Agent Trajectory Analysis

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.

Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring. Existing approaches either evaluate complete trajectories in a single pass or partition them into independently scored windows, limiting their ability to connect evidence across temporally distant actions. We propose TRACE, a monitoring framework for long-horizon LLM agent trajectories. TRACE operates through a TIJ (Triage-Inspect-Judge) loop that identifies high-signal regions, performs targeted inspection while maintaining accumulated evidence across reasoning steps, and synthesizes a trajectory-level verdict. We evaluate TRACE on ten task domains from SHADE-Arena against state-of-the-art baselines. TRACE achieves an aggregate F1 of 0.713 and recall of 0.844, with the largest gains on tasks requiring long-range evidence linking.

Agent benchmarks increasingly record rich interaction trajectories, yet evaluation often reduces each rollout to a pass rate or reward score. We introduce TraceGraph, a graph-based framework that turns released multi-model agent trajectories into shared decision landscapes. For each task, TraceGraph builds a graph over observable action-observation states from pooled rollouts before model identity is introduced. It then overlays outcome-informed productive cores and trap regions, and summarizes each rollout with three events: Access, Trap exposure, and Repair. Across trajectories spanning five benchmark splits, TraceGraph profiles reveal navigation differences hidden by aggregate scores and show that splits differ in whether they reward avoiding traps or recovering from them. The same TraceGraph landscape also motivates a trap-aware recovery pipeline for SWE-bench: aruntime detector fires on states matching historical trap regions, then lightweight continuation policies are evaluated from the same prefix. On fired states, the best pooled single-factor policy raises official resolved rate from 40.4% to 43.5% on the per-provider fired subset and from 41.0% to 44.8% on common-fired instances, with provider-specific active components. Overall, TraceGraph provides a process vocabulary for asking what agent benchmarks test, where models diverge on a shared landscape, and how failure regions can guide downstream improvement.

Computation cost is a critical challenge for LLM agent systems, as their long-horizon trajectories continuously accumulate computational overhead. While existing studies focus on improving the overall efficiency of agent systems, the efficiency of individual steps remains largely unexplored. In this paper, we propose and formulate a new research problem: redundant step detection, aiming to detect these steps that consume substantial computational resources while contributing little or nothing to task completion. To support this initiative, we introduce RedundancyBench, a new benchmark that contains 1,920 trajectories collected from 6 different LLMs with 3,613 step-level annotations. Using RedundancyBench, we develop and evaluate 6 frontier LLMs and Jev as redundant step detectors, summarizing their strengths and limitations. Our experiments reveal that the redundant step detection is still challenging even for SOTA models, such as Claude-Opus-5, particularly without prior information. Code and dataset in this paper are both available in https://anonymous.4open.science/r/RedundancyBench-E0CB.

Autonomous agents such as Claude Code and Codex now operate for hours or even days. Understanding their runtime behavior has become critical for downstream tasks such as diagnosing inefficiencies, fixing bugs, and ensuring better oversight. A primary way to gain this understanding is analyzing the reasoning trajectories and execution traces these agents generate. Yet such data remains in unstructured natural-language form, making it difficult for humans to interpret at scale. We introduce ACTONOMY (a combination of Action and Taxonomy), a taxonomy for describing and analyzing agent behavior at runtime. ACTONOMY has two components: (1) the taxonomy itself, developed through Grounded Theory and structured as a three-level hierarchy of 10 actions, 46 subactions, and 120 leaf categories; and (2) an open repository that hosts the living taxonomy, provides an automated analysis pipeline that applies it to agent trajectories analysis, and defines an extension protocol for customization and growth. Our experiments show that ACTONOMY can compare behavioral profiles across agents and characterize a single agent's behavior across diverse trajectories, surfacing patterns indicative of failure modes. By providing a shared vocabulary, ACT*ONOMY helps researchers, agent designers, and end users interpret agent behavior more consistently, enabling better oversight and control.

Diffusion models for multi-agent trajectory prediction are limited by iterative denoising, which causes inference latency that hinders their use in time-critical settings like autonomous driving. Fast-sampling variants using DDIM and informed initial noise distributions partially alleviate this issue, but they either fail to achieve true single-step generation or are constrained by the chosen noise distribution. Consistency Models (CMs) offer high-quality one-step generation by mapping noise directly to data, but are difficult to train from scratch. We propose ECTraj, an enhanced CM pipeline with improved training and conditional generation for trajectory prediction. Our framework extends the student-teacher consistency training scheme: the student produces standard outputs, while the teacher explicitly fuses its predictions with parts of the ground truth to give stronger supervision. We also exploit CMs' direct denoising for top-K multi-shot generation during training. Combining conditional generation with this enhanced consistency objective yields faster inference and improved prediction accuracy, establishing competitive new benchmarks on the large-scale Argoverse 2 dataset.

