SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.05808 · 2026

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents

Yang Deng, Nan Cheng, Yanhua Yu, Shuai Zhen, Roupei Guo

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2604.05808.json · badge: /api/ran/2604.05808.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
TonyStark042/STEP-HRL canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_step_process Ran
ran; our contract draft was wrong, not the code
TonyStark042/STEP-HRL/util/replay_buffer.py
pointer only (licence: NONE) · get_code("31c050f871b8a677")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonyStark042/STEP-HRL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_action Ran
ran; our contract draft was wrong, not the code
TonyStark042/STEP-HRL/util/extract.py
pointer only (licence: NONE) · get_code("4ad7102e66516be5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonyStark042/STEP-HRL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_action_done Ran
ran; our contract draft was wrong, not the code
TonyStark042/STEP-HRL/util/extract.py
pointer only (licence: NONE) · get_code("5119749903641e3c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonyStark042/STEP-HRL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_high_obs Ran
ran; our contract draft was wrong, not the code
TonyStark042/STEP-HRL/util/concat_input.py
pointer only (licence: NONE) · get_code("3188eea5d16e0b32")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonyStark042/STEP-HRL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

batch_traj_process Not yet run
unverified (harvested, no recorded run)
TonyStark042/STEP-HRL/util/replay_buffer.py
pointer only (licence: NONE) · get_code("aceb00536eb85d32")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonyStark042/STEP-HRL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks. However, existing LLM agents typically rely on increasingly long interaction histories, resulting in high computational cost and limited scalability. In this paper, we propose STEP-HRL, a hierarchical reinforcement learning (HRL) framework that enables step-level learning by conditioning only on single-step transitions rather than full interaction histories. STEP-HRL structures tasks hierarchically, using completed subtasks to represent global progress of overall task. By introducing a local progress module, it also iteratively and selectively summarizes interaction history within each subtask to produce a compact summary of local progress. Together, these components yield augmented step-level transitions for both high-level and low-level policies. Experimental results on ScienceWorld and ALFWorld benchmarks consistently demonstrate that STEP-HRL substantially outperforms baselines in terms of performance and generalization while reducing token usage. Our code is available at https: //github.com/TonyStark042/STEP-HRL. Task Description: Your task is to find a(n) non-living thing. First, focus on the thing. Then, move it to the purple box in the bathroom. Observation: This room is called the kitchen. In it, you see the agent, a substance called air, a chair, a counter, a cupboard, a freezer, a fridge, a glass jar, a lighter, an oven, a painting, a sink, soap, a stopwatch, a stove, a table with a glass cup, and a thermometer. You also see: a door to the bathroom (closed), a door to the hallway (closed), and a door to the outside (closed). Action: open door to bathroom Reward: 0.08 Observation: The door is now open. Action: go to bathroom Reward: 0.17 Observation: This room is called the bathroom. In it, you see a bathtub, a drawing, a glass cup, a purple box, a sink, and a toilet. Action: focus on cup Reward: 0.50 Observation: You focus on the glass cup. Action: move cup to purple box Reward: 0.25 Observation: You move the glass cup to the purple box. done.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2604.05808")
get_code_for_paper("2604.05808")
have("2604.05808")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2604.05808.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2604.05808.svg)](https://syntology.ai/paper/2604.05808)

Connect an agent — have() is free.