cd /news/ai-agents/carryon-learning-what-to-keep-in-con… · home › topics › ai-agents › article
[ARTICLE · art-170344] src=machinebrief.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

CarryOn: Learning What to Keep in Context for Long-Horizon LLM Agents

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.

by read1 min views1 publishedNov 16, 2026

arXiv:2611.17808v1 Announce Type: new Abstract: 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.

── more in #ai-agents 4 stories · sorted by recency
── more on @carryon 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/carryon-learning-wha…] indexed:0 read:1min 2026-11-16 · —