惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - Franky
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
美团技术团队
The Cloudflare Blog
量子位
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园_首页
F
Fortinet All Blogs
J
Java Code Geeks
人人都是产品经理
人人都是产品经理
N
Netflix TechBlog - Medium
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
爱范儿
爱范儿
Apple Machine Learning Research
Apple Machine Learning Research
B
Blog RSS Feed
博客园 - 聂微东
Hugging Face - Blog
Hugging Face - Blog
WordPress大学
WordPress大学
小众软件
小众软件
Y
Y Combinator Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Vercel News
Vercel News
S
SegmentFault 最新的问题
有赞技术团队
有赞技术团队

cs updates on arXiv.org

Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment Agentic Proving for Program Verification MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework Benchmarking Google Embeddings 2 against Open-Source Models for Multilingual Dense Retrieval and RAG Systems Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts Solving the Aircraft Disassembly Scheduling Problem Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents CP or DP? Why Not Both: A Case Study in the Partial Shop Scheduling Problem Asking For An Old Friend: Diagnosing and Mitigating Temporal Failure Modes in LLM-based Statutory Question Answering EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction Naturalistic measure of social norms alignment Articulatory strategy as a source of variation in acoustic vowel dynamics When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems EquiSumm : A Gender Bias-Aware Framework for Inclusive Tweet Summarization Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning Cultural Adaptation in Large Language Models for Political Discourse Emotion Recognition in Sign Language Conversation ClimateChat-300K: A Multi-Modal Facebook Dataset for Understanding Diverse Perspectives in Climate Communication AraHopeCorpus: Annotation Guidelines and Dataset for Hope Speech in Arabic Social Media Crisis Discourse Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference Learning Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning DART: Semantic Recoverability for Structured Tool Agents Ontological Knowledge Blocks: Executable Compliance and Profile-Based Validation for Trustworthy AI Systems Parallel Context Compaction for Long-Horizon LLM Agent Serving
Long Live the Librarian! A Persistent Search Sub-Agent fo...
Seunghyuk Cho, Sunghyun Choi, Jaeseung Heo, Youngbin Choi, Saemi · 2026-05-27 · via cs updates on arXiv.org

Multi-agent systems (MAS) have substantially advanced autonomous software engineering (SWE), but their growing inference energy demands raise sustainability concerns. In this paper, we demonstrate that this cost is concentrated in an overlooked source: redundant output tokens generated across agents. Two empirical findings ground this claim. First, our per-token energy attribution for MAS reveals a sharp asymmetry: an output token consumes 30 to 1,000 times more energy than an input or cached token. Second, MAS inflate per-episode output because agents repeatedly re-explore overlapping repository regions. To address this inefficiency, we propose Librarian, a persistent search sub-agent that tracks repository-search history and suppresses redundant exploration actions across agents. By returning short references to file regions instead of full file excerpts, Librarian further reduces output-token volume. On SWE-Bench Verified, Librarian reduces per-episode GPU energy consumption of existing multi-agent SWE systems by up to 25% while preserving task performance.