Agent Trajectory Analysis

Follow this topic Ask about this topic

Agent trajectory analysis examines sequences of actions or movements, from autonomous vehicles and pedestrians to language-model agents using tools. Methods include social and physics-guided motion prediction, trace and graph representations, step-level evaluation, and attribution of failures or reusable behaviors. Benchmarks and trajectory-level measures reveal inefficiency, unsafe steps, and procedural differences that final success scores can miss. A central challenge is reliably connecting events across long histories to outcomes, while balancing detailed diagnosis with scalable, efficient evaluation.

Latest papers

48 papers6 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Agent trajectories as programs: fingerprinting and programming coding-agent behavior
Jun 15, 2026Hamidah OderinwaleAI Coding Agents AI Agent Evaluation
Work done with support from Taste Labs
TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents
Jun 5, 2026Vijitha Mittapalli, Shreyaa Jayant Dani, Satya Srujana Pilli +7Long-Horizon Agent Evaluation AI Agent Security
University of Massachusetts at Amherst · Adobe Research · Dolby Labs +2
TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories
May 29, 2026Junjie Nian, Kang Chen, Ge Zhang +2Agent Reliability Software Engineering Benchmarks
1Fudan University · 2ByteDance · 3Shanghai Innovation Institute
Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories
May 28, 2026Liang Zhu, Bo Yang, Zhinuo Zhou +5LLM Agent Evaluation Agent Trajectory Analysis
Huawei Technologies, Noah Arks’ Lab · Institute of Computing Technology, Chinese Academy of Sciences
How to Interpret Agent Behavior
May 13, 2026Jie Gao, Kaiser Sun, Jen-tse Huang +8Hierarchical Classification AI Agent Monitoring
1Johns Hopkins University · 2California Institute of Technology · 3Northeastern University +1
ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction
May 9, 2026Alen Mrdovic, Qingze, Liu +6Trajectory Generation Multi-Agent Trajectory Prediction
Tony · Rutgers University, New Brunswick · The College of New Jersey
Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems
May 7, 2026Donghao Huang, Joon Kiat Chua, Zhaoxia WangFinancial Services Multi-Agent LLM Systems
School of Computing and Information Systems, Singapore Management University, 80 Stamford Rd, Singapore 178902, Singapore · Research and Development, Mastercard, 4250 Fairfax Dr, Arlington, VA 22203, USA
Chatting about Conditional Trajectory Prediction
Apr 20, 2026Yuxiang Zhao, Wei Huang, Haipeng Zeng +2Multi-Agent Trajectory Prediction Human Behavior Prediction
Sun Yat-sen University · Alibaba Group
HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark
Apr 15, 2026Jiacheng Wang, Jinchang Hou, Fabian Wang +3AI Agent Auditing Long-Horizon Agent Evaluation
Baidu Inc., Beijing, China · Beijing Institute of Technology, Beijing, China
CodeTracer: Towards Traceable Agent States
Apr 13, 2026Han Li, Yifan Yao, Letian Zhu +13AI Coding Agents Agent Trajectory Analysis
Nanjing University · Alibaba Group · Renmin University of China +3
MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
Apr 11, 2026Wenchang Duan, Zhenguo Gao, Jinguo Xian +1Model Compression Multi-Agent Trajectory Prediction
School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, China · Bio-X Institutes, Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders, Shanghai Jiao Tong University, Shanghai 200030, China · Shanghai Key Laboratory of Psychotic Disorders, and Brain Science and Technology Research Center, Shanghai Jiao Tong University, Shanghai 200030, China
FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks
Apr 11, 2026Yupeng Cao, Haohang Li, Weijin Liu +11Agent Trajectory Analysis LLM Tool Use
Stevens Institute of Technology · Independent Researcher · The FinAI +2
Signals: Trajectory Sampling and Triage for Agentic Interactions
Apr 1, 2026Shuguang Chen, Adil Hafeez, Salman ParachaAgent Trajectory Analysis AI Agent Monitoring
DigitalOcean Holdings, Inc.
Learning to Retrieve from Agent Trajectories
Mar 30, 2026Yuqi Zhou, Sunhao Dai, Changle Qu +3Agent Trajectory Analysis Agentic Retrieval
Gaoling School of Artificial Intelligence, Renmin University of China · CAS Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences
Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
Mar 25, 2026Myeongsoo Kim, Dingmin Wang, Siwei Cui +6Agent Failure Analysis AI Coding Agents
AWS AI Labs · Monash University
Introducing the transitional autonomous vehicle lane-changing dataset: Empirical Experiments
Mar 5, 2026Abhinav Sharma, Zijun He, Danjue ChenAutonomous Driving Datasets Autonomous Driving
Department of Civil, Construction and Environmental Engineering, North Carolina State University, Raleigh, North Carolina, USA
AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
Feb 2, 2026Shraddha Barke, Arnav Goyal, Alind Khare +3Fault Diagnosis AI Agent Reliability
1Microsoft Research · 2Microsoft · 3UIUC
Reverberation: Learning the Latencies Before Forecasting Trajectories
Nov 14, 2025Conghao Wong, Ziqian Zou, Beihao Xia +1Multi-Agent Trajectory Prediction Agent Trajectory Analysis
School of Electronic Information and Communications, Huazhong University of Science and Technology, and National Anti-Counterfeit Engineering Research Center

Jun 15, 2026J/K move · Enter open · S save

Agent trajectories as programs: fingerprinting and programming coding-agent behavior

Hamidah Oderinwale

Work done with support from Taste Labs

AI Coding Agents AI Agent Evaluation Language Model Fingerprinting Agent Trajectory Analysis Process-Based Agent Evaluation

Open paper AskPDF arXiv

Benchmark scores tell you what an agent got right; they do not tell you how it got there. In this work, we introduce methods for comparing agents procedurally in different contexts, where the model, tasks, and approaches vary. We compare ten agents and find that they are identifiable by their behavioral habits, which we define as fingerprints: a probe over these procedural signatures attributes an unseen trajectory to the correct agent at 85.7% accuracy, controlling for leakage across tasks. We develop procedural representations for agent problem-solving procedures with an emergent vocabulary induction technique that is meant to be maximally compressive to avoid surface-level variation while being expressive enough to unveil the quirks of the models' patterns. We apply our framework to the software engineering evaluation dataset SWE-Bench to study the structural distinctness of agent trajectories and find that behavior is most similar between models from similar release periods and those that are distilled from one another (e.g., a distilled student model and its teacher have a Jensen-Shannon divergence of 0.25, about half the distance between other model pairs). As more models saturate evaluations, we believe that it will be important to probe model behavior along more holistic dimensions than success rates alone. We introduce ProcGrep, a library for auditing and evaluating agents for how they approach tasks at a procedural level given their traces in a top-down fashion. We believe this work has a range of applications to help developers work with and program coding agents, such as task-aware model routing, agent monitoring, and finer-grained cost analysis.