LLM-based merge conflict resolution performs well on imbalanced conflicts but struggles with large or non-English inputs, while search-based methods show better generalization and strength on balanced conflicts.
Yue Wang, Weishi Wang, Shafiq Joty, and Steven C
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.SE 4representative citing papers
AgenticFlict is a public dataset of 29K+ textual merge conflicts from AI agent PRs, collected via merge simulation on 107K processed PRs and showing a 27.67% conflict rate with variation across agents.
Frontier LLMs like GPT-5.2 show large accuracy drops on perturbed program-output prediction tasks while open-source reasoning models remain more stable, exposing limits in code semantics understanding.
APIKG4Syn synthesizes API-oriented training data via knowledge graphs and Monte Carlo search to fine-tune a 7B model that reaches 25% pass@1 on HarmonyOS code generation, beating untuned GPT-4o at 17.59%.
citing papers explorer
-
LLM-based vs. Search-based Merge Conflict Resolution: An Empirical Study of Competing Paradigms
LLM-based merge conflict resolution performs well on imbalanced conflicts but struggles with large or non-English inputs, while search-based methods show better generalization and strength on balanced conflicts.
-
AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub
AgenticFlict is a public dataset of 29K+ textual merge conflicts from AI agent PRs, collected via merge simulation on 107K processed PRs and showing a 27.67% conflict rate with variation across agents.
-
How Robustly do LLMs Understand Execution Semantics?
Frontier LLMs like GPT-5.2 show large accuracy drops on perturbed program-output prediction tasks while open-source reasoning models remain more stable, exposing limits in code semantics understanding.
-
Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study
APIKG4Syn synthesizes API-oriented training data via knowledge graphs and Monte Carlo search to fine-tune a 7B model that reaches 25% pass@1 on HarmonyOS code generation, beating untuned GPT-4o at 17.59%.