10 papers
Towards Evaluation of Implicit Software World Models in Coding LLMs
Egor Bogomolov, Yaroslav Zharov
Software engineering, whether performed by humans or by AI agents, requires reasoning about how software behaves. We call the internal model that supports such reasoning the softwa…
On Problems of Implicit Context Compression for Software Engineering Agents
Kirill Gelvan, Igor Slinko, Felix Steinbauer +3
LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode cont…
Step Rejection Fine-Tuning: A Practical Distillation Recipe
Igor Slinko, Ilia Zavidnyi, Egor Bogomolov +1
Rejection Fine-Tuning (RFT) is a standard method for training LLM agents, where unsuccessful trajectories are discarded from the training set. In the context of SWE-bench tasks, th…
Multi-Agent Coordinated Rename Refactoring
Abhiram Bellur, Mohammed Raihan Ullah, Fraol Batole +9
The primary value of AI agents in software development lies in their ability to extend the developer's capacity for reasoning and action, not to supplant human involvement. To show…
The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
Tobias Lindenbauer, Igor Slinko, Ludwig Felder +2
Large Language Model (LLM)-based agents solve complex tasks through iterative reasoning, exploration, and tool-use, a process that can result in long, expensive context histories.…
Leveraging LLMs, IDEs, and Semantic Embeddings for Automated Move Method Refactoring
Abhiram Bellur, Fraol Batole, Mohammed Raihan Ullah +12
MOVEMETHOD is a hallmark refactoring. Despite a plethora of research tools that recommend which methods to move and where, these recommendations do not align with how expert develo…