OPD-Evolver introduces a slow-fast co-evolution framework that enables agents to select, act on, and reuse experience through on-policy self-distillation. It outperforms existing memory and training-based methods by up to 11.5% and 5.8% respectively, and demonstrates capability to challenge large-scale models like Qwen3.5-397B-A17B and Step-3.5-Flash.
arxiv
arXiv cs.CL
·
53d ago
·
research
OPD-Evolver: On-Policy Distillation for Holistic Agent Evolving
from English
Importance 3/3
Beats a top-lab benchmark
New feature vs. leaders
New harness with differentiators
arXiv cs.CL
Mistral AI
Alibaba (Qwen)
DeepSeek
AI agents
Evaluation & benchmarks
Reasoning models
Related articles
arxiv
arXiv cs.AI
·
46d ago
·
1 view
Benchmark Evaluation of Small Language Models for Arabic NLP
A benchmark of 240 Arabic test items across eight domains and ten skills assesses twelve small language models in zero-shot settings. Gemma 3 (12B) achieved the highest overall score (4.548/5), followed by Aya and C4AI Command Arabic, with performance linked more to Arabic alignment and instruction-following than model size. Common failure modes include prompt leakage, hallucination, and weak task adherence.
arxiv
arXiv cs.CL
·
47d ago
·
2 views
Benchmark Evaluation of Small Language Models for Arabic NLP
A benchmark of 240 Arabic test items across eight domains and ten skills assesses twelve small language models in zero-shot settings. Gemma 3 (12B) achieved the highest overall score (4.548/5), followed by Aya and C4AI Command Arabic, with performance linked more to Arabic alignment and instruction-following than model size. Common failure modes include prompt leakage, hallucination, and weak task adherence.
arxiv
arXiv cs.AI
·
52d ago
·
1 view
X+Slides: Benchmark for Audience-Conditioned Slide Generation
X+Slides introduces a benchmark that evaluates slide generation based on target audience needs. It uses 8,133 source-grounded probes across 113 topics and seven scenes to measure Audience Coverage, Domain-wise Coverage, Efficiency, and Correctness, revealing that current systems recover only partial audience-essential information, with DeepPresenter achieving 0.714 Audience Coverage, SlideTailor 0.594, and NotebookLM ablation 0.853, highlighting the need for source-grounded evaluation.
arxiv
arXiv cs.LG
·
52d ago
Spotlight: Using Spot GPUs to Accelerate DiT RL Post-Training
Spotlight enables DiT RL post-training by leveraging idle spot GPUs, reducing costs by 1.4-6.4x while achieving superior image quality. It uses stale model weights in exploration and reconfigures sequence parallelism on-the-fly, allowing efficient GPU utilization without breaking training pipelines.
arxiv
arXiv cs.LG
·
53d ago
ATT&CK-Labeled Multi-Source Cybersecurity Logs Dataset Released
A new dataset combines system, network, and browser logs from 870 Windows sessions, including 70 attacks and 800 benign cases. It provides per-event labels with MITRE ATT&CK technique IDs for 12 tactics and 53 techniques, using real attack tools like RAT and C2 tunnels. Fine-tuning three Small Language Models (SLMs) via LoRA improved chunk classification accuracy to 90–97% and achieved up to 42% exact-match accuracy in technique identification, showing strong reasoning capture despite challenges.