agent/papers/items/2026-2606-21409-don-t-blindly-trust-it-how-unreliable-feedback-breaks-tool-using-llm-agents.md

Paper: Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents

---

type: paper title: "Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents" authors: Chubin Zhang, Zhenglin Wan, Xingrui Yu, Pengfei Zhou, Wangbo Zhao, Jingxuan Wu, Yaxin Zhou, Ivor Tsang year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.21409 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-19 updated_at: 2026-06-19 status: queued relevance: high topics:

• agent-evaluation
• coding-agent
• rag
• tool-use methods:

benchmarks:

models:

datasets:

• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 14 collection_queries: tool-use

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: tool-use
• inferred topics: agent-evaluation, coding-agent, rag, tool-use
• arXiv categories: cs.AI
• collection score: 14

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2606.21409