cs.HCNov 3, 2026

From Watching to Steering: Enabling Human-Coding Agent Collaboration through Execution Traces

Authors: Xiaoke Yan, Jiaying Lei, Danqing Shi, Zichen Wang, Nan Cao

Organizations: Intelligent Design & Innovation Lab, Tongji University, Shanghai, China · Department of Computer Science, LTH, Lund University, Sweden · School of Mathematical Sciences, Tongji University, Shanghai, China

Abstract

Recent advances in large language models (LLMs) have enabled coding agents to autonomously perform complex software development tasks, yet their long-running execution remains difficult for users to inspect, understand, and steer. We present Vibetrace, an interactive trace visualization and intervention system for agentic programming built upon OpenCode. Vibetrace introduces a human-agent collaboration paradigm of Observe, Understand, Intervene, and Evolve. It (1) visualizes agent workflows as interactive execution traces for inspecting actions, intermediate states, and failures; (2) enables users to fork execution from prior steps and provide targeted corrections without restarting validated progress; and (3) distills traces and human feedback into reusable skills for continual agent evolution. On SWE-bench Verified, distilled skills reduce input tokens by 23.0% and cost by 15.5%, while improving pass rate from 65.0% to 68.0%. User studies further demonstrate improved accuracy and efficiency over conventional log-based interaction.

Figures & tables

Explore similar work

CardsList
  1. TraceLab: Characterizing Coding Agent Workloads for LLM Serving

    Jun 29, 2026Kan Zhu, Mathew Jacob, Chenxi Ma +4LLM ServingAI Coding Agents

  2. AgentTrails: Towards Trust and Reuse for Agentic Tasks

    Jul 21, 2026Eden Wu, Sonia Castelo, Yurong Liu +2Data ProvenanceAgent Trajectory Analysis