SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15809 · 2024

Empowering Large Language Model Agents through Action Learning

arXiv · PDF · Open in the Atlas

Code that ran

12 of 17 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 10 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2402.15809.json · badge: /api/ran/2402.15809.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
zhao-ht/learnact canonical (classifier label)
classifier basis: census
12 ran · 5 no recorded run
FunctionStatusWhere it lives
add_api_agent_args Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/model/model_arguments.py
pointer only (licence: NONE) · get_code("be016c6de5f601d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

add_learnact_agent_args Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/model/model_arguments.py
pointer only (licence: NONE) · get_code("7caf0b02e41211df")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

add_py_agent_args Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/model/model_arguments.py
pointer only (licence: NONE) · get_code("6859a11371fed89f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

answer_eval Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/pipelines.py
pointer only (licence: NONE) · get_code("b7f08cfff2002157")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

copy Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/aux_func/copy.py
pointer only (licence: NONE) · get_code("9dfdb5e4175893d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

execute Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/aux_func/aux_func.py
pointer only (licence: NONE) · get_code("a9ab3708c00ae21a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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_max_context_length Ran
ran, honoured the contract we drafted
zhao-ht/learnact/model/get_model.py
pointer only (licence: NONE) · get_code("5cc44cb6d5cddbbc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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_tool_improve_prompt_format_description Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/model/learnact_agent/learnact_learner.py
pointer only (licence: NONE) · get_code("d12c286b918664d5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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_tool_maker_decompose_combination_prompt Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/model/learnact_agent/learnact_learner.py
pointer only (licence: NONE) · get_code("65a2191cc48b12b8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

result_is_plan Ran
ran, violated the contract we drafted
zhao-ht/learnact/model/learnact_agent/learnact_learner.py
pointer only (licence: NONE) · get_code("24c0689eb0fad494")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

resume_result_pd Ran
ran; our contract draft was wrong, not the code
zhao-ht/learnact/pipelines.py
pointer only (licence: NONE) · get_code("53e3f2d42a930b19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

run_with_timeout Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhao-ht/learnact/aux_func/aux_func.py
pointer only (licence: NONE) · get_code("f8a4de0b6faeff3a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

call_chat_gpt Not yet run
unverified (harvested, no recorded run)
zhao-ht/learnact/backbone/gpt.py
pointer only (licence: NONE) · get_code("96896b883b68a043")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

execute_basic Not yet run
unverified (harvested, no recorded run)
zhao-ht/learnact/aux_func/aux_func.py
pointer only (licence: NONE) · get_code("8b1dcbddb6017e53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

load_backbone Not yet run
unverified (harvested, no recorded run)
zhao-ht/learnact/model/get_model.py
pointer only (licence: NONE) · get_code("6c4aba17c8429917")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

num_tokens_from_messages Not yet run
unverified (harvested, no recorded run)
zhao-ht/learnact/backbone/gpt.py
pointer only (licence: NONE) · get_code("f17d8dea2f3b9842")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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.

resume_result_jsonl Not yet run
unverified (harvested, no recorded run)
zhao-ht/learnact/pipelines.py
pointer only (licence: NONE) · get_code("996a26fe0469527e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao-ht/learnact 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 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 17 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 recently garnered increasing interest yet they are limited in their ability to learn from trial and error, a key element of intelligent behavior. In this work, we argue that the capacity to learn new actions from experience is fundamental to the advancement of learning in LLM agents. While humans naturally expand their action spaces and develop skills through experiential learning, LLM agents typically operate within fixed action spaces, limiting their potential for growth. To address these challenges, our study explores open-action learning for language agents. We introduce a framework LearnAct with an iterative learning strategy to create and improve actions in the form of Python functions. In each iteration, LLM revises and updates the currently available actions based on the errors identified in unsuccessful training tasks, thereby enhancing action effectiveness. Our experimental evaluations across Robotic Planning and Alfworld environments reveal that after learning on a few training task instances, our approach to open-action learning markedly improves agent performance for the type of task (by 32 percent in AlfWorld compared to ReAct+Reflexion, for instance) highlighting the importance of experiential action learning in the development of more intelligent LLM agents.

For agents

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

get_harvested_code_for_paper("2402.15809")
get_code_for_paper("2402.15809")
have("2402.15809")

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

curl https://syntology.ai/api/ran/2402.15809.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.15809.svg)](https://syntology.ai/paper/2402.15809)

Connect an agent — have() is free.