AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

DeepHA: Scaling Action Chains Elicits Deep Hierarchical Agents

Zihao Wang, Muyao Li, Kaichen He, Haowei Lin, Xiaojian Ma, Anji Liu, Yitao Liang

ICML 2026 · Multi-agent systems and games › LLM agents · approach: Robust and efficient agent execution

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes DeepHA, a unified hierarchical agent architecture that operates across a mixture of heterogeneous action spaces by generating action chains.

Problem

Autonomous agents are usually constrained to a single predefined action space, which limits generalization across tasks and causes compounding errors from decoupled policy execution.

Approach

A unified architecture that flexibly generates action chains spanning heterogeneous action spaces within one hierarchical policy, instead of a single fixed action space with decoupled execution.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add a Motion action before the raw action (ablation)DeepHA · MinecraftASR (%): 30.0 -> 39.2Improved
add a Grounding action before the raw action (ablation)DeepHA · MinecraftASR (%): 30.0 -> 42.6Improved
use full Grounding, Motion, Raw chain (depth 3) instead of depth 2 Grounding chain (ablation)DeepHA · MinecraftASR (%): 42.6 -> 48.9Improved
add efficient trajectory-compressed memory vs no memory (ablation)DeepHA · MinecraftASR (%): 37.1 -> 39.6Improved
add efficient memory vs no memory (ablation)DeepHA · MinecraftBo10 (%): 68.3 -> 77.3Improved
use efficient memory instead of full sliding-window memory (ablation)DeepHA · Minecraftcontext tokens: 7948 -> 1976Improved
use efficient memory instead of full memory (ablation)DeepHA · MinecraftBo10 (%): 78.5 -> 77.3No clear effect
use Eager mode instead of Direct mode with Motion outcome (ablation)DeepHA · Minecraft embodiedASR (%): 32.9 -> 37.6Improved
use Eager mode instead of Direct mode with Grounding outcome (ablation)DeepHA · Minecraft embodiedASR (%): 37.7 -> 40.7Improved
use Greedy mode with Raw outcome instead of Direct Raw (ablation)DeepHA · Minecraft embodiedASR (%): 34.5 -> 48.9Improved
use Eager (Grounding) instead of Greedy (Raw) mode (ablation)DeepHA · MinecraftFPS: 1.2 -> 6.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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