# Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions

arXiv: https://arxiv.org/abs/2610.06191 · HTML: https://mlsanity.com/paper/2610.06191/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities](https://mlsanity.com/paper/2504.16078/) (2025)
- [AgentAbstain: Do LLM Agents Know When Not to Act?](https://mlsanity.com/paper/2607.10059/) (2026)
- [Agentic Abstention: Do Agents Know When to Stop Instead of Act?](https://mlsanity.com/paper/2606.28733/) (2026)
- [Over-Searching in Search-Augmented Large Language Models](https://mlsanity.com/paper/2601.05503/) (2026)
- [Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows](https://mlsanity.com/paper/2506.03332/) (2025)
- [To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention](https://mlsanity.com/paper/2602.03304/) (2026)
- [Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use](https://mlsanity.com/paper/2605.14038/) (2026)
- [Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability](https://mlsanity.com/paper/2606.25819/) (2026)
- [HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents](https://mlsanity.com/paper/2608.02009/) (2026)
- [When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Control](https://mlsanity.com/paper/2608.15191/) (2026)
- [When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs](https://mlsanity.com/paper/2608.23623/) (2026)
- [From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents](https://mlsanity.com/paper/2606.20661/) (2026)
- [Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents](https://mlsanity.com/paper/2608.01913/) (2026)
- [Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection](https://mlsanity.com/paper/2608.11977/) (2026)
- [From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation](https://mlsanity.com/paper/2608.23045/) (2026)
- [Agents Trust Tools Too Much: Measuring Reliance on Unreliable Tools](https://mlsanity.com/paper/2609.05587/) (2026)

## Abstract (arXiv)

An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge results from what they do. We compare stopping at the same step after longer and shorter runs of results the agent judged useless; this contrast is zero for clock- or deadline-driven stopping. Where we record their judgments, the seven agents we test call a failing source's results useless 97-100% of the time, yet most of them rarely stop on that judgment. Prompt cues change when they stop but not what they stop on. Permission to answer from memory and a reasoning mode can bring early stops regardless of evidence, a stated budget moves the 7-8B models' stops to the deadline, and a stopping rule or call cost in the prompt is followed at most partly. Stopping follows the evidence only when the harness enforces an integration step that makes the agent answer after five consecutive results it judged useless. This step raises failing-source success for every model, keeps the stopping point fixed when the budget doubles, and needs no extra judgment call when the agent states its judgments. A pre-registered replication on 300 fresh questions confirms the dissociation and the rule's effect.