Papers › Empowering Large Language Model Agents through Action Learning

Empowering Large Language Model Agents through Action Learning

24 Feb 2024arXiv:2402.15809archive 2025-07-28

Haiteng Zhao, Chang Ma, Guoyin Wang, Jing Su, Lingpeng Kong, Jingjing Xu, Zhi-Hong Deng, Hongxia Yang

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 12 ran (6 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zhao-ht/learnact officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 12 ran (6 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
6ran · our draft was wrong
5ran
5unverified

Licence: 17 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhao-ht/learnact. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zhao-ht/learnact official repository 17 samples, 12 ran (6 instrument-failed) · 5 unverified
add_api_agent_args model/model_arguments.py ran · our draft was wrong no licence file found · pointer only · be016c6de5f601d7 · report fixture: signature parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-24
add_learnact_agent_args model/model_arguments.py ran · our draft was wrong no licence file found · pointer only · 7caf0b02e41211df · report fixture: signature parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-24
add_py_agent_args model/model_arguments.py ran · our draft was wrong no licence file found · pointer only · 6859a11371fed89f · report fixture: signature parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-24
answer_eval pipelines.py ran no licence file found · pointer only · b7f08cfff2002157 · report fixture: signature response:dict/0/?, dataset:str/0/str, data:dict/0/?, evaluator:callable/0/?, model_result_recoder:callable/0/? · returned tuple · level recorded 2026-09-24
copy aux_func/copy.py ran · our draft was wrong no licence file found · pointer only · 9dfdb5e4175893d8 · report fixture: signature x:SimpleObject/0/? · returned SimpleObject · level recorded 2026-09-24
execute in 12 papers aux_func/aux_func.py ran no licence file found · pointer only · a9ab3708c00ae21a · report fixture: signature code_str:str/0/str, time_limit_query:int/0/int, global_env:dict/0/? · returned dict · level recorded 2026-09-24
get_max_context_length model/get_model.py ran no licence file found · pointer only · 5cc44cb6d5cddbbc · report fixture: signature model_name:str/0/str, model_size:str/0/str · returned int · level recorded 2026-09-24
get_tool_improve_prompt_format_description model/learnact_agent/learnact_learner.py ran · our draft was wrong no licence file found · pointer only · d12c286b918664d5 · report fixture: signature version:str/0/str · returned str · level recorded 2026-09-24
get_tool_maker_decompose_combination_prompt model/learnact_agent/learnact_learner.py ran · our draft was wrong no licence file found · pointer only · 65a2191cc48b12b8 · report fixture: signature version:str/0/str · returned str · level recorded 2026-09-24
result_is_plan model/learnact_agent/learnact_learner.py ran · violated contract no licence file found · pointer only · 24c0689eb0fad494 · report fixture: signature response:str/0/str · returned bool · level recorded 2026-09-24
resume_result_pd pipelines.py ran no licence file found · pointer only · 53e3f2d42a930b19 · report fixture: signature file_name:str/0/str, executed_column:str/0/str · returned tuple · level recorded 2026-09-24
run_with_timeout in 7 papers aux_func/aux_func.py ran no licence file found · pointer only · f8a4de0b6faeff3a · report fixture: signature func:callable/0/?, args:tuple/1/int, kwargs:dict/0/?, timeout:int/0/int · returned int · level recorded 2026-09-24
call_chat_gpt backbone/gpt.py unverified no licence file found · pointer only · 96896b883b68a043 · report
execute_basic aux_func/aux_func.py unverified no licence file found · pointer only · 8b1dcbddb6017e53 · report
load_backbone in 6 papers model/get_model.py unverified no licence file found · pointer only · 6c4aba17c8429917 · report
num_tokens_from_messages in 14 papers backbone/gpt.py unverified no licence file found · pointer only · f17d8dea2f3b9842 · report
resume_result_jsonl pipelines.py unverified no licence file found · pointer only · 996a26fe0469527e · report

Tasks

Language ModelingLanguage ModellingLarge Language Modelmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections