Papers › Agent Instructs Large Language Models to be General Zero-Shot Reasoners

Agent Instructs Large Language Models to be General Zero-Shot Reasoners

5 Oct 2023arXiv:2310.03710archive 2025-07-28

Nicholas Crispino, Kyle Montgomery, Fankun Zeng, Dawn Song, Chenguang Wang

We introduce a method to improve the zero-shot reasoning abilities of large language models on general language understanding tasks. Specifically, we build an autonomous agent to instruct the reasoning process of large language models. We show this approach further unleashes the zero-shot reasoning abilities of large language models to more tasks. We study the performance of our method on a wide set of datasets spanning generation, classification, and reasoning. We show that our method generalizes to most tasks and obtains state-of-the-art zero-shot performance on 20 of the 29 datasets that we evaluate. For instance, our method boosts the performance of state-of-the-art large language models by a large margin, including Vicuna-13b (13.3%), Llama-2-70b-chat (23.2%), and GPT-3.5 Turbo (17.0%). Compared to zero-shot chain of thought, our improvement in reasoning is striking, with an average increase of 10.5%. With our method, Llama-2-70b-chat outperforms zero-shot GPT-3.5 Turbo by 10.2%.

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 10 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 9 ran (9 with no instrument failure; 0 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.

wang-research-lab/agentinstruct officialmentioned in papermentioned on GitHubApache-2.0Syntology: 10 samples, 9 ran (0 instrument-failed) · 1 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

10 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
1unverified

Licence: 0 of the 10 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 wang-research-lab/agentinstruct. “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.

wang-research-lab/agentinstruct official repository 10 samples, 9 ran (0 instrument-failed) · 1 unverified
format_instructions src/agentinstruct/reasoning/helm_updates/src/helm/benchmark/run_specs.py ran fingerprinted Apache-2.0 (permissive) · b8502db7194d7cfe · report fixture: signature instructions:str/0/str · returned str · level recorded 2026-09-24
get_dataset_phrase src/agentinstruct/agent/utils/dataset_preprocessing.py ran fingerprinted Apache-2.0 (permissive) · fd276022adc1ad3b · report fixture: signature dataset_name:str/0/str · returned str · level recorded 2026-09-24
get_float src/agentinstruct/reasoning/serve/custom_handler/llama-2-13b-chat-handler.py ran Apache-2.0 (permissive) · 26f037502faf788d · report fixture: signature input_:str/0/str, default:float/0/float · returned float · level recorded 2026-09-24
get_int in 6 papers src/agentinstruct/reasoning/serve/custom_handler/llama-2-13b-chat-handler.py ran fingerprinted Apache-2.0 (permissive) · 283c64914efa0e6f · report fixture: signature input_:str/0/str, default:int/0/int · returned int · level recorded 2026-09-24
get_links src/agentinstruct/agent/agent_instr_generation.py ran Apache-2.0 (permissive) · 59ed242ba642876f · report fixture: signature search_metadata:list/1/dict · returned list · level recorded 2026-09-24
letter_eval src/agentinstruct/eval/letter_eval.py ran Apache-2.0 (permissive) · a7687052123da6b0 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-24
parse_helm_name src/agentinstruct/reasoning/helm_updates/src/helm/benchmark/run_expander.py ran fingerprinted Apache-2.0 (permissive) · bbd4f51304c18a78 · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-24
post_processing_text src/agentinstruct/reasoning/serve/custom_handler/llama-2-13b-chat-handler.py ran Apache-2.0 (permissive) · e1a3a72ca5c64a6a · report fixture: signature output_text:str/0/str, stop_tokens:list/1/str, denylist:list/1/str · returned str · level recorded 2026-09-24
read_scenario_state src/agentinstruct/agent/utils/dataset_preprocessing.py ran Apache-2.0 (permissive) · 4eb9af73c57c297b · report fixture: signature scenario_state_path:str/0/str · returned tuple · level recorded 2026-09-24
truncate_instances src/agentinstruct/agent/utils/dataset_preprocessing.py unverified Apache-2.0 (permissive) · 2ba15317bdf1e40f · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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