SkillNet Cuts Agent Steps Through Reusable Skills
An ontology, evaluation scheme, and 600,000-skill repository let agents retrieve and compose prior procedures, reporting 40% higher rewards with 30% fewer steps.
Aug 23, 20264 min2603.04448
Computation and Language
cs.CLNatural language processing, computational linguistics, speech, and text retrieval.
Sort:
Agent Swarm Cuts Complex Task Latency Up To 4.5×
Kimi K2.5 couples joint text-vision training with dynamically scheduled parallel subagents, improving agentic search scores while reducing time to target quality.
Aug 13, 20264 min2602.02276
Kimi K3 Brings Open Weights Closer to Frontier Agents
A 2.8T-parameter MoE combines Delta Attention, 16-of-896 expert routing, and agentic reinforcement learning to approach leading proprietary systems at lower task cost.
Aug 10, 20264 min2607.24653
Qwen-CUA Reaches 86.2 on Verified Computer Use
A 397B-A17B mixture-of-experts agent learns screenshot-only keyboard and mouse control from verifiable interactive trajectories, improving OSWorld-Verified performance to 86.2.
Aug 8, 20264 min2608.02352
Mini Activations Narrow Frontier Model Gaps
A sparse 229.9B-parameter MoE activates 9.8B parameters per token and pairs agent-native data with RL for coding, cowork, and reasoning tasks.
Jul 31, 20265 min2605.26494
Hybrid Mamba MoE Trades Dense Scale for Throughput
Soofi S activates 3B of 30B parameters per token and matches larger open models while reaching 4.8k TPS/GPU at 40K context.
Jul 29, 20265 min2607.09424
Gemma 4 Narrows Open Model Gap With Efficient Multimodality
Dense and MoE variants combine thinking traces, local-global attention, QAT, and MTP drafting, reaching 1451 Arena Elo with a 31B dense model.
Jul 28, 20265 min2607.02770
A 35B Agent Matches Trillion-Parameter Models on Long-Horizon Tasks
Long-horizon trajectories, domain teachers, and routed on-policy distillation produce 56.4 on SEAL-0 and 80.6 on IFBench.
Jul 28, 20265 min2606.30616
Solar Open 2 Extends Open MoE Models to Agentic Context
A hybrid softmax-linear attention stack reaches a 1M-token window while selective transfer, curated data, and on-policy distillation target long-horizon agent work.
Jul 28, 20265 min2607.20062
On-Policy Distillation Reduces Cross-Platform GUI Forgetting
Platform-conditioned teacher selection distills desktop and mobile policies into one continual learner, reaching 38.2% OSWorld and 12.0% MobileWorld success.
Jul 12, 20264 min2607.04425