paper-with-me

홈 › Papers

An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning

2026-05-10 · Yikun Li, Jinfeng Jiang, Ting Zhang, Chengran Yang, Chenxing Zhong, Yin Yide, Leow Wen Bin, Eng Lieh Ouh, Lwin Khin Shar, David Lo arxiv

Evaluating whether large language models (LLMs) can recover execution-relevant program structure, rather than only produce code that passes tests, remains an open problem. Existing code benchmarks emphasize test-passing outputs, from standalone programming tasks (HumanEval, MBPP, LiveCodeBench) to repository repair (SWE-Bench); this is useful, but offers limited diagnostic signal about which program semantics a model can recover from source. We introduce TraceEval, to our knowledge the first execution-verified, multi-language benchmark for code semantic reasoning: recovering a program's runtime call structure from source code. Unlike prior call-graph benchmarks that rely on static-tool output or hand-annotated ground truth, every positive edge in TraceEval is mechanically witnessed by validation execution, eliminating annotator disagreement and label noise for observed behavior. TraceEval consists of (i) 10,583 real-world programs (2,129 test, 8,454 train) extracted from 1,600+ open-source repositories across Python, JavaScript, and Java via an LLM-assisted harness-generation pipeline with tracer validation; and (ii) a reproducible pipeline that converts any open-source repository into new verified benchmark instances. We evaluate 10 LLMs at zero-shot on the held-out test split. The strongest model, Claude-Opus-4.6, reaches an average F1 of 72.9% across the three languages. To demonstrate the train split's utility as a supervision substrate, we fine-tune the Qwen2.5-Coder family on it: lifts of up to +55.6 F1 bring tuned Qwen2.5-Coder-32B to 71.2%, within 1.7 F1 of zero-shot Claude-Opus-4.6. We release the benchmark, pipeline, baselines, and a datasheet at https://github.com/yikun-li/TraceEva

📄 PDF Abstract BibTeX arXiv:2605.11006

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AutoCoder: Enhancing Code Large Language Model with \textsc{AIEV-Instruct}

2024-05-23 · Bin Lei, Yuchen Li, Qiuwu Chen

We introduce AutoCoder, the first Large Language Model to surpass GPT-4 Turbo (April 2024) and GPT-4o in pass@1 on the Human Eval benchmark test ($\mathbf{90.9\%}$ vs. $\mathbf{90.2\%}$). In addition, AutoCoder offers a …

Class-level Code GenerationCode CompletionCode GenerationCode Repair+8

ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval

2026-09-01 · Aaryan Kapoor, Md Abdullah Al Hafiz Khan hf

Embedding-based code retrieval is a core component of coding agents and retrieval-augmented code generation, where retrieving correct code matters more than retrieving lexically similar code. Existing code-retrieval benc…

Code Generation

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models

2026-05-09 · Yuanhao Li, Hongbo Wang, Xiaotang Shang, Xunzhu Tang 외 arxiv

Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We present BoostAPR, a three-stage framework addressing the…

Reinforcement LearningProgram Repair

PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation

2026-07-02 · Junhao Chen, Xiang Li, Mingjin Chen, Boran Zhang 외 arxiv

Code is the medium through which large language models generate structured artifacts: charts, scientific figures, vector graphics, CAD models, 3D scenes, and hardware designs are all produced by writing programs. In this…

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

2026-04-02 · Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg arxiv

We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight frontier LLMs. Our pipeline replaces resource-heavy dependencies with an evolutionar…