SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.00215 · 2024

HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent

Fatemeh Fard, Wu, J Jie

arXiv · PDF · Open in the Atlas

Code that ran

12 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 9 failures of our instrument; 7 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.00215.json · badge: /api/ran/2406.00215.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
jie-jw-wu/human-eval-comm canonical (classifier label)
classifier basis: census
12 ran · 7 no recorded run
FunctionStatusWhere it lives
extract_prefix Ran
ran; our contract draft was wrong, not the code
jie-jw-wu/human-eval-comm/measurement_summary_draw_heatmap.py
pointer only (licence: NONE) · get_code("0bf323d93f03b832")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_text Ran
ran; our contract draft was wrong, not the code
jie-jw-wu/human-eval-comm/generate_response.py
pointer only (licence: NONE) · get_code("7f8144a905f5b101")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_ask_question_rate Ran
ran, honoured the contract we drafted
jie-jw-wu/human-eval-comm/syntactic_similarity_OER.py
pointer only (licence: NONE) · get_code("5dba7da2cfd89116")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_ask_question_rate_with_qq Ran
ran, honoured the contract we drafted
jie-jw-wu/human-eval-comm/syntactic_similarity_OER.py
pointer only (licence: NONE) · get_code("b088fc0024baa28f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

preprocess_data Ran
ran; our contract draft was wrong, not the code
jie-jw-wu/human-eval-comm/AgentFramework/designer.py
pointer only (licence: NONE) · get_code("491a124a37148dfd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

preprocess_data Ran
ran; our contract draft was wrong, not the code
jie-jw-wu/human-eval-comm/AgentFramework/executor.py
pointer only (licence: NONE) · get_code("b231819920453b1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

preprocess_data Ran
ran; our contract draft was wrong, not the code
jie-jw-wu/human-eval-comm/AgentFramework/programmer.py
pointer only (licence: NONE) · get_code("854e64377cfc300a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

programmer_main Ran
ran on a synthesized input
jie-jw-wu/human-eval-comm/AgentFramework/programmer.py
pointer only (licence: NONE) · get_code("2e3b2a31d4b30e77")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ratio_of_worst Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jie-jw-wu/human-eval-comm/measurement_summary_draw_heatmap.py
pointer only (licence: NONE) · get_code("3a8a940a00b74328")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

response_2_code Ran
ran; our contract draft was wrong, not the code
jie-jw-wu/human-eval-comm/intermedia_analyze.py
pointer only (licence: NONE) · get_code("ed2c1ad3bc24cdc8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

solution_evaluation Ran
ran; our contract draft was wrong, not the code
jie-jw-wu/human-eval-comm/intermedia_analyze.py
pointer only (licence: NONE) · get_code("44d500098cd18911")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

solution_evaluation_HumanEval Ran
ran; our contract draft was wrong, not the code
jie-jw-wu/human-eval-comm/intermedia_analyze.py
pointer only (licence: NONE) · get_code("cd60fe0a3a7d62ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

analyze_among_top0_5 Not yet run
unverified (harvested, no recorded run)
jie-jw-wu/human-eval-comm/syntactic_similarity_OER.py
pointer only (licence: NONE) · get_code("509467404a76b343")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

designer_main Not yet run
unverified (harvested, no recorded run)
jie-jw-wu/human-eval-comm/AgentFramework/designer.py
pointer only (licence: NONE) · get_code("310e25d69d224637")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

fetch_completion Not yet run
unverified (harvested, no recorded run)
jie-jw-wu/human-eval-comm/AgentFramework/designer.py
pointer only (licence: NONE) · get_code("c8ae809824048769")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

fetch_completion Not yet run
unverified (harvested, no recorded run)
jie-jw-wu/human-eval-comm/AgentFramework/programmer.py
pointer only (licence: NONE) · get_code("19a9b628e7fcf1e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_completion_starchat_nl_to_pl Not yet run
unverified (harvested, no recorded run)
jie-jw-wu/human-eval-comm/generate_response.py
pointer only (licence: NONE) · get_code("e5fc7b939577a999")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_completion_starchat_pl_to_nl Not yet run
unverified (harvested, no recorded run)
jie-jw-wu/human-eval-comm/generate_response.py
pointer only (licence: NONE) · get_code("1fcf5236ce19bc6e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

semantic_syntactic_structural_similarity Not yet run
unverified (harvested, no recorded run)
jie-jw-wu/human-eval-comm/measurement_summary_draw_heatmap.py
pointer only (licence: NONE) · get_code("5eef0e3253e15ffa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jie-jw-wu/human-eval-comm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 19 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) have significantly improved their ability to perform tasks in the field of code generation. However, there is still a gap between LLMs being capable coders and being top-tier software engineers. The most recent trend is using LLM-based agents to iterate the code generation process. Based on the observation that top-level software engineers often ask clarifying questions to reduce Ambiguity in both requirements and coding solutions, we argue that the same should be applied to LLMs for code generation tasks. For this purpose, we define the communication skills of LLMs as "being able to ask clarifying questions when the description of the code generation problem has issues". In this study, we restrict these issues to three matters from the software requirement engineering field: inconsistent requirements, ambiguous requirements, and incomplete requirements. By asking probing questions about the requirements of problem descriptions before generating the final code, the challenges of programming with LLMs, such as unclear intent specification may be alleviated, resulting to a correct code in the initial iterations. In this work, we conducted an empirical study on the benchmark and analysis of the communication skills of LLMs for code generation. We created a new benchmark, HumanEvalComm, by modifying problem descriptions according to three issues mentioned above, Inconsistency, Ambiguity, Incompleteness. We then experimented on HumanEvalComm with different Code LLMs, and a new LLM agent approach, Code Clarification and Generation Agent (Okanagan), to identify and ask questions in ambiguous parts from code and descriptions for further refining the generated code. In the evaluation, we introduced an LLM-based evaluator and created Communication Rate and Good Question Rate as the evaluation metrics to represent the ratio of questions asked and questions with good quality in responses. We found that more than 60% of responses from Code LLMs still generate code rather than ask questions when the problem descriptions are manually modified according to different clarification categories. The Pass@1 and Test Pass Rate of most Code LLMs drop by 35% ∼ 52% and by 17% ∼ 35% respectively, with statistical significance in each category for over 75% numbers. Okanagan, as an LLM agent approach that uses LLM such as ChatGPT 3.5, effectively increases the Communication Rate and Good Question Rate by an absolute 58% and 38%, respectively. Thus, Okanagan boosts Pass@1 and Test Pass Rate by an absolute 8% and 7%, respectively, when the problem descriptions are modified based on given clarification categories. This result indicates the potential for achieving more effective communication capability using LLM agent. Our benchmark and full code are publicly available at https://github.com/jie-jw-wu/human-eval-comm. "Asking a good question can be valuable in and of itself, irrespective of the answer. It communicates your respect for the other person. " -Adapted from the Iowa Peace Institute Message This article is published in ACM Transactions on Software Engineering and Methodology (TOSEM).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.00215")
get_code_for_paper("2406.00215")
have("2406.00215")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.00215.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.00215.svg)](https://syntology.ai/paper/2406.00215)

Connect an agent — have() is free.