MBPP

Dataset Card for Mostly Basic Python Problems (mbpp) Dataset Summary The benchmark consists of around 1,000 crowd-sourced Python programming problems, designed to be solvable by entry level programmers, covering programming fundamentals, standard library functionality, and so on. Each problem consists of a task descrip

Papers using MBPP (15)

SePO: Self-Evolving Prompt Agent for System Prompt Optimization2026Evoagentx: An Automated Framework For Evolving Agentic Workflows2025 · 1 citesAutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation2026Poison with Style: A Practical Poisoning Attack on Code Large Language Models2026SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing2026Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents2026TDPGen: Optimizing Agentic Code Generation via Test-Driven Planning and Hierarchical ReAct2026ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization2026Think Anywhere in Code Generation2026Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval2026Adaptive Confidence Gating In Multi-agent Collaboration For Efficient And Optimized Code Generation2026From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs2025Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning2024 · 9 citesDivide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation2024 · 1 citesFALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization system2024