AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork

Yuheng Jing, Kai Li, Jiajun Zhang, Zeyao Ma, Jiaxi Yang, Lei Zhang, Zhe Wu, Jinmin He, Junliang Xing, Jian Cheng

ICML 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Collaborative multi-agent perception · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use AD/DPT in-context RL instead of random policyAD, DPT · ICRL4AHT Track 1average return: DPT 12.4 vs Random 5.5; AD 9.1Mixed
use AD/DPT instead of random policy on unseen layoutsAD, DPT · ICRL4AHT Track 2average return: AD 4.4, DPT 13.2 vs Random 11.7 (asymm adv right)Hurt
add teammate actions as input (+TA) (ablation)AD, DPT · ICRL4AHT Track 1/2average return: DPT test wide H1 -23.4 -> -14.5; demo wide H2 9.4 -> 6.8Mixed
increase Transformer context length from 250 to 2000 (ablation)AD, DPT · test wide, demo wideaverage returnNo clear effect
scale model size and training budget (Small to Large) (ablation)AD, DPT · ICRL4AHT Tracks 1 and 2mean return: modest gains on teammate track, limited on layoutMixed
replace Transformer with CNN+GRU recurrent tracker (Hybrid-AD) (ablation)AD · ICRL4AHTmean return: test wide -7.9 -> -6.5; cramped down 0.8 -> 0.5No clear effect
use offline RL objective (AMAGO-Offline) instead of action prediction (ablation)AD/DPT · ICRL4AHT Teammate trackmean return: 8.3 vs AD 8.1, DPT 7.4No clear effect
extend context to 10,000 (ablation)AD, DPT · ICRL4AHT selected settingsreturnMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy