LLM Agent Reliability

LLM: Large Language Model

LLM agent reliability studies whether agents can complete tasks correctly, follow instructions and safety constraints, use evidence faithfully, and behave consistently across repeated or extended interactions. Common approaches combine structured harnesses and deterministic tool interfaces with state tracking, evidence checks, runtime monitoring, calibrated abstention, and recovery from failures; training methods also teach agents to verify actions or learn from execution feedback. Evaluations increasingly use interactive benchmarks, noisy or changing tools, repeated trials, and trajectory-level measures alongside final task success. A central tension is that added reasoning, delegation, memory, or orchestration can improve some tasks but also introduce new failure paths, so reliability depends on the model, harness, tools, and evaluation setting together.

Latest papers

843 papers181 papers in the last four weeks, up 93% on the four weeks before. 1.0% of all new papers.

ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents
May 18, 2026Jiawei He, Jie Jia, Chenbo Liu +4AI Coding Agents LLM Agent Evaluation
Amap, Alibaba Group
STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery
May 18, 2026Jiarui Su, Songjun Tu, Bei Sun +1LLM Self-Refinement AI Agents for Scientific Discovery
Central South University · Institute of Automation, Chinese Academy of Sciences · Pengcheng Laboratory
VerifyMAS: Hypothesis Verification for Failure Attribution in LLM-based Multi-Agent Systems
May 17, 2026Hezhe Qiao, Hanghang Tong, Ee-Peng Lim +2Agent Failure Analysis Multi-Agent LLM Systems
Singapore Management University · University of Illinois at Urbana-Champaign · University of Illinois at Chicago
Taming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution
May 17, 2026Taolin Zhang, Pukun Zhao, Qizhou Chen +5Multi-Agent LLM Systems Multi-Agent Coordination
School of Computer Science and Information Engineering, Hefei University of Technology · Guangdong University of Finance and Economics · East China Normal University +1
ContractBench: Can LLM Agents Preserve Observation Contracts?
May 17, 2026Jicheng Wang, Yifeng He, Zili Wang +3AI Agent Reliability LLM Agent Evaluation
University of California, Davis · University of Southern California · University of Hong Kong
Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
May 16, 2026Carol Xuan Long, David Simchi-Levi, Feng Zhu +3AI Agent Reliability Multi-Agent Systems
Harvard University · MIT/Purdue · MIT +2
To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
May 16, 2026Wei Shi, Ziheng Peng, Sihang Li +4Tool-Augmented Language Model Agents Causal Interventions in Language Models
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Renmin University of China +2
R2V Agent: Teaching SLMs When to Ask for Help
May 15, 2026Raghu Vamshi Hemadri, Humaira Firdowse Mohammed, Rishabh Maheshwary +5AI Agent Reliability Tool-Augmented Language Model Agents
New York University Tandon School of Engineering · University of California, San Diego · ServiceNow Research +3
PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures
May 15, 2026Yunan Lu, Luigi Liu, Omar Yahia +2AI Agent Reliability Adversarial Prompt Generation
Columbia University · University of California San Diego · Walmart
The Scaling Laws of Skills in LLM Agent Systems
May 15, 2026Charles Chen, Qiming Yu, Yuhang Gu +12Language Model Scaling Laws LLM Agent Reliability
Evolvent AI Team
paper.json: A Coordination Convention for LLM-Agent-Actionable Papers
May 15, 2026Arquimedes CanedoDocument Information Extraction LLM Agents
PRISM: Prompt Reliability via Iterative Simulation and Monitoring for Enterprise Conversational AI
May 15, 2026Keshava Chaitanya, Jahnavi GundakaramLLM Prompting LLM Agent Evaluation
STAR: A Stage-attributed Triage and Repair framework for RCA Agents in Microservices
May 15, 2026Junle Wang, Xingchuang Liao, Wenjun WuAgent Failure Analysis Root Cause Analysis
School of Artificial Intelligence, Beihang University
Runtime-Structured Task Decomposition for Agentic Coding Systems
May 14, 2026Shubhi Asthana, Bing Zhang, Chad DeLuca +2Software Engineering Agents Agentic Workflows
IBM Research · San Jose, California · Zoom +2
Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol
May 14, 2026Anantha SharmaAI Agent Reliability Multi-Agent LLM Systems
Synechron Inc · Charlotte, NC, USA
Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay
May 14, 2026Xiaohua Wang, Kai Yu, XuXiao Liang +2LLM Inference Efficiency AI Agent Reliability
1Artificial Intelligence Research Center, Bengbu Medical University, Bengbu 233000, China. · 2CHARMMIRAEL Biotech Co., Ltd, Nanjing 210000, China.
ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation
May 13, 2026Tarun MittalAI Agent Reliability LLM Agent Orchestration
Octave-X
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
May 13, 2026Yize Cheng, Chenrui Fan, Mahdi JafariRaviz +2LLM Tool Use LLM Agent Reliability
University of Maryland, College Park
Proof-Carrying Certificates for LLM Pipelines: A Trust-Boundary Architecture
May 13, 2026George KoomullilLLM Grounding LLM Auditing
Ascendr, Inc.
AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
May 13, 2026Hailin Zhong, Shengxin ZhuSoftware Engineering Agents Agent Evaluation
Hong Kong Baptist University, Hong Kong, China · Beijin Normal University, Zhuhai, China
An Agentic LLM-Based Framework for Population-Scale Mental Health Screening
May 13, 2026Giuliano Lorenzoni, Paulo Alencar, Donald CowanLLM Agent Orchestration Clinical NLP
University of Waterloo · Waterloo, Ontario, Canada
Useful Memories Become Faulty When Continuously Updated by LLMs
May 13, 2026Dylan Zhang, Yanshan Lin, Zhengkun Wu +4AI Agent Reliability Persistent Memory for Language Models
University of Illinois Urbana-Champaign · IIIS, Tsinghua University
When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
May 13, 2026Young Hyun Cho, Will Wei SunAnytime-Valid Inference Sequential Hypothesis Testing
Department of Statistics, Purdue University. · Mitch Daniels School of Business, Purdue University.
No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents
May 12, 2026Zixu Yang, Hang Zheng, Nan Jiang +5AI Agent Reliability Multi-Agent LLM Systems
1X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · 2Shanghai Innovation Institution, Shanghai, China · 3Jiangsu Key Lab of Language Computing, Suzhou, China
CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation
May 12, 2026Chenying Lin, Yichen Hai, Yi He +3LLM Agent Orchestration LLM Agent Evaluation
Shanghai Ultradimension Technology Co., Ltd., Shanghai, China · College of Logistics Engineering, Shanghai Maritime University, Shanghai, 201306, China · School of Civil Aviation, Northwestern Polytechnical University, Xi’an 710072, China +3
gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy
May 11, 2026Tousif Islam, Digvijay Wadekar, Zihan ZhouGravitational-Wave Astronomy AI Coding Agents
Kavli Institute for Theoretical Physics, University of California Santa Barbara, Kohn Hall, Lagoon Rd, Santa Barbara, CA 93106 · Center for Gravitational Physics, University of Texas at Austin, Austin, TX 78712, USA · Department of Physics, Princeton University, Princeton, NJ 08540, USA
From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems
May 11, 2026Ruizhe Zhou, Xiaoyang Liu, Gaoyuan Du +4Algorithmic Auditing ML Reproducibility
Amazon.com USA
Engineering Robustness into Personal Agents with the AI Workflow Store
May 11, 2026Roxana Geambasu, Mariana Raykova, Pierre Tholoniat +3Agentic Workflows LLM Agent Security
Columbia University and Google · Google
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
May 11, 2026Yuanyang Li, Xue Yang, Longyue Wang +2LLM Agent Evaluation AI Agent Benchmarks
1Zhejiang University · 2Zhejiang Lab · 3Alibaba Group
The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
May 11, 2026Xinrun Wang, Chang Yang, He Zhao +2Self-Improving Agents Long-Horizon LLM Agents
Singapore Management University · The Hong Kong Polytechnic University · Nanyang Technological University +2

