Papers › QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?

QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?

28 Mar 2025arXiv:2503.22674archive 2025-07-28

Belinda Z. Li, Been Kim, Zi Wang

Recently, a large amount of work has focused on improving large language models' (LLMs') performance on reasoning benchmarks such as math and logic. However, past work has largely assumed that tasks are well-defined. In the real world, queries to LLMs are often underspecified, only solvable through acquiring missing information. We formalize this as a constraint satisfaction problem (CSP) with missing variable assignments. Using a special case of this formalism where only one necessary variable assignment is missing, we can rigorously evaluate an LLM's ability to identify the minimal necessary question to ask and quantify axes of difficulty levels for each problem. We present QuestBench, a set of underspecified reasoning tasks solvable by asking at most one question, which includes: (1) Logic-Q: Logical reasoning tasks with one missing proposition, (2) Planning-Q: PDDL planning problems with initial states that are partially-observed, (3) GSM-Q: Human-annotated grade school math problems with one missing variable assignment, and (4) GSME-Q: a version of GSM-Q where word problems are translated into equations by human annotators. The LLM is tasked with selecting the correct clarification question(s) from a list of options. While state-of-the-art models excel at GSM-Q and GSME-Q, their accuracy is only 40-50% on Logic-Q and Planning-Q. Analysis demonstrates that the ability to solve well-specified reasoning problems may not be sufficient for success on our benchmark: models have difficulty identifying the right question to ask, even when they can solve the fully specified version of the problem. Furthermore, in the Planning-Q domain, LLMs tend not to hedge, even when explicitly presented with the option to predict ``not sure.'' This highlights the need for deeper investigation into models' information acquisition capabilities.

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 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 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: 12 samples from 1 repository, 11 ran (11 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 between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-deepmind/questbench officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 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.

11ran
1unverified

Licence: 0 of the 12 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 google-deepmind/questbench. “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.

google-deepmind/questbench official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
check_satisfies_constraints Planning/backtrace_utils.py ran Apache-2.0 (permissive) · 5aaad1d50295832c · report fixture: signature domain:str/0/str, facts:set/0/?, constraints:dict/0/? · returned bool · level recorded 2026-09-25
check_self_consistency Planning/backtrace_utils.py ran Apache-2.0 (permissive) · 950be6a18b37b85e · report fixture: signature domain:str/0/str, facts:set/0/?, contradicting_fact_pairs:set/0/? · returned bool · level recorded 2026-09-24
jsonify_prompt model_utils.py ran fingerprinted Apache-2.0 (permissive) · 938eefb6de7c1539 · report fixture: signature prompt:str/0/str · returned str · level recorded 2026-09-24
load_cache_file model_utils.py ran fingerprinted Apache-2.0 (permissive) · 08f538194a1bc5fa · report fixture: signature cache_file:str/0/str · returned dict · level recorded 2026-09-25
load_data in 700 papers SimpleLogic/ruleset.py ran fingerprinted Apache-2.0 (permissive) · dd14497bd4b9e103 · report fixture: signature sl_dir:str/0/str · returned tuple · level recorded 2026-09-24
make_constraints Planning/make_heldout_states.py ran Apache-2.0 (permissive) · 8d6a2e3dfcad9e26 · report fixture: signature problem_spec:dict/0/? · returned dict · level recorded 2026-09-24
make_heldout_states Planning/make_heldout_states.py ran Apache-2.0 (permissive) · 21b990e2c7f2ae64 · report fixture: signature conditions_to_path:dict/0/? · returned tuple · level recorded 2026-09-25
make_impossible_and_contradicting_facts Planning/make_heldout_states.py ran Apache-2.0 (permissive) · 2b52415e972eca31 · report fixture: signature domain:str/0/str, problem_spec:dict/0/? · returned tuple · level recorded 2026-09-25
negate SimpleLogic/ruleset.py ran fingerprinted Apache-2.0 (permissive) · f1184021116c0ed9 · report fixture: signature word:str/0/str · returned str · level recorded 2026-09-25
powerset in 23 papers Planning/backtrace_utils.py ran Apache-2.0 (permissive) · e661cb08acaf5994 · report fixture: signature iterable:list/1/int · returned chain · level recorded 2026-09-24
union in 11 papers SimpleLogic/derivation.py ran Apache-2.0 (permissive) · fe2be5fdd1352cb9 · report fixture: signature all_dicts:list/1/dict · returned dict · level recorded 2026-09-24
openai_request model_utils.py unverified Apache-2.0 (permissive) · 6f3d7c5896fdf158 · report

Tasks

Logical ReasoningMath

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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