Full Text Available
Access Full Text at Repository
Search Results - Civil Engineering
-
SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
Online Article RSS Article -
LoopTrap: Termination Poisoning Attacks on LLM Agents
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
LeakDojo: Decoding the Leakage Threats of RAG Systems
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
EMO: Pretraining Mixture of Experts for Emergent Modularity
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Parser agreement and disagreement in L2 Korean UD: Implications for human-in-the-loop annotation
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Algospeak, Hiding in the Open: The Trade-off Between Legible Meaning and Detection Avoidance
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
SkillOS: Learning Skill Curation for Self-Evolving Agents
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Long Context Pre-Training with Lighthouse Attention
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Efficient Pre-Training with Token Superposition
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Cubit: Token Mixer with Kernel Ridge Regression
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Litespark Inference on Consumer CPUs: Custom SIMD Kernels for Ternary Neural Networks
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text
-
Patch-Effect Graph Kernels for LLM Interpretability
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…Civil & Construction…”
Get full text