LLM-based multi-agent systems are increasingly deployed for payment workflows, yet prevailing metrics, Task Success Rate (TSR) and Agent Handoff F1-Score (HF1), capture only final outcomes or unordered routing decisions. We introduce the Agentic Success Rate (ASR), a trajectory-fidelity metric that compares observed and expected agent execution sequences at the transition level, decomposing performance into Transition Recall and Transition Precision. Applied to the Hierarchical Multi-Agent System for Payments (HMASP) across 18 LLMs and 90,000 task instances, ASR reveals that 10 of 18 models systematically skip a confirmation checkpoint during payment checkout, a deviation invisible to both TSR and HF1, while 8 models enforce the checkpoint perfectly. Notably, GPT-4.1 exhibits hidden workflow shortcuts despite achieving perfect TSR and HF1, while GPT-5.2 achieves perfect ASR. Prompt refinements and deterministic routing guards guided by ASR diagnostics yield substantial TSR improvements, with gains up to +93.8 percentage points for previously struggling models, demonstrating that trajectory-level evaluation is essential in regulated domains.

Human behavior has the nature of mutual dependencies, which requires human-robot interactive systems to predict surrounding agents trajectories by modeling complex social interactions, avoiding collisions and executing safe path planning. While there exist many trajectory prediction methods, most of them do not incorporate the own motion of the ego agent and only model interactions based on static information. We are inspired by the humans theory of mind during trajectory selection and propose a Cross time domain intention-interactive method for conditional Trajectory prediction(CiT). Our proposed CiT conducts joint analysis of behavior intentions over time, and achieves information complementarity and integration across different time domains. The intention in its own time domain can be corrected by the social interaction information from the other time domain to obtain a more precise intention representation. In addition, CiT is designed to closely integrate with robotic motion planning and control modules, capable of generating a set of optional trajectory prediction results for all surrounding agents based on potential motions of the ego agent. Extensive experiments demonstrate that the proposed CiT significantly outperforms the existing methods, achieving state-of-the-art performance in the benchmarks.

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of intrinsic risk, where intrinsic failures remain latent, propagate across long-horizon execution, and eventually lead to high-consequence outcomes. To evaluate this setting, we introduce non-attack intrinsic risk auditing, a guard-oriented safety evaluation task, and present HINTBench, a benchmark of 596 agent trajectories, comprising 400 synthetic risky trajectories, 136 synthetic safe trajectories, 30 reconstructed real-world risky trajectories, and 30 reconstructed real-world safe trajectories, with an average length of 24.0 steps. HINTBench supports three tasks: risk detection, risk-step localization, and intrinsic failure-type identification, with annotations organized under a unified five-constraint taxonomy. Experiments reveal a substantial capability gap: strong LLMs perform well on trajectory-level risk detection, but the best model remains below 37 on fine-grained Strict-F1 for risk-step localization. Existing off-the-shelf guard models evaluated under their native prompts transfer poorly to this setting. These findings establish intrinsic risk auditing as an open challenge for agent safety.

Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation hard to observe. In these runs, an early misstep can trap the agent in unproductive loops or even cascade into fundamental errors, forming hidden error chains that make it hard to tell when the agent goes off track and why. Existing agent tracing analyses either focus on simple interaction or rely on small-scale manual inspection, which limits their scalability and usefulness for real coding workflows. We present CodeTracer, a tracing architecture that parses heterogeneous run artifacts through evolving extractors, reconstructs the full state transition history as a hierarchical trace tree with persistent memory, and performs failure onset localization to pinpoint the failure origin and its downstream chain. To enable systematic evaluation, we construct CodeTraceBench from a large collection of executed trajectories generated by four widely used code agent frameworks on diverse code tasks (e.g., bug fixing, refactoring, and terminal interaction), with supervision at both the stage and step levels for failure localization. Experiments show that CodeTracer substantially outperforms direct prompting and lightweight baselines, and that replaying its diagnostic signals consistently recovers originally failed runs under matched budgets. Our code and data are publicly available.

