Papers Code Repair
“Code Repair” 태그가 달린 논문 70편 · 필터 해제
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge di…
Reinforcement LearningCode RepairDiffPDE: Masked Diffusion Language Models as PDE Solver
Existing approaches for synthesizing Partial Differential Equation (PDE) solvers predominantly rely on autoregressive models, yet their global left-to-right decoding incurs substantial redundancy when addressing inherent…
Reinforcement LearningCode RepairOne Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows
Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Yet completing consequential work beyond code requires more than prod…
Code RepairHELIX: Model-Harness Co-evolution for Recursive Self-Improvement
Scaling agent capability has largely focused on improving the model, yet an interactive agent acts through a runtime harness that mediates context, tools, control flow, and stopping. The harness shapes both what a model …
Code RepairAnchored Self-Play for Code Repair
Code repair is an important capability for language models (LMs): given a buggy program and unit tests, an LM must produce a fixed program that passes the tests. Because code repair data is limited, we aim to scale super…
Reinforcement LearningCode RepairEvidence-Driven LLM Agent for C-to-Synthesizable-C Conversion and Verification
Software-compilable C programs routinely fail to complete the four-stage pipeline of a high-level synthesis (HLS) toolchain -- compilation, C simulation (CSim), synthesis, and C/RTL co-simulation (CoSim) -- because HLS a…
Code RepairSHERLOC: Structured Diagnostic Localization for Code Repair Agents
LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated localization frameworks have emerged, yet are still evaluated as file…
Code RepairVeriPilot: An LLM-Powered Verilog Debugging Framework
Verilog debugging remains one of the most time-consuming stages in digital circuit design. Recent advances in Large Language Models (LLMs) have enabled automated debugging; however, most existing approaches rely solely o…
Code RepairGRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science
We introduce GRACE-DS, a Guarded Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agents. GRACE-DS is a set of evaluation metrics in an isolated environment t…
Feature EngineeringCode RepairBeyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored. In this work, we introduce UOJ-Bench, a benchma…
Code GenerationCode RepairMPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation
Repository-level benchmarks for evaluating Large Language Model (LLM) code repair on Secure Multi-Party Computation (MPC) software do not yet exist, and directly transplanting general-purpose benchmarks such as SWE-bench…
Code RepairLearning Explicit Behavioral Models with Adaptive Questions and World-Model Probes
Interactive agents trained only against task return can achieve high scores while failing to represent the mechanisms that make their actions succeed. This makes brittle behavior difficult to diagnose and limits adaptati…
Question AnsweringCode RepairPatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments
World models for interactive text agents must typically be learned from observation-action trajectories alone. Specifically, the environment returns text observations after each action, but does not expose a ground-truth…
Code RepairThe Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, new intervention-distinguishable failure modes can appear without bound…
Code RepairFaithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer sho…
Code RepairGenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design
Genetic circuit design remains a laborious, expert-driven process despite decades of progress in synthetic biology. We study this problem through code generation: models produce Python code in pysbol3 to construct geneti…
Reinforcement LearningCode GenerationCode RepairSignal Reshaping for GRPO in Weak-Feedback Agentic Code Repair
Code-agent RL often receives weak feedback: rollout-time signals are reliable and executable, but capture only necessary or surface conditions for task success rather than the target semantic predicate. Using agentic com…
Code RepairAutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation
Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experiments execute correctly or whether cited sources support ge…
Code RepairBias in the Loop: Auditing LLM-as-a-Judge for Software Engineering
Large Language Models are increasingly used as judges to evaluate code artifacts when exhaustive human review or executable test coverage is unavailable. LLM-judge is increasingly relevant in agentic software engineering…
Code GenerationCode RepairQiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing, where excessive modifications overwrite correct code and hinder bug localization. We systematically quantify its …
Program RepairCode Repair