REVIEW 19 cited by
Magentic-UI: Towards Human-in-the-loop Agentic Systems
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
Magentic-UI: Towards Human-in-the-loop Agentic Systems
read the original abstract
AI agents powered by large language models are increasingly capable of autonomously completing complex, multi-step tasks using external tools. Yet, they still fall short of human-level performance in most domains including computer use, software development, and research. Their growing autonomy and ability to interact with the outside world, also introduces safety and security risks including potentially misaligned actions and adversarial manipulation. We argue that human-in-the-loop agentic systems offer a promising path forward, combining human oversight and control with AI efficiency to unlock productivity from imperfect systems. We introduce Magentic-UI, an open-source web interface for developing and studying human-agent interaction. Built on a flexible multi-agent architecture, Magentic-UI supports web browsing, code execution, and file manipulation, and can be extended with diverse tools via Model Context Protocol (MCP). Moreover, Magentic-UI presents six interaction mechanisms for enabling effective, low-cost human involvement: co-planning, co-tasking, multi-tasking, action guards, and long-term memory. We evaluate Magentic-UI across four dimensions: autonomous task completion on agentic benchmarks, simulated user testing of its interaction capabilities, qualitative studies with real users, and targeted safety assessments. Our findings highlight Magentic-UI's potential to advance safe and efficient human-agent collaboration.
Forward citations
Cited by 19 Pith papers
-
Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents
Plan Mode for spreadsheet agents shifts requirements to clarifying questions, reduces refinement, and improves perceived collaboration without changing final workbook quality.
-
HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification
HANSEL extracts navigable evidence from agent trajectories with 83.7% precision and 88.8% recall on 45 tasks, reduces volume by 61.6%, and improves verification metrics in a 14-participant study.
-
How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
Formalizes design space for human-LLM collaborative planning along mode, scope, and level axes; evaluates AMBIPOM prototype via user study and benchmark revealing hybrid workflows and trade-offs.
-
Hedwig: Dynamic Autonomy for Coding Agents Under Local Oversight
Hedwig is a coding agent that dynamically adjusts its autonomy by learning behavioral guidelines from developer decisions and feedback over time.
-
AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents
AgentClick is a localhost npm server and skill-based plugin that connects terminal AI agents to a structured web UI for human review of plans, code execution, memory, and errors.
-
Comparing Human Oversight Strategies for Computer-Use Agents
Oversight strategy in computer-use agents shapes exposure to problematic actions more reliably than correction success, with plan-based approaches reducing occurrences but not uniformly improving interventions.
-
AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management
AgentProg reframes interaction history as a program with variables and control flow, plus a belief state for partial observability, achieving SOTA success rates on long-horizon GUI benchmarks while baselines degrade.
-
Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
GUI agents frequently fall for deceptive interface designs, often without recognizing them, and human supervision of agents improves avoidance only partially while introducing new attention and workload costs.
-
Instruction Agent: Enhancing Agent with Expert Demonstration
With one human demonstration, the Instruction Agent extracts instructions and uses verifier/backtracker modules to execute them, reaching 60% success on 20 previously unsolved OSWorld tasks.
-
Governed AI-Assisted Engineering: Graduated Human Oversight for Agentic Code Generation in Regulated Domains
A four-dimension classifier routes agentic coding tasks into HITL, human-over-the-loop, or automated-with-monitoring tiers, analytically estimated to keep ~91% of ungoverned coding velocity under regulatory constraints.
-
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents
JarvisHub open-sources a three-layer canvas-state, protocol-bridge, and agent-runtime harness so multimodal creative agents can inspect and update a shared editable project graph over long workflows.
-
Plover: Steering GUI Agents through Plan-Centric Interaction
An expert repairing visible plans rescued 23 of 26 failed GUI automation runs, turning 17 into full and 6 into partial successes.
-
HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization
HiLSVA shows that a human-in-the-loop LLM agent system can help novices and experts complete scientific visualization tasks, while human oversight adds measurable execution time.
-
RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution
RunAgent improves LLM reliability on structured plans by deriving constraints on the fly, using an agentic language with control flow, and dynamically selecting reasoning modes, outperforming baselines on Natural-plan...
-
Auditing and Controlling AI Agent Actions in Spreadsheets
Pista decomposes AI agent actions in spreadsheets into auditable steps, enabling real-time user intervention that improves task outcomes, user comprehension, agent perception, and sense of co-ownership over baseline agents.
-
HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization
HiLSVA introduces a plan-first multi-agent LLM system for scientific visualization that incorporates explicit human oversight, stepwise provenance, and learn-at-test-time adaptation, evaluated via case studies and a 1...
-
Governed AI-Assisted Engineering: Graduated Human Oversight for Agentic Code Generation in Regulated Domains
GAIE introduces an Oversight Classification Model to route code generation tasks to human-in-the-loop, human-over-the-loop, or automated-with-monitoring tiers based on regulatory impact, customer proximity, reversibil...
-
Omakase: proactive assistance with actionable suggestions for evolving scientific research projects
Omakase monitors project documents to infer timely queries and distills research reports into actionable suggestions that users rated significantly more useful than raw reports.
-
Agents in the Wild: Where Research Meets Deployment
A tutorial description reviewing the state of LLM agent deployment, with no new research findings.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.