Trajectory prediction is a key component of autonomous driving systems because future motions directly affect collision checking, behavior planning, and control. The task remains challenging under dense interactions, heterogeneous behaviors, multimodal futures, and limited on-board computation. Existing graph, attention, and generative predictors improve interaction reasoning or uncertainty modeling, but their high-capacity designs are often costly for real-time deployment. Lightweight predictors and conventional distillation reduce inference cost, yet usually rely on static imitation and do not explicitly correct safety-relevant teacher bias. This paper proposes MAVEN-T, a reinforced heterogeneous distillation framework for real-time multi-agent trajectory prediction. A high-capacity teacher models directed local interactions with a surround-aware graph encoder, combines efficient temporal filtering with shifted-window spatial attention, and decodes maneuver-specific futures through a sparse Mixture-of-Experts head. A compact GRU--Squeeze-and-Excitation student with a Low-Rank Adapted policy head is trained by feature-, attention-, and semantic-level distillation. To align prediction with downstream behavior, the student is further refined by Proximal Policy Optimization rewards for collision avoidance, comfort, and progress, while a complexity-aware curriculum and Elastic Weight Consolidation stabilize stage-wise training. Experiments on NGSIM, HighD, MoCAD, Argoverse~2, and the Waymo Open Motion Dataset evaluate accuracy, efficiency, generalization, robustness, and closed-loop safety. The student achieves 6.2$\times$ parameter compression, 3.7$\times$ inference acceleration, and 14.6,ms latency on an NVIDIA Jetson AGX Orin while maintaining competitive accuracy.

Recent studies demonstrate that tool-calling capability enables large language models (LLMs) to interact with external environments for long-horizon financial tasks. While existing benchmarks have begun evaluating financial tool calling, they focus on limited scenarios and rely on call-level metrics that fail to capture trajectory-level reasoning quality. To address this gap, we introduce FinTrace, a benchmark comprising 800 expert-annotated trajectories spanning 34 real-world financial task categories across multiple difficulty levels. FinTrace employs a rubric-based evaluation protocol with nine metrics organized along four axes -- action correctness, execution efficiency, process quality, and output quality -- enabling fine-grained assessment of LLM tool-calling behavior. Our evaluation of 13 LLMs reveals that while frontier models achieve strong tool selection, all models struggle with information utilization and final answer quality, exposing a critical gap between invoking the right tools and reasoning effectively over their outputs. To move beyond diagnosis, we construct FinTrace-Training, the first trajectory-level preference dataset for financial tool-calling, containing 8,196 curated trajectories with tool-augmented contexts and preference pairs. We fine-tune Qwen-3-8B/32B using supervised fine-tuning followed by direct preference optimization (DPO) and show that training on FinTrace-Training consistently improves intermediate reasoning metrics, with DPO more effectively suppressing failure modes. However, end-to-end answer quality remains a bottleneck, indicating that trajectory-level improvements do not yet fully propagate to final output quality.

Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such systems are now deployed at scale, improving them post-deployment remains challenging. Agent trajectories are voluminous and non-deterministic, and reviewing each one, whether through human review or auxiliary LLMs, is slow and cost-prohibitive. We propose a lightweight, signal-based framework for triaging agentic interaction trajectories. Our approach computes cheap, broadly applicable signals from live interactions and attaches them as structured attributes for trajectory triage, identifying interactions likely to be informative without affecting online agent behavior. We organize signals into a coarse-grained taxonomy spanning interaction (misalignment, stagnation, disengagement, satisfaction), execution (failure, loop), and environment (exhaustion), designed for computation without model calls. In a controlled annotation study on $τ$-bench, a widely used benchmark for tool-augmented agent evaluation, we show that signal-based sampling achieves an 82% informativeness rate compared to 74% for heuristic filtering and 54% for random sampling, with a 1.52x efficiency gain per informative trajectory. The advantage is robust across reward strata and task domains, confirming that signals provide genuine per-trajectory informativeness gains rather than merely oversampling obvious failures. These results show that lightweight signals can serve as practical sampling infrastructure for agentic systems, and suggest a path toward preference data construction and post-deployment optimization.

Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human interaction logs such as clicks and dwell time. With the rapid emergence of large language model (LLM) powered search agents, however, retrieval is increasingly consumed by agents rather than human beings, and is embedded as a core component within multi-turn reasoning and action loops. In this setting, retrieval models trained under human-centric assumptions exhibit a fundamental mismatch with the way agents issue queries and consume results. In this work, we argue that retrieval models for agentic search should be trained directly from agent interaction data. We introduce learning to retrieve from agent trajectories as a new training paradigm, where supervision is derived from multi-step agent interactions. Through a systematic analysis of search agent trajectories, we identify key behavioral signals that reveal document utility, including browsing actions, unbrowsed rejections, and post-browse reasoning traces. Guided by these insights, we propose LRAT, a simple yet effective framework that mines high-quality retrieval supervision from agent trajectories and incorporates relevance intensity through weighted optimization. Extensive experiments on both in-domain and out-of-domain deep research benchmarks demonstrate that retrievers trained with LRAT consistently improve evidence recall, end-to-end task success, and execution efficiency across diverse agent architectures and scales. Our results highlight agent trajectories as a practical and scalable supervision source, pointing to a promising direction for retrieval in the era of agentic search.

