LLM Agent Efficiency

LLM: Large Language Model

Follow this topic Ask about this topic

Latest papers

85 papers51 papers in the last four weeks, against 1 the four weeks before. 0.3% of all new papers.

Does Your Generalist Skill Optimizer Really Incentivize Agentic Tasks? Rethinking Skill Optimization via Bipartite Attribution
Oct 27, 2026Jiawei Zhou, Bo Peng, Yuxuan Huang +4Agent Skill Learning LLM Agent Skill Evaluation
Shanghai AI Laboratory · Fudan University · Shanghai Jiao Tong University +2
CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction
Oct 26, 2026Neil Chen, Adrian Serapio, Hanxue Gu +3LLM Agent Workflow Optimization LLM Agent Efficiency
UC Berkeley · UC San Francisco
A Unified Arena for LLM Agents across Diverse Eurogame
Oct 26, 2026Fengrui Zhang, Xiang Li, Ruomeng Ding +6LLM Agent Evaluation Game-Playing Agents
Alibaba Group · Nanjing University · National University of Singapore +3
Semantic Atoms for Scalable Text Analysis in Data Analytics in the Era of LLM-Based Agents
Oct 26, 2026Jinxiang Xie, Zihao Li, Rui Ding +3Data Analysis Agents LLM Agent Efficiency
Nanjing University · Tsinghua University · Microsoft Research
Silent and Costly: Characterizing and Detecting Prompt-Caching Mis-Integration in LLM Agents
Oct 26, 2026Ying Zhang, Ruoqi Guo, Yi Liu +4LLM Agent Reliability LLM Agent Efficiency
Wake Forest University Winston-Salem, USA · Griffith University Gold Coast, Australia · Nanyang Technological University Singapore +2
The Physical Cost of Context: Quality-Constrained Resource Accounting for Coding Agents
Oct 26, 2026Zhongming Yu, Yitong Ma, Hengjia Yu +4LLM Agent Efficiency LLM Context Management
University of California, San Diego · University of Massachusetts Amherst
AT-AT: Automatic Tool Optimization from Agent Traces
Oct 26, 2026Maya Ravichandran, Pragya Tripathi, Dharamendra Kumar +2Tool-Using Agents LLM Agent Efficiency
Netflix
What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents
Oct 25, 2026Kaiser Sun, Yongchan Kwon, Zain Hasan +3Inference-Time Compute Allocation LLM Agent Efficiency
Johns Hopkins University · Together AI · Cornell University
CTXAgent - Self-Controlled Context Management of LLM Agents
Oct 25, 2026Matthias Busch, Marius Tacke, Roland C. Aydin +2LLM Context Management Context Compaction for LLM Agents
Institute for Artificial Intelligence and Simulation in Mechanics, Hamburg University of Technology, Eißendorfer Straße, 21073 Hamburg, Germany · Institute of Material Systems Modeling, Helmholtz-Zentrum Hereon, Max-Planck-Straße, 21502 Geesthacht, Germany · German Research Center for Artificial Intelligence (DFKI), Stuhlsatzenhausweg, 66123 Saarbrücken, Germany +3
The Coordination Tax and the Heterogeneity Dividend: Break-Even Conditions for Multi-Agent LLM Pipelines
Oct 25, 2026Andreas Zettl, Diego GosmarMulti-Agent LLMs LLM Agent Efficiency
Member, VoiceInteroperability.ai Linux Foundation AI & Data Berlin, Germany · Member, VoiceInteroperability.ai Linux Foundation AI & Data Turin, Italy
AgentBaton: Efficient Model Collaboration in Agentic Tasks
Oct 25, 2026Junlong Li, Jindong Jiang, Yonggan Fu +6LLM Agent Efficiency LLM Agent Orchestration
The Hong Kong University of Science and Technology · Project Leads · University of Illinois Urbana-Champaign
ReGE: Stronger Agents through Experience Synthesis
Oct 24, 2026Jiarong Liang, Yubo Wang, Zijie Liu +3Experience Learning for LLM Agents LLM Agent Self-Improvement
University of Waterloo · University of North Carolina at Chapel Hill · University of British Columbia
Build or Adopt? Custom-Built vs. General-Purpose LLM Agent Harnesses for Automotive GUI Testing
Oct 24, 2026Arsham Gholamzadeh Khoee, Ruyu Fu, Jiaqi Wei +4LLM Agent Harnesses Automated Software Testing
Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden · Volvo Group, Gothenburg, Sweden
AOS-Bench: Can LLM Agents Manage Dynamic Workloads?
Oct 23, 2026Erle Zhu, Genrui Zhang, Keyang Hu +2LLM Agent Orchestration Coding Agent Benchmarks
Tsinghua University · Columbia University
HarnessMM: Recursive Self-Improvement for Harness Token Efficiency
Oct 23, 2026Yuhua Jiang, Chang Xu, Feifei Gao +1Agent Harness Optimization LLM Agent Efficiency
Tsinghua University · Microsoft Research Asia (MSRA)
Speculative Forking: Turning Idle Wait into Parallel Exploration for Repository Environment Setup
Oct 23, 2026Yuling Shi, Mingchu Zhong, Zhensu Sun +8Software Engineering Agents LLM Agent Efficiency
Shanghai Jiao Tong University · Singapore Management University · The Chinese University of Hong Kong +4
When Agents Fail: Model or Harness--Who's to Blame?
Oct 23, 2026Shao Zhang, Hangfan Zhang, Yuanyuan Shi +9LLM Agent Evaluation LLM Agent Harnesses
Shanghai Artificial Intelligence Laboratory
Muffin - A Shared Memory Buffer for Asynchronous AI Agents
Oct 22, 2026Ping-Lin Kuo, Suman Navaratnarajah, Christian Frey +2Multi-Agent LLM Systems Shared-Memory Multi-Agent Systems
Department of Computer Science & Artificial Intelligence, University of Technology Nuremberg, Dr.-Luise-Herzberg-Straße 4, 90461 Nuremberg, Germany
Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control
Oct 22, 2026Bingyu Bai, Cheng Zhang, Erhu FengMobile GUI Agents LLM Agent Efficiency
Institute of Parallel and Distributed Systems (IPADS), Shanghai Jiao Tong University
Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3
Oct 21, 2026Jens Lehmann, Sahar VahdatiLLM Agent Harnesses Agent Harness Optimization
Amazon∗ · Technische Universität Dresden · Universität Hannover +1
SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents
Oct 21, 2026Kaijian Zou, Vaibhav Chennareddy, Yunxiang Zhang +5Coding Agents LLM Agent Verification
University of Michigan · The University of Texas at Austin
HGM-Dual: Lineage-Aware Guided Agent Harness Optimization for Long-Horizon Planning
Oct 21, 2026Sudipta Paul, Pengrui Quan, Aounon Kumar +3Agent Harness Optimization LLM Agent Self-Improvement
Samsung Research America
MemoryTax: The Bitter Lesson of Agent Memory
Oct 21, 2026Zedong PengMemory-Augmented Language Model Agents Memory Management for LLM Agents
Shanghai Jiao Tong University
Signals and Queries: Token-Efficient Agentic Context Discovery
Oct 21, 2026Yam MarcovitzLLM Agent Efficiency Text Classification
Credit Where Credit Is Due: Contrastive Attribution Topology Search for Multi-Agent Systems
Oct 21, 2026Fabian Tritthart, Tom ZehleMulti-Agent LLM Systems Multi-Agent Systems
University of Freiburg
Rewards for Budget-Aware Multi-Turn Agents That Adapt to Arbitrary Test-Time Constraints
Oct 20, 2026Tom A. Lamb, Adam Golinski, Eleonora Gualdoni +2LLM Agent Efficiency Reward Design for RL
Apple · University of Oxford
The More the Better? A Comparison of Single- and Multi-Agent LLM Setups on a Financial Review Task
Oct 20, 2026Pei LiuMulti-Agent LLM Systems LLM Agent Evaluation
School of Engineering and Applied Science, George Washington University, Washington, DC, USA
Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents
Oct 19, 2026Zhenyu Zhang, Kewei Fu, Yongqi Tong +4Tool-Using Agents LLM Agent Efficiency
Ant International
SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents
Oct 19, 2026Ran Zhou, Zehui Kong, Fanyu Lin +3Procedural Memory for LLM Agents LLM Agent Memory
School of Intelligence Science and Technology, Nanjing University
NIOCIS: Typed-Decision Next-Hop Routing with Node-Conditioned Option Spaces for Tool-Use Agents
Oct 19, 2026Jin Han, Mingfeng Xin, Feng Liang +1LLM Agent Routing LLM Agent Efficiency
Independent Researcher

