Image de couverture de livre

Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cai, Yuandao, Zhu, Yuzhang, Gao, Liyou, Tang, Wensheng, Qin, Shengchao
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ConCovUp: Effective Agent-Based Test Driver Generation for Concurrency Testing
par: Cai, Yuandao, et autres
Publié: (2026)

FROAV: A Framework for RAG Observation and Agent Verification -- Lowering the Barrier to LLM Agent Research
par: Lin, Tzu-Hsuan, et autres
Publié: (2026)

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
par: Wang, Peiran, et autres
Publié: (2025)

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents
par: Cai, Yuandao, et autres
Publié: (2026)

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
par: Kuntz, Thomas, et autres
Publié: (2025)

MASTEST: A LLM-Based Multi-Agent System For RESTful API Tests
par: Han, Xiaoke, et autres
Publié: (2025)

Your Code Agent Can Grow Alongside You with Structured Memory
par: Deng, Yi-Xuan, et autres
Publié: (2026)

MooseAgent: A LLM Based Multi-agent Framework for Automating Moose Simulation
par: Zhang, Tao, et autres
Publié: (2025)

Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
par: Manglik, Akshay, et autres
Publié: (2026)

Boosting Path-Sensitive Value Flow Analysis via Removal of Redundant Summaries
par: Wang, Yongchao, et autres
Publié: (2025)

BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis
par: Jasper, Surya, et autres
Publié: (2025)

Measuring Agents in Production
par: Pan, Melissa Z., et autres
Publié: (2025)

AgentForge: A Flexible Low-Code Platform for Reinforcement Learning Agent Design
par: Junior, Francisco Erivaldo Fernandes, et autres
Publié: (2024)

The Dual-State Architecture for Reliable LLM Agents
par: Thompson, Matthew
Publié: (2025)

Exploring LLM-based Agents for Root Cause Analysis
par: Roy, Devjeet, et autres
Publié: (2024)

Bootstrapping Coding Agents: The Specification Is the Program
par: Monperrus, Martin
Publié: (2026)

Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap
par: Kim, Naryeong, et autres
Publié: (2026)

ReCodeAgent: A Multi-Agent Workflow for Language-agnostic Translation and Validation of Large-scale Repositories
par: Ibrahimzada, Ali Reza, et autres
Publié: (2026)

PostTrainBench: Can LLM Agents Automate LLM Post-Training?
par: Rank, Ben, et autres
Publié: (2026)

The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents
par: Yu, Shasha, et autres
Publié: (2026)

Agint: Agentic Graph Compilation for Software Engineering Agents
par: Chivukula, Abhi, et autres
Publié: (2025)

daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
par: Jiang, Mohan, et autres
Publié: (2026)

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
par: Golubev, Alexander, et autres
Publié: (2025)

Data Requirement Goal Modeling for Machine Learning Systems
par: Yamani, Asma, et autres
Publié: (2025)

Can Coding Agents Be General Agents?
par: Ivanov, Maksim, et autres
Publié: (2026)

CA2: Code-Aware Agent for Automated Game Testing
par: Adaikkappan, Valliappan Chidambaram, et autres
Publié: (2026)

SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
par: Raghavendra, Mohit, et autres
Publié: (2026)

Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
par: Yoon, Juyeon, et autres
Publié: (2025)

From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization
par: Xi, Haoran, et autres
Publié: (2025)

CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories
par: Xiao, Yijia, et autres
Publié: (2025)

SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow
par: Bula, Timothy, et autres
Publié: (2025)

Programming with Pixels: Can Computer-Use Agents do Software Engineering?
par: Aggarwal, Pranjal, et autres
Publié: (2025)

More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents
par: Gao, Pengfei, et autres
Publié: (2025)

ReVeal: Self-Evolving Code Agents via Reliable Self-Verification
par: Jin, Yiyang, et autres
Publié: (2025)

SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations
par: Wang, Shuaiqi, et autres
Publié: (2026)

Cerberus: Multi-Agent Reasoning and Coverage-Guided Exploration for Static Detection of Runtime Errors
par: Dhulipala, Hridya, et autres
Publié: (2025)

Concept-Guided LLM Agents for Human-AI Safety Codesign
par: Geissler, Florian, et autres
Publié: (2024)

Cleaning Maintenance Logs with LLM Agents for Improved Predictive Maintenance
par: Dimidov, Valeriu, et autres
Publié: (2025)

GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents
par: Wu, Jie JW, et autres
Publié: (2025)

Follow Your Nose -- Which Code Smells are Worth Chasing?
par: Amit, Idan, et autres
Publié: (2021)