arXiv AI
Agentic Societies Need a Social Harness
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 10
Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
arXiv:2605. 19035v2 Announce Type: replace Abstract: The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution.
arXiv AI
Jul 14
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
arXiv:2607. 09766v1 Announce Type: new Abstract: AI agents are increasingly deployed in shared environments where they pursue diverse goals and compete for rewards.
arXiv Computation and Language
Aug 24
Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers
The paper surveys 61 studies on mental‑health AI and identifies a misalignment in how trust is evaluated across disciplines. It proposes a three‑layer framework—human‑oriented, interaction‑oriented, and AI‑oriented trust—and maps stakeholder perspectives onto these layers. The authors argue that future research should focus on calibrating human trust to actual interaction and AI trustworthiness rather than merely maximizing perceived trust.
arXiv AI
Oct 21
MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
MAS-Guard is a unified framework designed to safeguard both single- and multi-agent large language model (LLM) systems. It introduces a local Agent Guardrail (A-Guard) layer that uses task-specific experts to evaluate agentic events, and a system-level Control Plane that applies deterministic structural checks and semantic assessments to routes, capabilities, and message content. The framework enforces interventions—allow, reflection, confirmation, and block—across benchmarks, reducing attack success rates by 71.5‑86.3% while maintaining utility on benign tasks.
arXiv Computation and Language
Oct 26
Under the Influence: Evaluating and Improving LLM Vigilance in Agentic Tasks
arXiv:2602.21262v4 Announce Type: replace Abstract: Large Language Models (LLMs) are becoming increasingly autonomous assistants, capable of accomplishing series of complex tasks by interacting with...
arXiv AI
1d ago
Corralling AI Risks with Grassroots Contracts
The paper "Corralling AI Risks with Grassroots Contracts" identifies three major AI risks affecting digital platforms: (1) AI control of global platforms, (2) unaccountable AI agents operating alongside humans, and (3) unattributed deepfakes. It proposes grassroots contracts—digital agreements inspired by Pierre‑Joseph Proudhon—to mitigate these risks by establishing accountability for AI agents in social graphs and ensuring digital provenance in social networks. The authors also present smartphone applications that implement these contracts and demonstrate how they address the identified risks.