{"slug": "carryon-learning-what-to-keep-in-context-for-long-horizon-llm-agents", "title": "CarryOn: Learning What to Keep in Context for Long-Horizon LLM Agents", "summary": "A new context manager called CarryOn, described in arXiv paper 2611.17808v1, achieved 75.7% macro-averaged task success across AppWorld, OfficeBench and Tau2 Telecom with three LLM Actors, beating the strongest baseline by 6.7 percentage points. CarryOn pairs a compact execution state with fine-grained, source-linked evidence, using a learned selector and adaptive retention policy that avoid extra LLM calls for context management. The authors also introduce two metrics, S_alpha (task success weighted by resource use) and normalized cost per success (NCS), on which CarryOn posts the best average scores.", "body_md": "arXiv:2611.17808v1 Announce Type: new \nAbstract: Long-horizon LLM agents can coordinate tools and applications to complete complex, multi-step tasks. As their interaction histories grow, effective context management becomes essential for reliable and efficient execution. Existing methods reduce context through summarization, pruning, or history selection. However, shorter contexts do not necessarily support better decisions: summaries can omit exact details needed for later actions, while retaining entire interactions can carry substantial irrelevant information. We propose CarryOn, a lightweight context manager that pairs compact execution state with fine-grained, source-linked evidence. A learned selector and adaptive retention policy keep relevant evidence available without additional LLM calls for context management. We introduce two complementary evaluation metrics: $S_\\alpha$ prioritizes task success while accounting for resource use, and normalized cost per success (NCS) measures the resources spent per successful task. Across AppWorld, OfficeBench, and Tau2 Telecom with three LLM Actors, CarryOn achieves 75.7% macro-averaged task success, exceeding the strongest baseline by 6.7 percentage points. It also achieves the best average scores on both metrics.", "url": "https://wpnews.pro/news/carryon-learning-what-to-keep-in-context-for-long-horizon-llm-agents", "canonical_source": "https://www.machinebrief.com/news/carryon-learning-what-to-keep-in-context-for-long-horizon-ll-pu52", "published_at": "2026-11-16 05:00:00+00:00", "updated_at": "2026-11-16 05:25:18.458270+00:00", "lang": "en", "topics": ["ai-agents", "large-language-models", "artificial-intelligence", "ai-research"], "entities": ["CarryOn", "AppWorld", "OfficeBench", "Tau2 Telecom", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/carryon-learning-what-to-keep-in-context-for-long-horizon-llm-agents", "markdown": "https://wpnews.pro/news/carryon-learning-what-to-keep-in-context-for-long-horizon-llm-agents.md", "text": "https://wpnews.pro/news/carryon-learning-what-to-keep-in-context-for-long-horizon-llm-agents.txt", "jsonld": "https://wpnews.pro/news/carryon-learning-what-to-keep-in-context-for-long-horizon-llm-agents.jsonld"}}