Code agents resolve 65-70% of SWE-bench Verified issues, but Pass@1 cannot tell us why the rest fail, and, as we show, capable-model failures are systematically misdiagnosed without trajectory data. We introduce TRAJEVAL, a training-free decomposition of agent trajectories into reference-patch-aligned search, read, and edit stages, and apply it across 16,758 trajectories spanning three architectures and seven models. The dominant failure of capable models is not localization: 60-69% of failures on SWE-Agent and OpenHands reach and edit the correct functions yet still produce incorrect patches, and the pattern persists for most models on the bash-only LiveSWEAgent. Within this Edit-Quality residual, we identify Coherence Collapse, where the agent reaches correct code and then overwrites or thrashes it, as the largest theme, replicating across SWE-bench Verified and the multilingual PolyBench Verified. In 5 cases, the agent produces a patch bit-identical to the gold reference mid-trajectory and destroys it later; an edit-commit checkpoint recovers all 5 against the SWE-bench Docker harness. A reference-free consensus-driven variant yields a directional +3.0 pp Pass@1 measurement on GPT-5 (p=0.08).

Transitional autonomous vehicles (tAVs), which operate beyond SAE Level 1-2 automation but short of full autonomy, are increasingly sharing the road with human-driven vehicles (HDVs). As these systems interact during complex maneuvers such as lane changes, new patterns may emerge with implications for traffic stability and safety. Assessing these dynamics, particularly during mandatory lane changes, requires high-resolution trajectory data, yet datasets capturing tAV lane-changing behavior are scarce. This study introduces the North Carolina Transitional Autonomous Vehicle Lane-Changing (NC-tALC) Dataset, a high-fidelity trajectory dataset designed to characterize tAV interactions during lane-changing maneuvers. The dataset includes two controlled experimental series. In the first, tAV lane-changing experiments, a tAV executes lane changes in the presence of adaptive cruise control (ACC) equipped target vehicles, enabling analysis of lane-changing execution. In the second, tAV responding experiments, two tAVs act as followers and respond to cut-in maneuvers initiated by another tAV, enabling analysis of follower response dynamics. The dataset contains 152 trials (72 lane-changing and 80 responding trials) sampled at 20 Hz with centimeter-level RTK-GPS accuracy. The NC-tALC dataset provides a rigorous empirical foundation for evaluating tAV decision-making and interaction dynamics in controlled mandatory lane-changing scenarios.

AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a novel benchmark of 170 trajectories across 11 diverse task settings, including structured API workflows, incident management, and open-ended web/file tasks. Each trajectory is annotated with a critical failure step and a category from a grounded-theory derived, cross-domain failure taxonomy. To mitigate the human cost of failure attribution, we present AgentRx, an $\textit{automated diagnostic framework}$ that pinpoints the critical failure step in a failed agent trajectory. It synthesizes constraints, evaluates them step-by-step, and produces an auditable validation log of constraint violations with associated evidence; an LLM-based judge uses this log to localize the critical step and category. AgentRx improves step localization by 75% on average over prior work, while providing failure category attribution.

Bridging the past to the future, connecting agents both spatially and temporally, lies at the core of the trajectory prediction task. Despite great efforts, it remains challenging to explicitly learn and predict latencies, i.e., response intervals or temporal delays with which agents respond to various trajectory-changing events and adjust their future paths, whether on their own or interactively. Different agents may exhibit distinct latency preferences for noticing, processing, and reacting to a specific trajectory-changing event. The lack of consideration of such latencies may undermine the temporal continuity of forecasting systems, leading to implausible or unintended trajectories. Inspired by reverberation in acoustics, we propose a new reverberation transform and the corresponding Reverberation (Rev for short) trajectory prediction model, which predicts both individual latency preferences and their stochastic variations accordingly, by using two explicit and learnable reverberation kernels, enabling latency-conditioned and controllable trajectory prediction under both non-interactive and social latencies. Experiments on multiple datasets, whether of pedestrians or vehicles, demonstrate that Rev achieves competitive accuracy while revealing interpretable latency dynamics across agents and scenarios. Qualitative analyses further verify the properties of the reverberation transform, highlighting its potential as a general latency modeling approach.