Pith. sign in

REVIEW 7 cited by

HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.21199 v2 pith:LZBA242B submitted 2024-12-30 cs.SE cs.CL

HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation

classification cs.SE cs.CL
keywords codegenerationself-invokinghumanevalllmsbenchmarksmodelsbase
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They must solve the base problem and then utilize its solution to address the more complex one. This work features three key contributions. First, we propose a general recipe for generating more challenging versions of existing benchmarks, resulting in three new benchmarks: HumanEval Pro, MBPP Pro, and BigCodeBench-Lite Pro, specifically designed to assess LLMs on self-invoking code generation. Second, from the analysis of experimental results over twenty LLMs on our benchmarks, we have two important observations: (i) Most LLMs excel in traditional code generation benchmarks like HumanEval and MBPP, but their performance declines on self-invoking tasks. For example, o1-mini achieves 96.2% pass@1 on HumanEval but only 76.2% on HumanEval Pro. (ii) On self-invoking code generation task, the instruction-tuned models demonstrate only marginal improvements compared to the base models. Third, we disclose the types of failure modes that exist in our evaluation results. All these results underscore the need for further advancements in self-invoking code generation tasks and provide a new direction for future research on enhancing LLMs' code reasoning capabilities.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions

    cs.AI 2026-04 unverdicted novelty 7.0

    Intent2Tx shows that LLMs often generate syntactically valid but functionally incorrect Ethereum transactions, especially on multi-step and out-of-distribution intents, despite gains from scaling and retrieval augmentation.

  2. ACPO: Adaptive Credit Policy Optimization via Fine-Grained Surrogate Entropy

    cs.LG 2026-07 conditional novelty 6.0

    Mode-local surrogate entropy asymmetrically reweights token advantages in RLVR, improving LLM math and code reasoning over SAPO, DAPO, and GTPO.

  3. SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution

    cs.LG 2026-05 unverdicted novelty 6.0

    SWE Atlas is a benchmark suite for coding agents that evaluates Codebase Q&A, Test Writing, and Refactoring using comprehensive protocols assessing both functional correctness and software engineering quality.

  4. Agentic Frameworks for Reasoning Tasks: An Empirical Study

    cs.AI 2026-04 unverdicted novelty 6.0

    An empirical evaluation of 22 agentic frameworks on BBH, GSM8K, and ARC benchmarks shows stable performance in 12 frameworks but highlights orchestration failures and weaker mathematical reasoning.

  5. CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models

    cs.SE 2026-05 unverdicted novelty 5.0

    CodeGolf Bench is a dynamic benchmark for LLM concise code generation in 60 languages, showing reasoning models reach 70.97% average human percentile on Python and C++ tasks while non-reasoning models lag.

  6. A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback

    cs.SE 2026-05 unverdicted novelty 5.0

    A-ProS uses a hybrid multi-model feedback framework with stateful refinement to improve success rates on competitive programming problems, achieving over 2x gains compared to baseline agent loops.

  7. LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review

    cs.SE 2026-02 unverdicted novelty 3.0

    A review of 114 studies classifies motivations into nine categories, analyzes common models and benchmarks, synthesizes challenges into six categories with 26 subcategories and solutions, and identifies six future res...