Skip to content

/

ZeroHour

ZeroHour aggregates public sources — security and AI press, vendor advisories, NVD, CISA KEV, FIRST EPSS, leak-site trackers and Have I Been Pwned — and classifies them with AI. Summaries can be wrong: read the original. All times are UTC.

News CVEs Incidents Tags Daily brief Traffic Sources RSS & API Kiosk Health Sitemap

Home
News feed
Exploited now

Security

CVEs
Ransomware & breaches
Threat actors & entities
IOCs

AI

AI & models

Explore

Tags
Daily brief
Analytics
Traffic & readers
Ask the feed
Sources

You

Watchlist
Saved
RSS, API & alerts

07:57 UTC· 9m ago

#tool-calling — news, CVEs and analysis · ZeroHour

today 47 visits · 60 views · 7 reads·all time 17K views

Tag

#tool-calling

3 stories this week · 9 this month · 9 in 6 months · mostly AI

stories per day · 30 days

Related#benchmark 3 #llm-agents 3 #agent-harness 2 #open-weights 2 #tts 2 #agents 1 #agent-security 1 #asr 1 #benchmarks 1 #browsecomp 1 #cost-efficiency 1 #data-synthesis 1 #edge-ai 1 #edge-cases 1 #fine-tuning 1 #finetuning 1 #full-duplex 1 #gemma 1

9 stories, newest first · one card per story

Hacker News · AI·4d ago

Unreal Agent

#unreal-agent #unreal-labs #agent-harness

4 min

arXiv cs.AI / cs.LG / cs.CL·4d ago

Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents

#llm-agents #agent-harness #webarena

AI research

Hugging Face daily papers·6d ago

EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation

#tool-calling #synthetic-data #agents

1

arXiv cs.AI / cs.LG / cs.CL·8d ago

NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities

#speech-to-speech #full-duplex #tool-calling

AI research

arXiv cs.AI / cs.LG / cs.CL·9d ago

MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents

#asr #benchmark #llm-evaluation

AI research

arXiv cs.CR·10d ago

Closed-World Resolution Against Tool Hallucination in LLM Agents

#agent-security #benchmark #llm-agents

AI safety & security

1

Hugging Face trending models·11d ago

Cactus-Compute/needle3 — new model trending #30 on Hugging Face

#edge-ai #on-device #open-weights

Model release

6 min

arXiv cs.AI / cs.LG / cs.CL·11d ago

What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity

#llm-compression #model-degradation #moe

AI research

arXiv cs.AI / cs.LG / cs.CL·22d ago

Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe

#benchmark #data-synthesis #fine-tuning

AI research

1