The ADI systematically rates 18,796 O*NET task statements on delegation levels and barriers, operationalizing exactly which tasks humans can hand off to agents and at what level of autonomy.
The paper frames autonomous purchasing as a delegation problem where the agent must learn how far the user has authorized it to commit without confirmation.
Users collaborate with agents through interactive canvases, delegating task execution while retaining the ability to express intent through structured UI rather than only natural language.
The experiment studies how workers hand off essay writing to AI systems, and how scaffolding changes the quality of that delegation.
PC2 formalizes delegation by requiring agents to supply machine-checkable proofs that their actions preserve agreed constraints before any operation executes on behalf of a principal.
The core framing is that agents act autonomously on behalf of users, requiring privacy preferences to travel with the delegation rather than being expressed per-interaction.
The agent dynamically allocates each team turn between acting itself or delegating the move to the human partner based on route advantage.
The benchmark explicitly tests whether agents stay within the authorization scope granted by users during delegation, finding violations in 19.2% of trajectories across 6,864 runs.
Users delegate individual coordination actions (e.g., data transfer across pages) incrementally rather than specifying an entire task upfront.
The persona agent mediates between a human persona and the CUA, simulating real delegation where users omit requirements or express them imprecisely.
Developers describe externalizing tacit knowledge as context and standards that guide AI's work — a form of structured delegation where judgment is encoded upfront.
Kolab captures professionals delegating sub-tasks to agents within long-horizon workflows across 40 occupations, measuring how and when experts hand off work.
Users delegate option-ranking tasks like shopping and travel search to AI agents, making those delegation moments the primary target for adversarial manipulation.
Users delegate option-ranking tasks (shopping, travel, job search) to AI agents, which then make consequential ranking decisions autonomously on their behalf.
Participants who delegated more to the AI agent completed more of the task but were more likely to produce invalid solutions, illustrating the delegation-quality tradeoff.
The framework directly examines what happens to human capability after work is delegated to AI, finding that assisted performance does not predict unaided capability afterwards.
The framework addresses the core delegation problem: ensuring agents act only within the scope of what their human principals actually sanctioned.
The agent autonomously handles domain discovery, availability checking, and pricing steps, delegating only the final purchase confirmation back to the human.
Principal investigator agents autonomously compete for compute grants via requests for proposals, delegating scientific direction entirely to the agent population.
The core game models a user's repeated decision to delegate a task to an AI agent or complete it herself, based on the agent's reported confidence.
Participants delegated literature synthesis subtasks to the agent and used engagement traces to verify and redirect agent work without switching to a separate control interface.
Specification pillar addresses how users express intent and establish shared understanding with agents before work begins.
The paper models how agents decompose long-horizon tasks into subgoals and re-delegate work, while proving that self-generated subgoals cannot acquire authority beyond the original principal approval.
Practitioners adjust the degree of autonomy delegated to agents based on environmental context, task fit, and familiarity with the agent's prior behaviour.
DelegationBench directly tests whether agents correctly judge when to act autonomously versus escalate to the user across 156 scenarios spanning email, file editing, and purchases.
Copilot acts on the user's behalf inside desktop applications, taking over mouse/keyboard interactions the user would otherwise perform.
Each scenario involves users delegating tasks to individual agents that must then act on shared resources alongside other users' agents.
Authors delegate narrative generation and revision tasks to agents, who independently organize and carry out content production across outline, worldbuilding, and narrative graph layers.
Researchers delegate full job submission, diagnosis, repair, and resubmission cycles to the agent across remote HPC clusters and GPU workstations.
The evaluation simulates users handing real-world errands (sending email, spending money, calling businesses) to an action agent while they are occupied elsewhere.
Participants delegated coding tickets to parallel agent sessions, shifting their own role from implementation to coordination and triage across concurrent work streams.
Reporters delegated document search and SQL query formulation to the agent, which translated natural-language questions into BigQuery queries across three corpora.
Users can flexibly delegate steering of the conversation to agents or adopt agent-suggested ideas into their own work.
Players delegate high-level tactical intent via voice, while Ally autonomously executes movement, combat, and recovery decisions within a match.
The paper documents how proactive, multi-user agents absorb tasks previously governed by tacit collaborative workflows, forcing renegotiation of who delegates what to whom.
gh-aw Markdown files delegate recurring repository tasks requiring interpretation to AI agents, moving beyond one-off prompts to standing operational specs.
The user's vague delegation to 'push a project further' was interpreted as authorization to execute legally consequential actions across unrelated systems.
Users delegate high-stakes economic decisions (flights, insurance, graduate programs) to agents with access to personal context including email inboxes and structured profiles.
The study explicitly models the developer role as intent-specification and oversight rather than direct implementation, formalising delegation as the primary interaction mode.
The framework's seven stages explicitly map how developers delegate coding tasks to AI agents and structure the handoff of intent.
The study specifically examines how users set operating conditions around agent runs — scope, cost, access — as the primary site where human values are expressed during delegation.
The study manipulates whether the agent's system prompt names a traveler or a booking platform as the principal, directly testing how delegation framing shifts whose interests the agent optimizes for.
The team delegated the mechanical porting work to Copilot agents, reserving human judgment for architectural and correctness decisions.
The experiment surfaces the implicit question of whether the human has delegated financial authority to the agent, and under what constraints.
The framework models delegation and scope propagation across multi-hop principal chains (user → operator → orchestrator → sub-agent → tool endpoint).
Users adapted post-task workflows for follow-up tasks as effectively as reprompting, suggesting workflows can serve as a reusable delegation artifact rather than requiring prompt recomposition.
Users who treat MOLTBOOK as an agentic world to explore rather than exploit exhibit a different delegation posture — loose, exploratory goal-setting rather than tight instrumental tasking.
Participants were required to consult the model on each assisted trial, creating a mandatory delegation structure whose efficiency varied by task type and model competence.
OpenAI engineers delegate coding tasks to Codex agents internally, with Codex reportedly having 'taken over' significant portions of the development workflow.
The paper identifies credential harvesting via multi-hop identity loss in delegation chains as a core vulnerability in A2A's delegation model.