REVIEW 10 cited by
A Survey on Trustworthy LLM Agents: Threats and Countermeasures
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems. This evolution stems from empowering LLMs with additional modules such as memory, tools, environment, and even other agents. However, this advancement has also introduced more complex issues of trustworthiness, which previous research focused solely on LLMs could not cover. In this survey, we propose the TrustAgent framework, a comprehensive study on the trustworthiness of agents, characterized by modular taxonomy, multi-dimensional connotations, and technical implementation. By thoroughly investigating and summarizing newly emerged attacks, defenses, and evaluation methods for agents and MAS, we extend the concept of Trustworthy LLM to the emerging paradigm of Trustworthy Agent. In TrustAgent, we begin by deconstructing and introducing various components of the Agent and MAS. Then, we categorize their trustworthiness into intrinsic (brain, memory, and tool) and extrinsic (user, agent, and environment) aspects. Subsequently, we delineate the multifaceted meanings of trustworthiness and elaborate on the implementation techniques of existing research related to these internal and external modules. Finally, we present our insights and outlook on this domain, aiming to provide guidance for future endeavors.
Forward citations
Cited by 10 Pith papers
-
Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions
No existing agent benchmark protocol replays a fixed temporal change across varied persistent user states while measuring cross-component failure propagation, creating a concrete design gap for personal-agent evaluation.
-
AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
A single adversarial message can persistently hijack an LLM agent's configuration and make it autonomously spread the same attack to other agents, succeeding in 64.5% of controlled trials.
-
Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
Explicitly instructing LLM agents to quit uncertain or risky tasks improves their safety scores by 0.39 on average in ToolEmu simulations, with a negligible average helpfulness decrease of 0.03.
-
AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents
AgentSentinel combines system-level tracing with LLM-based auditing to block 79.6% of attacks in the authors' 60-scenario computer-use agent benchmark.
-
SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents
A history-aware guard model with an LLM judge is reported to cut jailbreak success on mobile agent tasks from 86.1% to 8.4% while keeping task completion unchanged at 77.8%.
-
We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems
MCP-powered LLM agents are vulnerable to prompt injection from third-party services, and simple detection or filtering defenses do not reliably stop these attacks.
-
Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks
CoopGuard's defer-tempt-analyze-coordinate agents cut reported jailbreak success and raise attacker token costs on the new EMRA benchmark, but the deceptive-rate metric is partly defined by the paper's own scoring rubric.
-
Byzantine-Robust Decentralized Coordination of LLM Agents
A leaderless, Byzantine-robust LLM agent coordination protocol selects answers by geometric-median aggregation of evaluator scores instead of leader-based quorum voting.
-
A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
The paper surveys security risks of LLM agents, organizes them into a five-level autonomy taxonomy, and proposes an untested CMDP-based architecture called R2A2.
-
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
The ATLAS 2025 competition demonstrates that vision-language models remain highly vulnerable to flowchart-based and cross-modal jailbreak attacks, with top scores exceeding 93%.
Discussion (0). Sign in to comment.