmentsPapers · 23 Oct 2026 · Monojit Banerjee, Zhujun Lan, Defu Cao