# Task-Aware Delegation Cues for LLM Agents

arXiv: https://arxiv.org/abs/2603.11011 · HTML: https://mlsanity.com/paper/2603.11011/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 11 of 11)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs](https://mlsanity.com/paper/2503.10657/) (2025)
- [Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models](https://mlsanity.com/paper/2402.11723/) (2024)
- [Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions](https://mlsanity.com/paper/2402.06509/) (2024)
- [Advancing Multimodal Data Fusion in Pain Recognition: A Strategy Leveraging Statistical Correlation and Human-Centered Perspectives](https://mlsanity.com/paper/2404.00320/) (2024)
- [CauSkelNet: Causal Representation Learning for Human Behaviour Analysis](https://mlsanity.com/paper/2409.15564/) (2024)
- [Uncertainty-Gated Generative Modeling](https://mlsanity.com/paper/2603.07753/) (2026)

## Built on by (most cited first, 2 of 2)

- [CADMAS-CTX: Contextual Capability Calibration for Multi-Agent Delegation](https://mlsanity.com/paper/2604.17950/) (2026)
- [Delegating or Doing? Understanding User Behavior in Hybrid Human-Agent Interfaces](https://mlsanity.com/paper/2608.19551/) (2026)

## Abstract (arXiv)

LLM agents increasingly present as conversational collaborators, yet human--agent teamwork remains brittle due to information asymmetry: users lack task-specific reliability cues, and agents rarely surface calibrated uncertainty or rationale. We propose a task-aware collaboration signaling layer that turns offline preference evaluations into online, user-facing primitives for delegation. Using Chatbot Arena pairwise comparisons, we induce an interpretable task taxonomy via semantic clustering, then derive (i) Capability Profiles as task-conditioned win-rate maps and (ii) Coordination-Risk Cues as task-conditioned disagreement (tie-rate) priors. These signals drive a closed-loop delegation protocol that supports common-ground verification, adaptive routing (primary vs. primary+auditor), explicit rationale disclosure, and privacy-preserving accountability logs. Two predictive probes validate that task typing carries actionable structure: cluster features improve winner prediction accuracy and reduce difficulty prediction error under stratified 5-fold cross-validation. Overall, our framework reframes delegation from an opaque system default into a visible, negotiable, and auditable collaborative decision, providing a principled design space for adaptive human--agent collaboration grounded in mutual awareness and shared accountability.