V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning Paper • 2606.25319 • Published 2 days ago • 20
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents Paper • 2606.22883 • Published 4 days ago • 32
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding Paper • 2606.21906 • Published 6 days ago • 20
EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory Paper • 2606.21649 • Published 7 days ago • 28
OpenRath: Session-Centered Runtime State for Agent Systems Paper • 2606.19409 • Published 9 days ago • 74
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems Paper • 2606.22388 • Published 5 days ago • 91
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams Paper • 2606.21337 • Published 7 days ago • 70
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention Paper • 2606.20945 • Published 8 days ago • 64
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions Paper • 2606.23654 • Published 4 days ago • 76
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking Paper • 2606.22807 • Published 4 days ago • 44
Tmax Collection Data and models associated with "Tmax: A simple recipe for terminal agents". paper: https://arxiv.org/abs/2606.23321 • 23 items • Updated 3 days ago • 12