Same Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents Accuracy

Paper recorded by Signals 4 on 2026-10-19 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-19 on arXiv · recorded by Signals 4 on 2026-10-20

Category: cs.AI · 人工智能 · first seen 2026-10-20

Abstract

LLM agents that compute the right answer can still answer wrongly. Agent harnesses increasingly keep long tool outputs out of the context window, saving them to files that the agent searches or reads on demand. We ask where this costs accuracy with a real scientific tool: PHREEQC, a widely used geochemistry simulator from the USGS, whose reports reach 846.8k characters and whose determinism lets e

Read on arXiv →