VLMs preserve linearly separable visual magnitudes and can compare them, yet collapse at symbolic mapping because visual and textual number spaces remain fractured and disjoint.
hub
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
abstract
Agentic AI systems are increasingly capable of performing professional and personal tasks with limited human involvement. However, tracking these developments is difficult because the AI agent ecosystem is complex, rapidly evolving, and inconsistently documented, posing obstacles to both researchers and policymakers. To address these challenges, this paper presents the 2025 AI Agent Index. The Index documents information regarding the origins, design, capabilities, ecosystem, and safety features of 30 state-of-the-art AI agents based on publicly available information and email correspondence with developers. In addition to documenting information about individual agents, the Index illuminates broader trends in the development of agents, their capabilities, and the level of transparency of developers. Notably, we find different transparency levels among agent developers and observe that most developers share little information about safety, evaluations, and societal impacts. The 2025 AI Agent Index is available online at https://aiagentindex.mit.edu
hub tools
citation-role summary
background 4
citation-polarity summary
years
2026 17roles
background 4polarities
background 4representative citing papers
The Moltbook Observatory Archive is the first large-scale dataset from a social network populated exclusively by autonomous AI agents, covering 78 days with 2.6 million posts and 1.2 million comments.
Anumati defines proof of adherence via versioned PolicyDocument, ConsentRecord, and AdherenceEvent primitives as a non-breaking extension to A2A and MCP protocols.
AI agent providers face an exhaustive inventory requirement for actions and data flows, as high-risk systems with untraceable behavioral drift cannot meet the AI Act's essential requirements.
The web's anti-bot regime should be replaced by a framework that presumptively lets user-authorized AI agents act for their principals, requires platforms to disclose access policies, and permits agent blocking only when proportionate to concrete harms.
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
A typed-contract harness with containerized 'chambers' and robotics-specific agent skills lets a coding LLM turn a single natural-language prompt into working reproduction, evaluation, and deployment workflows for robot learning.
Claude Code answers recurring agent design questions with a thin model loop wrapped in dense safety, context, extensibility, and persistence harnesses, and those same questions get different answers in OpenClaw and Hermes.
HDP is a lightweight protocol that binds human authorization to sessions via signed append-only token chains, enabling offline verification of delegation provenance using only an Ed25519 public key and session identifier.
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
Self-evolving LLM agents introduce persistent, amplifying security threats that static defenses cannot address, as shown by analysis of 25 attack surface cells and case studies.
Agentic AI systems are shifting software engineering from line-level code generation to delegated repository-scale execution under supervision, with SWE-bench performance rising from 1.96% to 78.4% and productivity gains of 13.6-55.8%.
Sovereign Agentic Loops decouple LLM reasoning from execution by emitting validated intents through a control plane with obfuscation and evidence chains, blocking 93% of unsafe actions in a cloud prototype while adding 12.4 ms latency.
TRiSM-guided agentic workflows reduced RAG poisoning attack success from 31% to 10%, data-field injection from 42% to 25%, eliminated network injection, and raised report accuracy from 72.5% to 86.5% across five LLMs and 800 generations.
A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.
A reported 2026 frontier model escape shows that alignment training, sandboxing, tool interception, and audits fail against adversarial agentic AI, requiring five new architectural requirements for durable containment.
citing papers explorer
-
Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms
VLMs preserve linearly separable visual magnitudes and can compare them, yet collapse at symbolic mapping because visual and textual number spaces remain fractured and disjoint.
-
The Moltbook Observatory Archive: an incremental dataset of agent-only social network activity
The Moltbook Observatory Archive is the first large-scale dataset from a social network populated exclusively by autonomous AI agents, covering 78 days with 2.6 million posts and 1.2 million comments.
-
Anumati: Proof of Adherence as a Formal Consent Model for Autonomous Agent Protocols
Anumati defines proof of adherence via versioned PolicyDocument, ConsentRecord, and AdherenceEvent primitives as a non-breaking extension to A2A and MCP protocols.
-
AI Agents Under EU Law
AI agent providers face an exhaustive inventory requirement for actions and data flows, as high-risk systems with untraceable behavioral drift cannot meet the AI Act's essential requirements.
-
The Agentic Web Requires New Normative Infrastructure
The web's anti-bot regime should be replaced by a framework that presumptively lets user-authorized AI agents act for their principals, requires platforms to disclose access policies, and permits agent blocking only when proportionate to concrete harms.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
Nautilus: From One Prompt to Plug-and-Play Robot Learning
A typed-contract harness with containerized 'chambers' and robotics-specific agent skills lets a coding LLM turn a single natural-language prompt into working reproduction, evaluation, and deployment workflows for robot learning.
-
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Claude Code answers recurring agent design questions with a thin model loop wrapped in dense safety, context, extensibility, and persistence harnesses, and those same questions get different answers in OpenClaw and Hermes.
-
HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems
HDP is a lightweight protocol that binds human authorization to sessions via signed append-only token chains, enabling offline verification of delegation provenance using only an Ed25519 public key and session identifier.
-
Security Considerations for Multi-agent Systems
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
-
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Self-evolving LLM agents introduce persistent, amplifying security threats that static defenses cannot address, as shown by analysis of 25 attack surface cells and case studies.
-
Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering
Agentic AI systems are shifting software engineering from line-level code generation to delegated repository-scale execution under supervision, with SWE-bench performance rising from 1.96% to 78.4% and productivity gains of 13.6-55.8%.
-
Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems
Sovereign Agentic Loops decouple LLM reasoning from execution by emitting validated intents through a control plane with obfuscation and evidence chains, blocking 93% of unsafe actions in a cloud prototype while adding 12.4 ms latency.
-
Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare
TRiSM-guided agentic workflows reduced RAG poisoning attack success from 31% to 10%, data-field injection from 42% to 25%, eliminated network injection, and raised report accuracy from 72.5% to 86.5% across five LLMs and 800 generations.
-
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.
-
Responsible Agentic AI Requires Explicit Provenance
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.
-
When the Agent Is the Adversary: Architectural Requirements for Agentic AI Containment After the April 2026 Frontier Model Escape
A reported 2026 frontier model escape shows that alignment training, sandboxing, tool interception, and audits fail against adversarial agentic AI, requiring five new architectural requirements for durable containment.