Cool Papers · cs.CL (papers.cool) · RSS 摘要

信源：Cool Papers · cs.CL (papers.cool) · https://papers.cool/arxiv/cs.CL/feed

• OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory — Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone…
• LatComm: Reusable Context Compression for Latent Communication between Large Language Models — Systems that combine several large language models (LLMs) often use one context for many questions. When the context is passed between models as text, the receiving model processe…
• Competing Learning in Hybrid Architectures — Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention. Modern recurrence layers provide a highly express…
• KEEP-Bench: Evaluating Evidence Preservation in Context Compression — Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but a reader…
• RefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web Development — Beyond basic tool use and coding skills, effectively incorporating visual references into agentic generation is equally essential for applying AI agents to real-world productivity…