Coding agents struggle to infer least-privilege file permissions by omitting needed accesses while granting unused or sensitive ones, but Sufficiency-Tightness Decomposition improves sensitive-task success by up to 15.8% and reduces attacks.
hub
Trism for agentic ai: A review of trust, risk, and security management in llm-based agentic multi-agent systems
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 3
baseline 1
citation-polarity summary
representative citing papers
FLARE extracts specifications from multi-agent LLM code and applies coverage-guided fuzzing to achieve 96.9% inter-agent and 91.1% intra-agent coverage while uncovering 56 new failures across 16 applications.
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
Context Kubernetes formalizes six abstractions for knowledge orchestration in agentic AI, with experiments showing a three-tier permission model blocks all five tested attack scenarios where simpler baselines fail.
The AAGMM five-level model, validated in 750 simulations, shows higher governance maturity cuts agent sprawl by 94% and risk incidents by 96% while raising task completion rates by 33%.
Agentic entropy names the systemic drift in AI coding agents away from architectural intent; a new framework using conformity seeding, reasoning monitoring, and causal graph interfaces supplies process-level oversight to complement existing review methods.
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
An integrated framework using autoencoders, deep reinforcement learning, and LLMs automates risk-based prioritization and contextual analysis of suspicious network traffic within Splunk SOC environments.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
A hybrid agentic AI and multi-agent framework is proposed for prescriptive maintenance in smart manufacturing, using an LLM planner for workflow orchestration and specialized agents for schema discovery, feature analysis, model selection, and optimization, with initial validation on two industrial 1
A rapid review of fairness in LLM-enabled multi-agent systems for the software development lifecycle concludes that the field lacks standardized evaluations, broad coverage, and effective governance, leaving it unprepared for deployable fair systems.
citing papers explorer
-
Do Coding Agents Understand Least-Privilege Authorization?
Coding agents struggle to infer least-privilege file permissions by omitting needed accesses while granting unused or sensitive ones, but Sufficiency-Tightness Decomposition improves sensitive-task success by up to 15.8% and reduces attacks.
-
FLARE: Agentic Coverage-Guided Fuzzing for LLM-Based Multi-Agent Systems
FLARE extracts specifications from multi-agent LLM code and applies coverage-guided fuzzing to achieve 96.9% inter-agent and 91.1% intra-agent coverage while uncovering 56 new failures across 16 applications.
-
When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
-
Context Kubernetes: Declarative Orchestration of Enterprise Knowledge for Agentic AI Systems
Context Kubernetes formalizes six abstractions for knowledge orchestration in agentic AI, with experiments showing a three-tier permission model blocks all five tested attack scenarios where simpler baselines fail.
-
Governing the Agentic Enterprise: A Governance Maturity Model for Managing AI Agent Sprawl in Business Operations
The AAGMM five-level model, validated in 750 simulations, shows higher governance maturity cuts agent sprawl by 94% and risk incidents by 96% while raising task completion rates by 33%.
-
Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development
Agentic entropy names the systemic drift in AI coding agents away from architectural intent; a new framework using conformity seeding, reasoning monitoring, and causal graph interfaces supplies process-level oversight to complement existing review methods.
-
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
-
Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage
An integrated framework using autoencoders, deep reinforcement learning, and LLMs automates risk-based prioritization and contextual analysis of suspicious network traffic within Splunk SOC environments.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
-
Hybrid Agentic AI and Multi-Agent Systems in Smart Manufacturing
A hybrid agentic AI and multi-agent framework is proposed for prescriptive maintenance in smart manufacturing, using an LLM planner for workflow orchestration and specialized agents for schema discovery, feature analysis, model selection, and optimization, with initial validation on two industrial 1
-
Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review
A rapid review of fairness in LLM-enabled multi-agent systems for the software development lifecycle concludes that the field lacks standardized evaluations, broad coverage, and effective governance, leaving it unprepared for deployable fair systems.