Tuesday, October 27, 2026i10X News · Section desk11 stories
Studies
Agent Research
Research on autonomous agents, tool use and multi-agent systems
FilterMeta
Filtered: Meta in Agent Research · 1 storyReset filter ×
-
AI Agents Almost Never Stop in Time When a Task Is Impossible
Across 28,000+ tasks, timely abstention recall stays under 40% for all models. Best web AbsRec@1 is 26.7%; a scaffold can lift Llama-3.3-70B from 26.7% to 57.4%.
By
Editor's picks
- Realistic MCP Faults Halve Agent Quality, and a Bigger Model Doesn’t Help
- Stale CLAUDE.md and AGENTS.md Files Override the Code, and One Sentence Fixes It
- Coding Agents Can Be Tricked Into Running Attacker Commands After Compacting Context
- Even Top Agents Finish Only ~30% of Real Startup Product Workflows
- No Single Agent Memory Architecture Wins Everywhere, Systems Study Finds
More stories
· RSS