# SWE-Together: Evaluating Coding Agents in Interactive User Sessions

arXiv: https://arxiv.org/abs/2606.29957 · HTML: https://mlsanity.com/paper/2606.29957/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 21 of 21)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [CollabLLM: From Passive Responders to Active Collaborators](https://mlsanity.com/paper/2502.00640/) (2025)
- [SWE-bench Goes Live!](https://mlsanity.com/paper/2505.23419/) (2025)
- [SWE-chat: Coding Agent Interactions From Real Users in the Wild](https://mlsanity.com/paper/2604.20779/) (2026)
- [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://mlsanity.com/paper/2510.06186/) (2025)
- [When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback](https://mlsanity.com/paper/2502.18413/) (2025)
- [Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation](https://mlsanity.com/paper/2510.08996/) (2025)
- [ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments](https://mlsanity.com/paper/2502.19852/) (2025)
- [FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback](https://mlsanity.com/paper/2601.04203/) (2025)
- [EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits](https://mlsanity.com/paper/2511.04486/) (2025)
- [Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants](https://mlsanity.com/paper/2605.09808/) (2026)
- [FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use](https://mlsanity.com/paper/2510.24645/) (2025)
- [Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality](https://mlsanity.com/paper/2509.10402/) (2025)
- [BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution](https://mlsanity.com/paper/2510.08697/) (2025)
- [Decoding Human-LLM Collaboration in Coding: An Empirical Study of Multi-Turn Conversations in the Wild](https://mlsanity.com/paper/2512.10493/) (2025)

## Built on by (most cited first, 18 of 18)

- [GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?](https://mlsanity.com/paper/2608.21833/) (2026)
- [Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments](https://mlsanity.com/paper/2609.04148/) (2026)
- [Learning Generalizable Behaviors for Terminal Agents](https://mlsanity.com/paper/2608.22631/) (2026)
- [CORAL: An LLM-Native Harness for Production Recommender Systems](https://mlsanity.com/paper/2609.02730/) (2026)
- [Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Histories](https://mlsanity.com/paper/2608.10319/) (2026)
- [ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks](https://mlsanity.com/paper/2609.18805/) (2026)
- [RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems](https://mlsanity.com/paper/2609.32490/) (2026)
- [AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering](https://mlsanity.com/paper/2609.32662/) (2026)
- [TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces](https://mlsanity.com/paper/2609.33295/) (2026)
- [Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents](https://mlsanity.com/paper/2609.37236/) (2026)
- [Zero2Repo: Can Coding Agents Build Repositories from Scratch?](https://mlsanity.com/paper/2609.38269/) (2026)
- [Persistent Context Graphs for Efficient Memory Compaction in LLM Agents](https://mlsanity.com/paper/2609.40118/) (2026)
- [Coding-Agent Benchmarks Should Match Their Users' Task Flows](https://mlsanity.com/paper/2610.09633/) (2026)
- [SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction](https://mlsanity.com/paper/2610.11559/) (2026)
- [ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents](https://mlsanity.com/paper/2610.13395/) (2026)
- [Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules](https://mlsanity.com/paper/2610.14216/) (2026)
- [EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications](https://mlsanity.com/paper/2610.16402/) (2026)
- [Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents](https://mlsanity.com/paper/2610.17757/) (2026)

## Abstract (arXiv)

Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with users clarifying goals, adding constraints, and correcting mistakes over multiple turns. We introduce SWE-Together, a multi-turn benchmark reconstructed from real user-agent coding sessions. To make real interactions verifiable, we curate 109 repository-level tasks from 11,260 recorded sessions, selecting sessions with recoverable repository states, clear user goals, and observable outcomes. To replay these interactions across agents, we build a reactive LLM-based user simulator that preserves the original users' intents and provides feedback when the coding agent's progress requires it. To evaluate agents as collaborators, we measure both final repository correctness and the number of corrective feedback turns required during the interaction. Experiments with frontier coding agents show that stronger agents generally achieve higher final success rates while requiring fewer interventions, suggesting an improved user experience.