Papers › StateAct: State Tracking and Reasoning for Acting and Planning with Large Language Models

StateAct: State Tracking and Reasoning for Acting and Planning with Large Language Models

21 Sep 2024arXiv:2410.02810archive 2025-07-28

Nikolai Rozanov, Marek Rei

Planning and acting to solve `real' tasks using large language models (LLMs) in interactive environments has become a new frontier for AI methods. While recent advances allowed LLMs to interact with online tools, solve robotics tasks and many more, long range reasoning tasks remain a problem for LLMs. Existing methods to address this issue are very resource intensive and require additional data or human crafted rules, instead, we propose a simple method based on few-shot in-context learning alone to enhance `chain-of-thought' with state-tracking for planning and acting with LLMs. We show that our method establishes the new state-of-the-art on Alfworld for in-context learning methods (+14% over the previous best few-shot in-context learning method) and performs on par with methods that use additional training data and additional tools such as code-execution. We also demonstrate that our enhanced `chain-of-states' allows the agent to both solve longer horizon problems and to be more efficient in number of steps required to solve a task. We show that our method works across a variety of LLMs for both API-based and open source ones. Finally, we also conduct ablation studies and show that `chain-of-thoughts' helps state-tracking accuracy, while a json-structure harms overall performance. We open-source our code and annotations at https://github.com/ai-nikolai/StateAct.

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 19 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, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 7 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: 19 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ai-nikolai/stateact officialmentioned in papermentioned on GitHubSyntology: 19 samples, 12 ran (6 instrument-failed) · 7 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

19 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 7 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.

6ran · our draft was wrong
6ran
7unverified

Licence: 19 of the 19 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 ai-nikolai/stateact. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ai-nikolai/stateact official repository 19 samples, 12 ran (6 instrument-failed) · 7 unverified
extract_command_and_format alfworld_runs/alfworld_react_prompt_utils.py ran no licence file found · pointer only · 2ab8b87e8d7a5b77 · report fixture: signature command:str/0/str, version:int/0/int, think_key:str/0/str, action_key:str/0/str · returned tuple · level recorded 2026-09-24
general_action_cleaning alfworld_runs/alfworld_run.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 6077500f2a5fe7bb · report fixture: signature action:str/0/str · returned str · level recorded 2026-09-24
get_env_type alfworld_runs/alfworld_run.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 615dc37d09ed8ef9 · report fixture: signature env_name:str/0/str · returned str · level recorded 2026-09-24
parse_expression textcraft_runs/run_textcraft_adapt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · bee05b7b2b0ae815 · report fixture: signature expression:str/0/str · returned dict · level recorded 2026-09-22
parse_results webshop_runs/transform.py ran · our draft was wrong no licence file found · pointer only · df43aebbc0d02eb2 · report fixture: signature text:str/0/str · returned tuple · level recorded 2026-09-24
phi in 30 papers
census: 8 implementations from 8 papers, 8 distinct outputs across 5 buckets, one shared input per bucket
textcraft_runs/run_textcraft_thread.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9eae20ece0fa12fe · report fixture: signature parent_token_sequ:str/0/str · returned str · level recorded 2026-09-24
plan_to_args textcraft_runs/run_textcraft_adapt.py ran fingerprinted no licence file found · pointer only · 163b27b8444b232b · report fixture: signature plan:str/0/str, keyword:str/0/str, lkey:str/0/str · returned dict · level recorded 2026-09-24
psi in 8 papers textcraft_runs/run_textcraft_thread.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 142de1580a8559de · report fixture: signature token_sequ:str/0/str · returned str · level recorded 2026-09-24
remove_keys alfworld_runs/alfworld_ablation_generator.py ran no licence file found · pointer only · 2757e9521faf9ae2 · report fixture: signature base_prompt:list/1/str, keys_to_remove:list/1/str · returned list · level recorded 2026-09-24
transform_baseprompt_into_jsonstate_string alfworld_runs/alfworld_ablation_generator.py ran no licence file found · pointer only · 2a292e9393408367 · report fixture: signature base_prompt:list/1/str, system_prefix:str/0/str, agent_prefix:str/0/str · returned str · level recorded 2026-09-24
transform_baseprompt_into_stringstate_string alfworld_runs/alfworld_ablation_generator.py ran no licence file found · pointer only · 19fd321d955bf1c7 · report fixture: signature base_prompt:list/1/str, system_prefix:str/0/str, agent_prefix:str/0/str · returned str · level recorded 2026-09-24
transform_put_action alfworld_runs/alfworld_run.py ran no licence file found · pointer only · 5ac406ca03d4dcc5 · report fixture: signature action:str/0/str, transform_to_move_syntax:bool/0/bool · returned tuple · level recorded 2026-09-24
llm in 7 papers textcraft_runs/run_textcraft_adapt.py unverified no licence file found · pointer only · 0b9398a05fe8427e · report
llm in 7 papers webshop_runs/run_webshop_adapted.py unverified no licence file found · pointer only · fa6aecfd93116153 · report
llm_chat webshop_runs/run_webshop_adapted.py unverified no licence file found · pointer only · fa828596043c1e90 · report
llm_tropic webshop_runs/run_webshop_adapted.py unverified no licence file found · pointer only · 8377ace36b15d7c1 · report
load_results in 82 papers alfworld_runs/get_score.py unverified no licence file found · pointer only · c67ce7ef9daabda8 · report
return_json_react_examples alfworld_runs/alfworld_react_prompt_utils.py unverified no licence file found · pointer only · 2173d108b18e06c8 · report
return_react_examples alfworld_runs/alfworld_react_prompt_utils.py unverified no licence file found · pointer only · 8515d68e79091391 · report

Tasks

In-Context Learning

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