Oct 27, 2026J/K move · Enter open · S save

Does Your Generalist Skill Optimizer Really Incentivize Agentic Tasks? Rethinking Skill Optimization via Bipartite Attribution

Jiawei Zhou, Bo Peng, Yuxuan Huang, Ming Zhang+3

Shanghai AI Laboratory · Fudan University · Shanghai Jiao Tong University+2

Agent Skill Learning LLM Agent Skill Evaluation LLM Agent Efficiency LLM Agent Evaluation

Open paper AskPDF arXiv

Skill optimizers adapt an agent to long-horizon tasks, such as repairing a terminal environment, by rewriting its skill, a natural-language procedure in its context, and keeping the edits that raise success on a small dev set. On such tasks success is noisy, so a gain on a small dev set does not show that an edit helps, and a success score does not show what the edit costs. We introduce BiPA, which replays an optimizer's acceptance rule on candidates identical to its seed to measure what selection alone reports, and records each episode as a bipartite graph of turns and the text they read to trace extra input tokens to the behavior behind them. Across three optimizers, three agentic benchmarks and two models, the learned skills succeed about as often as their hand-written seed, 0.1 points higher on average. Their dev gains vanish on test: keeping the best of several candidates on at most 30 tasks reports gains this large even when none changed. They read about 16% more input tokens: the optimizers almost always add rules, half to re-check work and some to act one call at a time, and the agent follows them as extra turns, each re-sending the whole conversation. Four principles follow: accept an edit only if its gain exceeds what selection alone reports; charge it for the turns it adds, not for its length; let the editor delete and merge rules; show it what earlier rules cost. Code is available at https://github.com/valleysprings/BiPA.git.