May 18, 2026J/K move · Enter open · S save

ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents

Jiawei He, Jie Jia, Chenbo Liu, Chaoyi Xue+3

Amap, Alibaba Group

AI Coding Agents LLM Agent Evaluation AI Agent Benchmarks LLM Agent Reliability

Open paper AskPDF arXiv

Existing benchmarks for LLM coding agents primarily evaluate final outcomes. While useful for measuring overall capability, these metrics provide limited visibility and often miss defects that arise during execution. We present ProcCtrlBench, a benchmark for execution-process evaluation in LLM coding agents. ProcCtrlBench organizes recurrent execution defects into a reusable ontology covering 11 defect types in 4 categories, and evaluates agent trajectories through standardized process evidence rather than final outcomes alone. To support comparison across heterogeneous agents, ProcCtrlBench standardizes raw logs into a unified trajectory representation and reports calibrated scorecards over process-level findings. In addition, ProcCtrlBench uses control preservation as a way to quantify execution-process quality, capturing whether execution remains interpretable, interruptible, correctable, reversible, and able to hand back authority when needed. We evaluate ProcCtrlBench on 200 cases sampled from three benchmarks: AndroidBench, TerminalBench, and SWE-bench-Verified. Results show that ProcCtrlBench can be instantiated with useful reliability, provides more stable semantics than direct thresholding, and reveals meaningful differences in execution quality that are often overlooked by conventional outcome-based evaluation.