CORTEXA
← Browse
arxivcs.AI2026-07-06

FORGE: Research-Trajectory Hijacking Attacks on Deep Research Agents

Yue Pan, Ziheng Zhang, Junxiang Lei, Changhao Jia, Qingyi Si, Hongcheng Guo

Deep research agents decompose open-ended queries into subtasks, retrieve web evidence over multiple rounds, and synthesize long-form reports. This workflow creates a planning-layer poisoning surface: adversarial documents that enter the retrieval pool can steer follow-up questions and turn a local injection into report-level contamination. We present FORGE (Fabricated Orchestrated Reasoning chain for aGent Exploitation), a two-level attack that combines intra-document reasoning fabrication with inter-document chain coordination to hijack subtask planning. We further introduce the PRISM metric, which weights infected report claims by cognitive type, and Root Query Anchoring, a lightweight defense that ties recursive follow-up generation to the root query. Across 25 queries, Network FORGE reaches 26.4% PRISM with five injected documents and exhibits depth migration, in which recursive synthesis shifts poisoned content from overt framing into factual premises. On the 10-query defense subset, RQA (Root Query Anchoring) reduces PRISM from 38.5% to 18.3%.

View free PDFSource page

Related papers

arxivcs.AI2026-07-23

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Shuqi Lu, Chaofan Li, Kun Luo, Zhang Zhang, Hui Wang, Hongwang Xiao, et al.

Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed into tractable constraint-wise checks. This discovery--verification asymmetry suggests that a researc…

View free PDFSource page
arxivcs.AIcs.CLcs.LG2026-07-20

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

Zhaokai Wang, Tianlin Gui, Jiayuan Rao, Shangzhe Di, Yihong Tang, Dingli Liang

Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents. The 20…

View free PDFSource page
arxivcs.CRcs.AI2026-07-06

Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses

Neeraj Karamchandani, Piyush Nagasubramaniam, Sencun Zhu, Dinghao Wu

Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this has improved the agent's functionality and continuity across tasks, it has also introduced a new attac…

View free PDFSource page
arxivcs.AI2026-06-30

Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents

Keyu Zhao, Lingyan Kong, Fengli Xu, Yong Li

Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. However, existing approaches predominantly rely on pre-defined agentic workflows. This constraint severely limits the flexibility r…

View free PDFSource page
arxivcs.AIcs.HC2026-06-29

DEEPMED Search: An Open-Source Agentic Platform for Medical Deep Research with Introspective Verification

Maolin Liu, Fanyu Xu, Ruoqing Xu, Jiahang Zhang, Hao Wang, Rui Wang

Navigating the deluge of heterogeneous medical data, from academic literature (PubMed) to clinical guidelines (Web) and private knowledge bases, remains a critical bottleneck for evidence-based medicine. While commercial black-box tools lack transparency, standard open-source RAG…

View free PDFSource page