TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories

• URL: http://arxiv.org/abs/2605.31308v1
• Date: Fri, 29 May 2026 13:40:31 GMT
• Title: TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories
• Abstract summary: We introduce TraceGraph, a graph-based framework that turns released multi-model agent trajectories into shared decision landscapes.<n>For each task, TraceGraph builds a graph over observable action-observation states from pooled rollouts before model identity is introduced.<n>It then overlays outcome-informed productive cores and trap regions, and summarizes each rollout with three events: Access, Trap exposure, and Repair.
• Score: 61.51984029109709
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• VeriGraph: Towards Verifiable Data-Analytic Agents [71.17693022916896]
  LLM-based agents have demonstrated strong capabilities in data-intensive analytical tasks, yet their outputs are rarely verifiable.<n>We propose VeriGraph, a traceable neuro-symbolic reasoning framework that enables agents to construct an explicit heterogeneous evidence directed acyclic graph.<n>Our results suggest that explicit evidence-graph construction is a promising path toward verifiable data-analytic agents.
  arXiv  Detail & Related papers  (2026-06-15T11:50:56Z)
• PathRouter: Aligning Rewards with Retrieval Quality in Agentic Graph Retrieval-Augmented Generation [41.730631759393525]
  Agentic GraphRAG trains language-model agents to iteratively retrieve and reason over graph-structured evidence.<n>We present Path, a path-aware training framework for agentic GraphRAG.
  arXiv  Detail & Related papers  (2026-06-15T08:48:04Z)
• Can Graph-Based Microservice Performance Detection Be Used for Microservice Intrusion Detection? [0.0]
  This paper asks whether graph-based microservice performance detection can also serve as a foundation for microservice intrusion detection.<n>We deploy a Docker Compose based synthetic e-commerce microservice benchmark, run 50 controlled trials across five attack types under normal workloads, and collect metrics, logs, and distributed traces.<n>We train a two-layer graph convolutional network for 6-way classification over 21,438 request graphs. The model 96.2% test accuracy with a macro F1 of 0.955 under a graph-level random split.
  arXiv  Detail & Related papers  (2026-05-22T23:30:38Z)
• WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representation [13.14840279219976]
  We present WebGraphEval, a framework that abstracts trajectories from multiple agents into a unified, weighted action graph.<n>We show that WebGraphEval captures cross-model regularities, highlights redundancy and inefficiency, and identifies critical decision points overlooked by outcome-based metrics.
  arXiv  Detail & Related papers  (2025-10-22T03:29:25Z)
• GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding [13.356521655409422]
  Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries.<n>We propose GraphCogent, a collaborative agent framework that decomposes graph reasoning into specialized cognitive processes: sense, buffer, and execute.
  arXiv  Detail & Related papers  (2025-08-17T14:28:38Z)
• GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval [3.792463570467098]
  GraphRunner is a novel graph-based retrieval framework that operates in three distinct stages: planning, verification, and execution.<n>It significantly reduces reasoning errors and detects hallucinations before execution.<n>Our evaluation using the GRBench dataset shows that GraphRunner consistently outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-07-11T18:10:01Z)
• UniGoal: Towards Universal Zero-shot Goal-oriented Navigation [68.45058159533376]
  We propose a general framework for universal zero-shot goal-oriented navigation.<n>We propose a uniform graph representation to unify different goals, including object category, instance image and text description.<n>Our UniGoal achieves state-of-the-art zero-shot performance on three studied navigation tasks with a single model.
  arXiv  Detail & Related papers  (2025-03-13T17:59:48Z)
• A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizability [17.075744814372936]
  We have constructed a comprehensive benchmark that includes 17 graph pooling methods and 28 different graph datasets.<n>This benchmark systematically assesses the performance of graph pooling methods in three dimensions, i.e., effectiveness, robustness, and generalizability.
  arXiv  Detail & Related papers  (2024-06-13T12:04:40Z)
• Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework [76.70603443624012]
  We propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. OSTrack achieves state-of-the-art performance on multiple benchmarks, in particular, it shows impressive results on the one-shot tracking benchmark GOT-10k.
  arXiv  Detail & Related papers  (2022-03-22T18:37:11Z)
• GraphDCA -- a Framework for Node Distribution Comparison in Real and Synthetic Graphs [72.51835626235368]
  We argue that when comparing two graphs, the distribution of node structural features is more informative than global graph statistics. We present GraphDCA - a framework for evaluating similarity between graphs based on the alignment of their respective node representation sets.
  arXiv  Detail & Related papers  (2022-02-08T14:19:19Z)
• Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement [54.29252286561449]
  We propose a two-stage graph-based and model-agnostic framework, called Graph-PCNN. In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled. In the second stage, for each guided point, different visual feature is extracted by the localization. The relationship between guided points is explored by the graph pose refinement module to get more accurate localization results.
  arXiv  Detail & Related papers  (2020-07-21T04:59:15Z)

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.