ATEST adapts LLM test-time sampling to live GPU energy
On four A100 datasets, ATEST-Online stayed inside the energy budget and tied or led accuracy as load rose.
43
AI model
Qwen2.5-3B
- Mentions · 7d0
- Mentions · 30d4
- All mentions4
- First seenSep 26, 2026
- Last mentioned8d ago
Timeline
4 articles · newest firstSemantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents
Semantic Behavioral Watermarking marks LLM-agent actions so provenance survives paraphrasing and resists forged trajectories.
50
Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance
RegLLM measures escalation, grounding, and unsafe actions for regulated agents, but only at smoke scale.
43
Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents
AlignOPSD fixes decision-timestamp mismatch in on-policy distillation, beating GRPO by 5.5–8.7% on agent tasks.
47
Appears with
- L40Sproduct · 1
- Phi-3-miniai model · 1
- Qwen2.5-7Bai model · 1
- NVIDIAvendor · 1
- ToolBenchproduct · 1
- ALFWorldproduct · 1
- A100product · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.