The agentic web is here
This Technology Review feature argues that LLM-based agents are beginning to reshape the web, moving from browser-automation experiments to tool connectors and assistant agents from Meta, OpenAI, and Anthropic. It descri...
Explore tools, prompts, skills, news and resources related to war 第38页.
Latest articles, prompts, use cases and editorial content about war 第38页
This Technology Review feature argues that LLM-based agents are beginning to reshape the web, moving from browser-automation experiments to tool connectors and assistant agents from Meta, OpenAI, and Anthropic. It descri...
Researchers propose Knowledge Association (KA) as the target of LLM unlearning, defined as the conditional predictive distribution linking a query context to its target knowledge. They introduce Knowledge Association Rei...
The paper proposes a hybrid framework that couples a CNN with a learnable-kernel Gaussian process to jointly perform data assimilation and bias correction from extremely sparse observations. A patch-based strategy reduce...
ORION introduces a hierarchical orchestrator that uses two LLM agents to translate service intents and generate abstract placement plans for 6G network slices across administrative domains. A cooperative multi-agent RL c...
A new neuro-symbolic decoding framework enforces formal specifications during LLM generation, not just syntax. It offers a forward-only variant guaranteeing specification satisfaction and a backtracking variant that revi...
The paper introduces DualBudget, a sparse text diffusion method that separately budgets attention graph edges and expert activations. It combines local, dilated, and global attention with conditional expert computation....
Researchers introduce a benchmark using 722 official UN Security Council records and five complementary tests to measure nation-level bias in LLMs, including opinion ranking, association sorting, vote simulation, opposit...
The paper introduces KEEPER, a framework that analyzes auxiliary objectives for recursive textual memory in LLM agents, identifying self-consistency bias where incorrect claims persist in memory. It compares four supervi...
This arXiv paper presents a mechanistic study of membership inference signals in large language models, introducing Decodable Information Score, Used Information Score, and Readout Accessibility Gap (DUG) to separate mem...
SparseGDN introduces a hardware-aware framework for Gated Delta Networks that reduces computation and memory traffic by combining structured intra-chunk approximation with input-dependent recurrent-event selection. Evalu...
The paper introduces GraphMP, a learning-based message-passing decoder for quantum low-density parity-check codes that generalizes across code families, sizes, error rates, and noise models without fine-tuning. It uses b...
Cybersecurity researchers have uncovered a Windows infostealer named VOLTA-AUTODOXER that leverages large language models (LLMs) including Claude, Gemini, and Kimi to evaluate and rank stolen data by its monetization pot...
The paper introduces Predictive Signed-Dyadic Coding (PG), a bio-inspired method that transmits events only when prediction residuals exceed a learned threshold, using signed power-of-two magnitudes. Applied to Mandarin...
LEAP is a length prediction system for LLM serving that reuses prefill hidden states to estimate output length via a linear readout, avoiding costly retraining. It adapts to domain shifts at test time using recursive lea...
Researchers present PIFT, a framework that transfers peptide-target interaction patterns to small-molecule generation for protein-protein interaction targets. It maps peptide-target and small-molecule-target interfaces i...
A new study demonstrates that a student model can acquire a trait (e.g., preference for an animal) solely from a judge's scores during group relative policy optimization, even when the training data contains no sema...
This paper investigates using auxiliary trajectory preferences, specifically confidence-based (SC) and entropy-based (UID-Conj.) metrics, to enhance small language model self-improvement and transfer under limited superv...
The paper introduces Agentic Soft-Token Compression (ASTC), a training-free method that uses soft tokens within an LLM agent to compress accumulated context for long-horizon tasks. ASTC leverages the model's native...
Iluvatar CoreX has published benchmark results indicating its Tiangai 300 AI accelerator outperforms Nvidia's H200 on selected metrics, drawing attention to China's domestic chip progress. The commentary notes...
Figma announced 20 new Model Context Protocol partners at its Config India event on October 15, including Notion and Mistral. This move opens Figma's canvas to AI coding agents, positioning it against Canva's p...