TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories
Summary
TraceGraph is a graph-based framework that constructs shared decision landscapes from multi-model agent trajectories, enabling diagnosis of failure regions and improvement via trap-aware recovery pipelines.
View Cached Full Text
Cached at: 06/01/26, 09:27 AM
# TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories Source: [https://arxiv.org/abs/2605.31308](https://arxiv.org/abs/2605.31308) [View PDF](https://arxiv.org/pdf/2605.31308) > 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\. ## Submission history From: Junjie Nian \[[view email](https://arxiv.org/show-email/23d7ba74/2605.31308)\] **\[v1\]**Fri, 29 May 2026 13:40:31 UTC \(1,139 KB\)
Similar Articles
TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents
TRACE is a monitoring framework for long-horizon LLM agent trajectories that uses a Triage-Inspect-Judge loop to connect evidence across temporally distant actions, achieving high recall and F1 on evasive sabotage detection tasks.
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
This paper proposes TRACE, a trajectory-level safety detection method for long-horizon LLM agents that compresses full trajectory evidence into a latent state to better aggregate dispersed risk signals, achieving state-of-the-art accuracy on multiple benchmarks.
Using Grounded Theory for Agent Behavior Analysis at Scale
AutoTraceGT automates grounded theory analysis on agent trajectories to build behavioral taxonomies, effectively recovering human failure-mode annotations and improving downstream prediction tasks.
TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation
TrajGenAgent proposes a hierarchical LLM agent framework that decouples macro-level activity planning from micro-level spatiotemporal instantiation for realistic human mobility trajectory generation without fine-tuning. It also introduces an anomaly-detection-based evaluation for behavioral fidelity.
SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents
Introduces SciTrace, a framework that integrates safety reasoning into every stage of scientific agent pipelines using a Safety-Intrinsic Reasoning Loop and a Compositional Tool-Chain Verifier, achieving state-of-the-art safety while preserving output quality.