{"slug": "evosyn-framework-improves-agent-task-success-by-13-3-points-via-agentic-data", "title": "EvoSyn framework improves agent task success by 13.3 points via agentic data synthesis", "summary": "The EvoSyn framework reports a 13.3-point average task-success gain over the strongest synthetic-data baseline on τ²-Bench and CAR-Bench by making the synthesis space itself editable from learner feedback. EvoSyn converts learner failures directly into synthesis directives, expanding the generation space to surface controllable interaction factors that static synthesis pipelines never discover. The result argues for a feedback-driven, revisable synthesis state rather than one-shot bulk generation when fine-tuning agents on synthetic trajectories.", "body_md": "[arXiv](https://arxiv.org/abs/2610.12593)\n\n### EvoSyn framework improves agent task success by 13.3 points via agentic data synthesis\n\nWhich summary reads better? Pick one — models revealed after.Both summaries are AI-generated.\n\nEvoSyn reports a 13.3-point average task-success gain over the strongest synthetic-data baseline on τ²-Bench and CAR-Bench by making the synthesis space itself editable from learner feedback. The practical shift is that agent training data generation stops being just “sample more failed cases” and becomes a closed-loop controller that can add new controllable interaction factors, which matters if your bottleneck is coverage of rare, task-specific failure modes rather than raw trajectory volume.\n\nEvoSyn closes the loop on agent training data by converting learner failures directly into synthesis directives, yielding a 13.3-point average task-success gain over the strongest synthesis baseline on τ²-Bench and CAR-Bench. The key shift is that it not only targets weak regions within a fixed generation space but expands that space—surfacing controllable interaction factors that static synthesis pipelines never discover. If you're generating synthetic trajectories to fine-tune agents, this argues for a feedback-driven, revisable synthesis state rather than one-shot bulk generation, since your current pipeline is likely blind to coverage gaps it can't yet represent.", "url": "https://wpnews.pro/news/evosyn-framework-improves-agent-task-success-by-13-3-points-via-agentic-data", "canonical_source": "https://www.snipvote.com/story/cmv4xgwsc000688m2dywsedeg", "published_at": "2026-10-12 07:39:32.108592+00:00", "updated_at": "2026-10-12 07:39:33.987880+00:00", "lang": "en", "topics": ["ai-agents", "ai-research", "machine-learning", "artificial-intelligence"], "entities": ["EvoSyn", "τ²-Bench", "CAR-Bench", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/evosyn-framework-improves-agent-task-success-by-13-3-points-via-agentic-data", "markdown": "https://wpnews.pro/news/evosyn-framework-improves-agent-task-success-by-13-3-points-via-agentic-data.md", "text": "https://wpnews.pro/news/evosyn-framework-improves-agent-task-success-by-13-3-points-via-agentic-data.txt", "jsonld": "https://wpnews.pro/news/evosyn-framework-improves-agent-task-success-by-13-3-points-via-agentic-data.jsonld"}}