AgentTrails: Towards Trust and Reuse for Agentic Tasks
- URL: http://arxiv.org/abs/2607.18816v1
- Date: Tue, 21 Jul 2026 07:53:58 GMT
- Title: AgentTrails: Towards Trust and Reuse for Agentic Tasks
- Abstract summary: LLM-powered agents tackle complex tasks by invoking tools, querying databases, executing code, and manipulating intermediate artifacts.<n>These agents follow trajectories that are typically stored as chronological logs, obscuring the underlying dataflow.<n>We present AgentTrails, a prototype system for agent provenance and sensemaking.
- Score: 12.615897924172812
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: LLM-powered agents increasingly tackle complex tasks by invoking tools, querying databases, executing code, and manipulating intermediate artifacts. These agents follow trajectories that are typically stored as chronological logs, obscuring the underlying dataflow -- the dependencies between their actions and the artifacts they create and manipulate. This limits developers' ability to understand the agents' trails, compare executions, debug failures, and re-use the computations. We present AgentTrails, a prototype system for agent provenance and sensemaking. AgentTrails converts raw trajectories into structured provenance graphs, where tool calls are modeled as computational actions and inputs and outputs as data artifacts. The system supports the comparison of executions by placing multiple provenance graphs on a shared canvas and constructing a joined quotient graph that aligns recurring tools, artifacts, and dependency structures across trajectories. On top of this representation, AgentTrails supports pattern extraction, downstream analysis, and skill abstraction. We demonstrate AgentTrails on real-world agent trajectories, showing that it reveals hidden dependencies, aligns divergent executions, and surfaces recurring tool-use patterns beyond chronological logs.
Related papers
- Agent ATO: Visualizing Agent Interaction Timelines from Logs [1.5639957559514246]
Agent ATO is a tool for visualizing AI coding agent interaction timelines from console logs.<n>In addition to an all-interaction timeline, Agent ATO provides filtered timelines that emphasize file discovery, file reading, file editing, and execution.
arXiv Detail & Related papers (2026-09-08T06:22:44Z) - Inference-Time Graph Engineering for Multi-Agent LLM Workflows [51.56038180639833]
We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs.<n>We show that ReActNet consistently improves over fixed-topology and learned-topology baselines while maintaining competitive inference cost.
arXiv Detail & Related papers (2026-09-04T23:32:11Z) - WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents [53.426679066400844]
We introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery.<n>We develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout.<n>We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image.
arXiv Detail & Related papers (2026-08-28T08:28:43Z) - LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents [2.9951905451976106]
LEDGER builds trace graphs over observed agent sessions.<n>We show how the resulting traces expose workflow decisions, artifact lineage, repair steps, validation steps, and claim-support paths for evidence-centered audit.
arXiv Detail & Related papers (2026-08-19T00:10:04Z) - Execution-First Synthetic Tool-Use Trace Generation for LLM Agents [10.291533584425252]
SyntheticAgentTraceQA is an execution- first framework for generating scalable supervision data for tool- augmented agents.<n>We evaluate the framework across four tool ecosystems and use the resulting data to fine-tune and evaluate Qwen model variants.
arXiv Detail & Related papers (2026-07-31T08:52:26Z) - AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs [7.897669686886619]
We present AgentFlow, the first static analysis framework for recovering and analyzing agent dependencies from agent programs.<n>AgentFlow supports a range of analyses for agent governance and security, including prompt-to-tool risk detection.<n>We implement AgentFlow for five representative agent frameworks and evaluate it on AgentZoo, a corpus of 5,399 real-world agent programs.
arXiv Detail & Related papers (2026-07-02T03:11:41Z) - From Question Answering to Task Completion: A Survey on Agent System and Harness Design [67.8241530947325]
This survey examines LLM-based agents through a model-harness lens.<n>We first clarify the functional definition of agents and the implementation view of an LLM-based agent as a foundation model and an execution harness.<n>We then analyze the limits of model-centric scaling, trace four paradigms of agent engineering, and decompose the execution harness into six coupled runtime responsibilities.
arXiv Detail & Related papers (2026-06-14T05:40:16Z) - How to Interpret Agent Behavior [56.59836196946289]
We introduce ACT*ONOMY, a taxonomy for describing and analyzing agent behavior at runtime.<n>By providing a shared vocabulary, ACT*ONOMY helps researchers, agent designers, and end users interpret agent behavior more consistently.
arXiv Detail & Related papers (2026-05-13T14:52:40Z) - CodeTracer: Towards Traceable Agent States [40.51936201889185]
We present CodeTracer, a tracing architecture that parses heterogeneous run artifacts through evolving extractors.<n>CodeTracer reconstructs the full state transition history as a hierarchical trace tree with persistent memory.<n>It performs failure onset localization to pinpoint the failure origin and its downstream chain.
arXiv Detail & Related papers (2026-04-13T15:52:03Z) - Learning to Retrieve from Agent Trajectories [72.8923565916533]
We argue that retrieval models for agentic search should be trained directly from agent interaction data.<n>We introduce learning to retrieve from agent trajectories as a new training paradigm, where supervision is derived from multi-step agent interactions.<n>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.
arXiv Detail & Related papers (2026-03-30T17:59:02Z) - DLLM Agent: See Farther, Run Faster [94.74432470237817]
Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
arXiv Detail & Related papers (2026-02-07T09:01:18Z) - AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
arXiv Detail & Related papers (2025-10-06T23:20:49Z) - Open Agent Specification (Agent Spec): A Unified Representation for AI Agents [10.685555728094338]
We introduce Open Agent Specification (Agent Spec), a declarative language that defines AI agents and agentic.<n>Agent Spec defines a common set of components, control and data flow semantics, and schemas that allow an agent to be defined once and executed across different runtimes.
arXiv Detail & Related papers (2025-10-05T12:26:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.