Tootfinder

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/2]:
- The Geometry of Harmful Intent: Training-Free Anomaly Detection via Angular Deviation in LLM Resi...
Isaac Llorente-Saguer
https://arxiv.org/abs/2603.27412 https://mastoxiv.page/@arXiv_csLG_bot/116323180390164201
- LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Meituan LongCat Team, et al.
https://arxiv.org/abs/2603.27538 https://mastoxiv.page/@arXiv_csCV_bot/116323299668026852
- Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Huang, Jiang, Wang, Zhuang, Luo, Ma, Xu, Chen, Moniz, Lin, Chen, Chawla, Dziri, Sun, Zhang
https://arxiv.org/abs/2603.27771 https://mastoxiv.page/@arXiv_csMA_bot/116322908437739020
- KVSculpt: KV Cache Compression as Distillation
Bo Jiang, Sian Jin
https://arxiv.org/abs/2603.27819 https://mastoxiv.page/@arXiv_csLG_bot/116323241993833314
- Q-Bridge: Code Translation for Quantum Machine Learning via LLMs
Runjia Zeng, Priyabrata Senapati, Ruixiang Tang, Dongfang Liu, Qiang Guan
https://arxiv.org/abs/2603.27836 https://mastoxiv.page/@arXiv_quantph_bot/116323164660887506
- EffiSkill: Agent Skill Based Automated Code Efficiency Optimization
Zimu Wang, Yuling Shi, Mengfan Li, Zijun Liu, Jie M. Zhang, Chengcheng Wan, Xiaodong Gu
https://arxiv.org/abs/2603.27850 https://mastoxiv.page/@arXiv_csSE_bot/116322989347928729
- Efficient Inference of Large Vision Language Models
Surendra Pathak
https://arxiv.org/abs/2603.27960 https://mastoxiv.page/@arXiv_csLG_bot/116323256085918152
- CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-...
Kesheng Chen, Yamin Hu, Qi Zhou, Zhenqian Zhu, Wenjian Luo
https://arxiv.org/abs/2603.27982 https://mastoxiv.page/@arXiv_csCV_bot/116323319000206060
- MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions
Huang, Fan, Jiang, Jiang, Tu, Zhu, Zhang, Zhao, Yang, Fei, Li, Yang, Cheng, Qiu
https://arxiv.org/abs/2603.28086 https://mastoxiv.page/@arXiv_csSD_bot/116322971980743316
- Does Claude's Constitution Have a Culture?
Parham Pourdavood
https://arxiv.org/abs/2603.28123 https://mastoxiv.page/@arXiv_csCY_bot/116322911684465443
- MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
Fangda Ye, et al.
https://arxiv.org/abs/2603.28407 https://mastoxiv.page/@arXiv_csAI_bot/116323220038984883
- IsoQuant: Hardware-Aligned SO(4) Isoclinic Rotations for LLM KV Cache Compression
Zhongping Ji
https://arxiv.org/abs/2603.28430 https://mastoxiv.page/@arXiv_csLG_bot/116323286231537351
- Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG
Davide Di Gioia
https://arxiv.org/abs/2603.28444 https://mastoxiv.page/@arXiv_csAI_bot/116323220366355511
- Moving Beyond Review: Applying Language Models to Planning and Translation in Reflection
Seyed Parsa Neshaei, Richard Lee Davis, Tanja K\"aser
https://arxiv.org/abs/2603.28596 https://mastoxiv.page/@arXiv_csHC_bot/116323161382060848
- ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
Huanxuan Liao, Zhongtao Jiang, Yupu Hao, Yuqiao Tan, Shizhu He, Jun Zhao, Kun Xu, Kang Liu
https://arxiv.org/abs/2603.28610 https://mastoxiv.page/@arXiv_csCV_bot/116323344559859277
- The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGE...
Lara Russell-Lasalandra, Hudson Golino, Luis Eduardo Garrido, Alexander P. Christensen
https://arxiv.org/abs/2603.28643 https://mastoxiv.page/@arXiv_csAI_bot/116323236095523987
- SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
Philip Schroeder, Thomas Weng, Karl Schmeckpeper, Eric Rosen, Stephen Hart, Ondrej Biza
https://arxiv.org/abs/2603.28730 https://mastoxiv.page/@arXiv_csRO_bot/116323253135037252
- ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath
https://arxiv.org/abs/2603.28737 https://mastoxiv.page/@arXiv_eessAS_bot/116322903493463665
toXiv_bot_toot

#Blakes7 Series B, Episode 04 - Horizon
RO: Let her go.
KOMMISSAR: She's no good to you, Ro. None at all. You must be rid of her. She should not have been brought back to the palace.
RO: You are, I think, mistaken, Kommissar. She means us no harm.

AgentCgroup: Understanding and Controlling OS Resources of AI Agents
Yusheng Zheng, Jiakun Fan, Quanzhi Fu, Yiwei Yang, Wei Zhang, Andi Quinn
https://arxiv.org/abs/2602.09345 https://arxiv.org/pdf/2602.09345 https://arxiv.org/html/2602.09345
arXiv:2602.09345v1 Announce Type: new
Abstract: AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, each call with distinct resource demands and rapid fluctuations. We present a systematic characterization of OS-level resource dynamics in sandboxed AI coding agents, analyzing 144 software engineering tasks from the SWE-rebench benchmark across two LLM models. Our measurements reveal that (1) OS-level execution (tool calls, container and agent initialization) accounts for 56-74% of end-to-end task latency; (2) memory, not CPU, is the concurrency bottleneck; (3) memory spikes are tool-call-driven with a up to 15.4x peak-to-average ratio; and (4) resource demands are highly unpredictable across tasks, runs, and models. Comparing these characteristics against serverless, microservice, and batch workloads, we identify three mismatches in existing resource controls: a granularity mismatch (container-level policies vs. tool-call-level dynamics), a responsiveness mismatch (user-space reaction vs. sub-second unpredictable bursts), and an adaptability mismatch (history-based prediction vs. non-deterministic stateful execution). We propose AgentCgroup , an eBPF-based resource controller that addresses these mismatches through hierarchical cgroup structures aligned with tool-call boundaries, in-kernel enforcement via sched_ext and memcg_bpf_ops, and runtime-adaptive policies driven by in-kernel monitoring. Preliminary evaluation demonstrates improved multi-tenant isolation and reduced resource waste.
toXiv_bot_toot