{"slug": "online-monitoring-and-corrective-steering-of-programming-agents", "title": "Online Monitoring and Corrective Steering of Programming Agents", "summary": "Researchers propose LivePlan, a system that monitors and corrects programming agents in real time, improving issue resolution rates by up to 15.2% (average 9.9%) over vanilla SWE-agent across SWE-bench Verified and SWE-bench Pro, at an additional cost of $0.08 per instance. LivePlan decouples judging from advising, using a deterministic rule-based monitor to detect issues without invoking an LLM, and only then consulting an advisor LLM for high-level corrections. The system, implemented on top of SWE-agent, consistently outperforms alternative approaches with minimal regression on already successful runs.", "body_md": "arXiv:2608.06701v1 Announce Type: cross\nAbstract: Fixing GitHub issues in large-scale projects is a long-horizon task, especially when a fix requires changes across multiple locations or the issue description lacks the information needed to localize and repair it. As a result, agents traverse long trajectories that are prone to inefficiency and error: they drift away from their intended plan, repeat failed actions, or terminate without a working patch. This paper proposes LivePlan to monitor, detect, and correct such behavioral inefficiencies and drifts in real time. LivePlan decouples judging from advising: a deterministic, rule-based monitor examines general signals over the trajectory to detect issues without invoking an LLM, and only when an issue is detected does it consult an advisor LLM for a high-level, next-step correction. This design avoids the misleading re-planning and costly interventions of prior approaches. We implement LivePlan on top of SWE-agent and evaluate it using five LLMs (three as executor agents and two as advisors) across SWE-bench Verified and SWE-bench Pro. Compared to vanilla SWE-agent, LivePlan notably improves issue resolution rates, achieving consistent gains of up to 15.2% (average: 9.9%), while incurring only an additional cost of $0.08 per instance. The additional solutions concentrate on medium and hard instances. LivePlan consistently outperforms alternative approaches in resolution rate, with minimal regression on already successful runs and new successes on problems that no baseline solves.", "url": "https://wpnews.pro/news/online-monitoring-and-corrective-steering-of-programming-agents", "canonical_source": "https://www.machinebrief.com/news/online-monitoring-and-corrective-steering-of-programming-age-f1k9", "published_at": "2026-08-10 04:00:00+00:00", "updated_at": "2026-08-10 05:11:47.134327+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "developer-tools"], "entities": ["LivePlan", "SWE-agent", "SWE-bench Verified", "SWE-bench Pro"], "alternates": {"html": "https://wpnews.pro/news/online-monitoring-and-corrective-steering-of-programming-agents", "markdown": "https://wpnews.pro/news/online-monitoring-and-corrective-steering-of-programming-agents.md", "text": "https://wpnews.pro/news/online-monitoring-and-corrective-steering-of-programming-agents.txt", "jsonld": "https://wpnews.pro/news/online-monitoring-and-corrective-steering-of-programming-agents.jsonld"}}