New research on AI and security, selected for relevance to language models, AI agents and cybersecurity. Summaries are the authors’ or publisher’s own words, linked to the original.
Peer-reviewed
Supervising the search process produces reliable and generalizable information-seeking agents
New preprints (not yet peer-reviewed)
PrivacyEvalClaw: A Tool-Augmented Deliberative Agent for Auditing Privacy Leakage in LLM Jailbreak Responses
Reliable evaluation is a critical bottleneck in privacy red-teaming of large language models (LLMs): determining whether a jailbreak response actually reveals personal information can be difficult when disclosures are indirect, contextual, partial, or obfuscated. Existing evaluation approaches increasingly rely on guard models and LLM-as-Judges, yet these evaluators may interpret the same response differently.
LM-DSB: A Lightweight Multi-agent System for Automated Daily Safety Bulletin Generation in Construction
Construction safety management still struggles to produce daily safety bulletins (DSBs), structured daily communications that identify site-specific hazards, convey safety protocols, and set preventive measures for workers. Manual DSB creation takes 2-3 hours daily and yields inconsistent quality, with 25% of crews never conducting pretask planning (Olson et al., 2016), diverting safety personnel from field supervision.
RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG
Web-based applications increasingly rely on understanding long multimodal documents, where answering questions often requires combining information across pages, tables, and figures. Agentic retrieval-augmented generation addresses these tasks through iterative retrieval and reasoning.
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete multi-step tasks. This execution model exposes agents to indirect prompt injection (IPI) attacks, in which attacker-controlled instructions embedded in external artifacts enter the agent state and later influence tool use.
RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models
Modern Network Intrusion Detection Systems (NIDS) generate vast volumes of low-level alerts that remain semantically fragmented, requiring labor-intensive manual correlation with high-level adversarial behaviors. Existing automation, namely rule-based systems and machine learning classifiers, has critical limitations: rule-based approaches fail to adapt to novel attack variations, while machine learning methods lack contextual awareness and treat tactic-technique (TT) mapping as syntactic matching rather than reasoning.
Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
Large language model (LLM) agents are increasingly deployed in scientific research, where reliability is critical and the underlying knowledge is densely interconnected. In such settings, hallucinations are particularly damaging: a single erroneous claim on a foundational concept can propagate through multi-step reasoning and corrupt entire trajectories.
OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning
Large language models (LLMs) perform well across many real-world tasks but remain prone to hallucination, limiting their reliability in domains such as biomedicine and healthcare, where answers must be grounded in established knowledge. Retrieval-augmented generation (RAG) mitigates this problem by incorporating external information, but often overlooks logical relationships and relies heavily on the LLM's own reasoning, which can compromise answer faithfulness.
MAREval: A Multi-Agent Framework for Evaluating Natural Language Recommendation Explanations
Evaluating natural language explanations in recommender systems is essential for fostering user trust, transparency, and engagement. However, existing evaluation approaches like human evaluations, while accurate, are resource-intensive and impractical at the scale required by modern recommendation platforms.