Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

AI Research Radar

November 10–16: 18 frontier papers out of 2,145 read.

18 frontier278 cleared2,145 papers read

Frontier

Papers rated as moving the field

How we choose

Infrathon

Claude Opus 5.5 raises the mean KV-cache compression ratio from 6.82% with the human-designed Quant-VideoGen codec to 19.86%.

AgentsAllenAIBenchmark

Lazare, veni foras

Editing seven neurons turns Nemotron-Terminal-8B into a sleeper agent that fires the payload on at least 98.8% of triggered test trajectories.

SecurityMicrosoft

Bait

Bait mitigates harmful agentic reinforcement learning by probing the reward function while still allowing learning from benign rewards.

SecurityGoogleCode

When Experience Becomes a Backdoor

BadEvolve demonstrates effective task-level backdoor attacks on self-evolving LLM agents across diverse frameworks, benchmarks, and backbone LLMs.

SecurityMicrosoftCode

WebArena-Pro

On WebArena-Pro, Codex with GPT 6.1 Sol and Claude Code with Claude Opus 5.5 both reach 62.3%, the best among evaluated agents.

AgentsBenchmark

ManiLadder

ManiLadder benchmark with 112 tasks across 4 difficulty levels calibrates manipulation task difficulty using a unified imitation learning policy.

RoboticsBenchmark

Soteria

Soteria achieves 1.7 times the average task success rate of the best baselines across tool-use benchmarks, with no violations of policy specifications.

Safety

Reins

Reins lets GPT-6.1 Sol complete 88% of real dual-arm manipulation episodes on five tasks with no task-specific code.

Robotics

Jais 3

Jais 3 matches or outperforms open-weight models of comparable size on Arabic and agentic benchmarks with fewer hallucinations.

Agents

Compass 1

Compass 1 achieves a 79.4% overall success rate in open-world embodied navigation, versus 17.8% for the strongest baseline.

Robotics

Shortcuts and Boundaries

A binary compliance penalty raises safe completion on 32 unseen changing-evidence tasks from 53.1% to 89.1% while both policies achieve full real work.

Safety

The week by field

Nov 10–16: 278 cleared, 18 frontier

Also cleared

260 papers, by field

Security & privacy92
All 92 papers in Security & privacy
Agents32
All 32 papers in Agents
Safety & alignment30
All 30 papers in Safety & alignment
Inference & efficiency26
All 26 papers in Inference & efficiency
AI & society21
All 21 papers in AI & society
Robotics & embodied AI16
All 16 papers in Robotics & embodied AI
Language & speech13
All 13 papers in Language & speech
Vision & multimodal11
All 11 papers in Vision & multimodal
Science & health7
All 7 papers in Science & health
Reasoning & math5
Machine learning4
Training & data3