Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork

• URL: http://arxiv.org/abs/2607.27177v1
• Date: Wed, 29 Jul 2026 17:50:39 GMT
• Title: Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
• Abstract summary: Ad-hoc teamwork is a crucial skill for autonomous agents.<n>Most current ad-hoc teamwork approaches assume that agents will collaborate on a single, fixed task.<n>We re-frame it as a problem of joint planning with decentralised execution under hidden partner capabilities.
• Score: 6.7593408237313115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents. Most current ad-hoc teamwork (AHT) approaches assume that agents will collaborate on a single, fixed task and that the partner's capabilities, their ability to successfully execute the desired action, are already known. In reality, a partner's true capabilities are often hidden, and human collaborators may act sub-optimally on tasks with multiple valid strategies. To address these limitations, we extend ad-hoc teamwork into a multi-task setting by re-framing it as a problem of joint planning with decentralised execution under hidden partner capabilities. We introduce CE-CM (Capability Estimation via Contextual Models), an approximate Bayesian method that infers task-invariant capability vectors. By using simulation-based sampling, the agent estimates capabilities and induces a contextual Multi-agent Markov Decision Processes for planning. This approach requires no population pre-training and refines its beliefs online from just a few tasks. To account for human unpredictability, we propose CE-CM-Div, an extension that evaluates capability hypotheses against diverse planner rollouts rather than a single optimal trajectory. Simulated experiments demonstrate that CE-CM rapidly recovers hidden capabilities, reduces infeasible action assignments, and adapts to changes over time. Furthermore, in an offline human study of 225 trajectories from 15 participants, CE-CM-Div substantially improved capability estimates over the baseline CE-CM method. Our results suggest capability-based modelling is a promising interpretable, task-agnostic representation in the studied settings, demonstrating that accounting for behavioural diversity is essential for robust human-AI teaming.

Related papers

• CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments [32.043112677406064]
  CollabSim is a simulation framework that combines a theory-grounded definition of collaborative capabilities, controlled manipulation of interaction conditions, and action-level probing of agents' internal states.<n> Experiments show that CollabSim can capture condition effects, separate model performance patterns, and reveal task-dependent effects of agent design.
  arXiv  Detail & Related papers  (2026-06-04T17:06:22Z)
• Adaptive Human-AI Coordination via Hierarchical Action Disentanglement [1.4255659581428333]
  Human-AI collaboration requires agents that can adapt to diverse partner behaviors and skill levels while remaining robust to unseen partners.<n>We propose Intrinsic Action Disentanglement (IAD), a deep hierarchical reinforcement learning framework that learns distinct, partner-aware low-level action sequences conditioned on high-level latent skills.<n>We evaluate IAD in the Overcooked-AI domain across multiple layouts and diverse partner settings, including unseen simulated partners, a human-proxy model trained on human-human gameplay, and real human partners.
  arXiv  Detail & Related papers  (2026-05-23T01:59:41Z)
• MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning [68.91090643731987]
  Deep reinforcement learning (RL) has been applied extensively to solve complex decision-making problems.<n>Existing approaches are limited to separate fields and can only handle multi-agent decision-making with a single objective.<n>We propose MO-mix to solve the multi-objective multi-agent reinforcement learning (MOMARL) problem.
  arXiv  Detail & Related papers  (2026-02-28T16:25:22Z)
• CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning [97.4254365377865]
  Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning.<n>We propose Channel-of-Mobile-Experts (CoME), a novel agent architecture consisting of four distinct experts.<n>Experiments show that CoME outperforms dense mobile agents and MoE methods on both AITZ and AMEX datasets.
  arXiv  Detail & Related papers  (2026-02-27T16:19:45Z)
• Learning "Partner-Aware" Collaborators in Multi-Party Collaboration [12.287537011305497]
  Large Language Models (LLMs) are increasingly bring deployed in agentic settings where they act as collaborators with humans.<n>This paper builds on the AI alignment and safe interruptability literature to offer novel theoretical insights on collaborative behavior.<n>We propose Interruptible Collaborative Roleplayer (ICR)-a novel partner-aware learning algorithm to train CG-optimal collaborators.
  arXiv  Detail & Related papers  (2025-10-26T00:05:48Z)
• Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies [0.0]
  Team-Attention-Actor-Critic (TAAC) is a learning algorithm designed to enhance multi-agent collaboration in cooperative environments.<n>We evaluate TAAC in a simulated soccer environment against benchmark algorithms.
  arXiv  Detail & Related papers  (2025-07-30T15:48:38Z)
• Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning [51.52387511006586]
  We propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm. HOP is hierarchically composed of two modules: an opponent modeling module that infers others' goals and learns corresponding goal-conditioned policies. HOP exhibits superior few-shot adaptation capabilities when interacting with various unseen agents, and excels in self-play scenarios.
  arXiv  Detail & Related papers  (2024-06-12T08:48:06Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors [93.38830440346783]
  We propose a multi-agent framework framework that can collaboratively adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that framework framework can effectively deploy multi-agent groups that outperform a single agent. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups.
  arXiv  Detail & Related papers  (2023-08-21T16:47:11Z)
• CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learning [5.865719902445064]
  We propose a novel multi-agent reinforcement learning algorithm CAMMARL. It involves modeling the actions of other agents in different situations in the form of confident sets. We show that CAMMARL elevates the capabilities of an autonomous agent in MARL by modeling conformal prediction sets.
  arXiv  Detail & Related papers  (2023-06-19T19:03:53Z)
• RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning [55.55009081609396]
  We propose a novel method, called Relation-Aware Credit Assignment (RACA), which achieves zero-shot generalization in ad-hoc cooperation scenarios. RACA takes advantage of a graph-based encoder relation to encode the topological structure between agents. Our method outperforms baseline methods on the StarCraftII micromanagement benchmark and ad-hoc cooperation scenarios.
  arXiv  Detail & Related papers  (2022-06-02T03:39:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.