NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#long-horizon-agents

0 stories this week · 3 this month · 3 in 6 months · mostly AI

Stories per day · 30 days

Relateddistillation2 agent-benchmarks1 agent-orchestration1 belief-state1 evaluation1 multi-agent1 opod1 payments1 porchestra1 terminus-21 tool-use1 world-model1

3 stories, newest first · one card per story

Hugging Face daily papers17d ago

BizBench tests long-horizon payment agents on constraint-valid execution

Claude Opus 5 and GPT-6 Sol reach only 64.0% and 61.3% strict success on 50 payment tasks.

agent-benchmarks long-horizon-agents

1

Hugging Face daily papers18d ago

BELIEFWEAVER improves long-horizon agent recovery from earlier failures

A distilled 9B student gained 9.8 points over the native baseline and cut estimated teacher API cost by 54.8%.

long-horizon-agents world-model

2

arXiv cs.AI / cs.LG / cs.CL21d ago

Proactive Agentic Orchestration

POrchestra lets sub-agents request mid-run harness changes, lifting long-horizon task success by about 9%.

agent-orchestration porchestra

3