SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks. Existing frontier SWE benchmarks typically provide complete requirements upfront and evaluate agents on autonomous implementation. In contrast, SWE-Interact places agents in a realistic developer workflow: a carefully designed user simulator starts with vague or incomplete instructions, progressively reveals requirements, inspects the agent's workspace, and provides targeted feedback, revisions, and new constraints until the full task goal has been handed off. Grounded in large-scale studies of real coding-agent interactions, this setup tests whether agents can discover user intent, adapt to evolving requirements, and build on their own prior work. Across a suite of frontier and open-weight models, we find that strong performance on single-turn SWE tasks does not reliably transfer to multi-turn, user-driven workflows: the best-performing models solve roughly 50% of single-turn baseline tasks but only 25% of the corresponding SWE-Interact tasks. The strongest models in our evaluation, including Opus 4.8 and GPT 5.5, start strong even in the face of vague initial instructions, persevere until all the requirements are surfaced by the user, integrate them better and write clean code. However, they still suffer from over-agentic coding, forgetting requirements and technical mistakes. Weaker models start poorly under ambiguity, give up early, forget or ignore instructions and rework their code more. Overall, SWE-Interact measures an orthogonal, real-world capability axis for frontier model development: interactive goal discovery and iterative refinement with a user in the loop.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Story Ribbons: Reimagining Storyline Visualizations with Large Language Models
Analyzing literature involves tracking interactions between characters, locations, and themes. Visualization has the potential to facilitate the mapping and analysis of these complex relationships, but capturing structur…
Reimagining Social Robots as Recommender Systems: Foundations, Framework, and Applications
Personalization in social robots refers to the ability of the robot to meet the needs and/or preferences of an individual user. Existing approaches typically rely on large language models (LLMs) to generate context-aware…
Reinforcement LearningLifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation
The rapid advancement of large language models (LLMs) has accelerated progress toward universal AI assistants. However, existing benchmarks for personalized assistants remain misaligned with real-world user-assistant int…
VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Space
Video editing is a creative and complex endeavor and we believe that there is potential for reimagining a new video editing interface to better support the creative and exploratory nature of video editing. We take inspir…
Asset ManagementManagementVideo EditingAMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
Long-horizon interactions between users and LLM-based assistants necessitate effective memory management, yet current approaches face challenges in training and evaluation of memory. Existing memory benchmarks rely on st…