Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions
Seven tool-using agents almost always call failed retrieval useless but rarely stop unless the harness forces it.
1 stories, newest first · one card per story
Seven tool-using agents almost always call failed retrieval useless but rarely stop unless the harness forces it.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views