arXiv Computation and Language
Lazy Grounding: Attacking Search Agents with Factual Evidence
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Jul 21
DRNOISE: Benchmarking Deep Research Agents in Misleading Evidence Environments
arXiv:2607. 17291v1 Announce Type: new Abstract: Deep research agents increasingly operate over the open web, where relevant records coexist with redundant summaries, outdated reports, and misleading documents.
arXiv AI
Aug 12
Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory
arXiv:2608. 10676v1 Announce Type: new Abstract: Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments.
arXiv AI
Aug 6
Breadcrumbing Search Agents
arXiv:2608. 04565v1 Announce Type: cross Abstract: LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk: web content retrieved during execution is untrusted, exposing agents to prompt injection and goal hijacking.
arXiv AI
Jul 3
GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation
arXiv:2606. 22737v2 Announce Type: replace Abstract: Before letting an agent operate over real context, can you prove it used the right evidence?
arXiv AI
Oct 31
Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories
The paper investigates how large language model (LLM) search agents can be manipulated through repeated, coordinated search-result injections, a threat that extends beyond single-page poisoning. It introduces Authority‑Chain Hijack (ACH), a strategy that chains manipulated evidence across multiple sources, achieving high attack success rates on the SafeSearch benchmark. The authors also present Trace‑Guided Strategy Evolution (TGSE), an automated method that refines attacker strategies using execution traces, further improving success rates.
Hugging Face Trending Papers
Aug 11
Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory
Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments. However, providing complete execution trajectories to the LLM causes unbounded context growth and introduces noise.