# TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories

arXiv: https://arxiv.org/abs/2605.31308 · HTML: https://mlsanity.com/paper/2605.31308/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 19 of 19)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025)
- [Benchmark Test-Time Scaling of General LLM Agents](https://mlsanity.com/paper/2602.18998/) (2026)
- [Process-Centric Analysis of Agentic Software Systems](https://mlsanity.com/paper/2512.02393/) (2025)
- [Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM](https://mlsanity.com/paper/2505.13890/) (2025)
- [The Shape of Reasoning: Topological Analysis of Reasoning Traces in Large Language Models](https://mlsanity.com/paper/2510.20665/) (2025)
- [SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning](https://mlsanity.com/paper/2605.14619/) (2026)
- [Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart](https://mlsanity.com/paper/2601.11940/) (2026)

## Built on by (most cited first, 1 of 1)

- [AgentPProf: Semantic Profiler for Long Horizon AI Agents](https://mlsanity.com/paper/2609.20301/) (2026)

## Abstract (arXiv)

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.