Explore tools, prompts, skills, news and resources related to arXiv 第4页.
Latest articles, prompts, use cases and editorial content about arXiv 第4页
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...
EvoMCP is a framework that enables Model Context Protocol (MCP) agents to improve through a closed loop of task evolution, trajectory evolution, and supervised fine-tuning. It assesses the student's capabilities fro...
A new arXiv paper introduces an evidence-guided framework for AI agents to recover from ambiguous tool outcomes and partial execution. The approach uses approved obligations, provider capabilities, and public evidence to...
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...
A new benchmark, BlindToChange, reveals that AI agents often fail to proactively search for recent real-world events that affect their responses, even though they can find changes when explicitly asked. The benchmark use...
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...
CryoAtlas is a rigorously curated dataset and unified benchmark for density-guided atomic model building of protein chains from cryo-EM maps. It provides 17,809 map-model-sequence entries, including a curated training sp...
The paper proposes a privacy-preserving paradigm for safety auditing of LLM agents, separating audit computation from plaintext access and execution authority. It introduces SealCall, a framework combining learned audit...
scAnyOmics is a generative framework that distills knowledge from a frozen single-cell foundation model into a multimodal student model, enabling cross-modal prediction and reconstruction of missing modalities from scRNA...
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...
The paper introduces a profile-bounded protocol for authorizing AI computer-use agents across graphical, command-line, API, script, and Model Context Protocol interfaces. It formalizes effect-bearing routes and durable s...
ProSearch is a new benchmark designed to evaluate multi-constraint protocol retrieval in experimental science, featuring 1,515 queries across six domains. It incorporates realism, complexity, and diagnosticity with 3-5 e...
The paper formalizes Online Evidence-Containment Prediction (OECP) for nested text spans in evidence-grounded NLP systems. It shows that span containment corresponds to a triangular 2D product order, enabling distinct-qu...
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...
This arXiv paper reviews pinching antenna systems (PASS) for integrated sensing and communication (ISAC) in 6G wireless networks. It compares single-waveguide, multi-waveguide, and segmented-waveguide architectures, and...
Researchers propose Ask on Demand (AOD), a communication framework that lets parallel LLM agents request targeted assistance from peers only when specific information needs arise. A lightweight gate trained on team outco...
BULLPEN is a new framework that extends EmbedLLM to profile large language models by jointly encoding answer text, correctness, and question features. It adds 20 behavioral, style, and provenance benchmarks and achieves...
