Papers › NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls

NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls

4 Sep 2024arXiv:2409.03797archive 2025-07-28

Kinjal Basu, Ibrahim Abdelaziz, Kiran Kate, Mayank Agarwal, Maxwell Crouse, Yara Rizk, Kelsey Bradford, Asim Munawar, Sadhana Kumaravel, Saurabh Goyal, Xin Wang, Luis A. Lastras, Pavan Kapanipathi

The resurgence of autonomous agents built using large language models (LLMs) to solve complex real-world tasks has brought increased focus on LLMs' fundamental ability of tool or function calling. At the core of these agents, an LLM must plan, execute, and respond using external tools, APIs, and custom functions. Research on tool calling has gathered momentum, but evaluation benchmarks and datasets representing the complexity of the tasks have lagged behind. In this work, we focus on one such complexity, nested sequencing, with the goal of extending existing benchmarks and evaluation. Specifically, we present NESTFUL, a benchmark to evaluate LLMs on nested sequences of API calls, i.e., sequences where the output of one API call is passed as input to a subsequent call. NESTFUL contains 1800+ nested sequences where all the function calls are executable. Experimental results on a variety of models show that the best-performing model (GPT-4o) achieves a full sequence match accuracy of 28% and a win-rate of 60%, necessitating a large scope for improvement in the nested sequencing aspect of function calling. Our analysis of these results provides possible future research directions for the community, in addition to a benchmark to track progress. We have released the NESTFUL dataset under the Apache 2.0 license at https://github.com/IBM/NESTFUL.

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 21 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 7 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 4 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: 21 samples from 1 repository, 17 ran (11 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.

ibm/nestful officialmentioned in papermentioned on GitHubApache-2.0Syntology: 21 samples, 17 ran (6 instrument-failed) · 4 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

21 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 7 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 4 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.

7ran · honoured contract
6ran · our draft was wrong
4ran
4unverified

Licence: 0 of the 21 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 ibm/nestful. “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.

ibm/nestful official repository 21 samples, 17 ran (6 instrument-failed) · 4 unverified
ast_parse src/ast_utils.py ran Apache-2.0 (permissive) · 9c6d8f0b3847114f · report fixture: signature input_str:str/0/str, language:str/0/str · returned list · level recorded 2026-09-24
create_service_account data_v2/executable_functions/py_code_file_1001.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ce18037f4b6348c6 · report fixture: signature company_name:str/0/str · returned str · level recorded 2026-09-24
do_stuff data_v2/executable_functions/py_code_file_1002.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 153e1cc7a8f8d341 · report fixture: signature x:int/0/int, y:float/0/float · returned float · level recorded 2026-09-24
extend_num data_v2/executable_functions/py_code_file_100.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 31c2e27c79774797 · report fixture: signature num1:int/0/int, num2:int/0/int · returned int · level recorded 2026-09-24
find_strings_with_pattern data_v2/executable_functions/py_code_file_1.py ran · honoured contract Apache-2.0 (permissive) · 47cc520d6946b782 · report fixture: signature string_list:list/1/str, pattern:str/0/str · returned list · level recorded 2026-09-24
format_padding data_v2/executable_functions/py_code_file_10.py ran fingerprinted Apache-2.0 (permissive) · fb5af146b3521b50 · report fixture: signature string:str/0/str, padding_length:int/0/int, padding_char:str/0/str · returned str · level recorded 2026-09-24
get_deli_sep_str_list src/output_parsers.py ran fingerprinted Apache-2.0 (permissive) · a58b18082fe1da3f · report fixture: signature text:str/0/str, deli:str/0/str · returned list · level recorded 2026-09-24
get_icl_str src/instruct_data_prep.py ran Apache-2.0 (permissive) · 48207fba685d16d6 · report fixture: signature icl_examples:list/1/dict, model_name:str/0/str · returned str · level recorded 2026-09-24
listit src/scorer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · f0a4f5a7f292a3d0 · report fixture: signature t:list/1/int · returned list · level recorded 2026-09-24
permutation data_v2/executable_functions/basic_functions.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · b524a104e61bdc60 · report fixture: signature n:int/0/int, r:int/0/int · returned int · level recorded 2026-09-24
power in 16 papers data_v2/executable_functions/basic_functions.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 29da7d03953ecf87 · report fixture: signature base:int/0/int, exponent:int/0/int · returned int · level recorded 2026-09-24
process_slot_value src/output_parsers.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cd5994aa5f8341d1 · report fixture: signature slot_value:str/0/str · returned str · level recorded 2026-09-24
read_file in 112 papers src/utils.py ran · our draft was wrong Apache-2.0 (permissive) · ba6cfefa8094dcb6 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-24
resolve_ast_by_type src/ast_utils.py ran · honoured contract Apache-2.0 (permissive) · cc91f822de63292f · report fixture: signature value:Constant/0/? · returned int · level recorded 2026-09-24
resolve_ast_call src/ast_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 053e58f476c2e09c · report fixture: signature elem:Call/0/? · returned dict · level recorded 2026-09-24
simplify_slug data_v2/executable_functions/py_code_file_1000.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 662385c90863ea91 · report fixture: signature slug:str/0/str · returned str · level recorded 2026-09-24
subtract in 5 papers data_v2/executable_functions/basic_functions.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 7f2f2e2df15e6716 · report fixture: signature arg_0:int/0/int, arg_1:int/0/int · returned int · level recorded 2026-09-24
calculate_ans src/scorer.py unverified Apache-2.0 (permissive) · f5b3c135f40d531c · report
get_basic_func_list src/scorer.py unverified Apache-2.0 (permissive) · c9fb850a9577a4d4 · report
get_granite_tokenizer src/instruct_data_prep.py unverified Apache-2.0 (permissive) · 63f870a98c11420f · report
granite_3_1_prompt_input src/instruct_data_prep.py unverified Apache-2.0 (permissive) · 0d5485e114c8ba34 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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