View-oriented Conversation Compiler for Agent Trace Analysis

arXiv 2603.29678 ↗First posted 31 Mar 2026cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We observe that an agent trace is a structured document. A coding agent session contains user turns, assistant text, chain of thought blocks, tool calls, tool results, subagent invocations, compaction boundaries, and harness injected directives, and may exceed ten thousand JSONL lines. Effective trace analysis requires a lossless record, a session level overview, and content retrieval with conversational roles. To this end, we propose VCC, namely View oriented Conversation Compiler, which lexes, parses, and lowers a raw JSONL log into three views based on one intermediate representation. The full view provides the lossless transcript and defines the line number coordinate system. The UI view reconstructs the interaction perceived by the user. The adaptive view selects relevant trace content and preserves role annotations and line range pointers. Line numbers are assigned before view lowering, ensuring that all pointers can be resolved to the full view. We evaluate VCC in a context engineering experiment on AppWorld by varying the input format of the reflector. Experiments with three model configurations and two test splits show that VCC improves aggregate task goal pass rates by 1.1 to 4.2 points, reduces reflector token consumption by one half to two thirds, and generates smaller memory files. These results demonstrate the effectiveness of trace format as an important component of context engineering infrastructure.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 54 references that are in the map. First posted on arXiv 31 Mar 2026.

Builds on

45 of 54 references.

References · 45

2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107

33 more

2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 359
2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 349
2025Memory in the Age of AI Agentscited by 285
2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 146
2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 136
2024Does Prompt Formatting Have Any Impact on LLM Performance?cited by 132
2025A Survey of Context Engineering for Large Language Modelscited by 120
2025Context Length Alone Hurts LLM Performance Despite Perfect Retrievalcited by 118
2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 105
2025TRAIL: Trace Reasoning and Agentic Issue Localizationcited by 98
2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 95
2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agentscited by 69
2026AgentRx: Diagnosing AI Agent Failures from Execution Trajectoriescited by 53
2024AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learningcited by 52
2025Reducing Cost of LLM Agents with Trajectory Reductioncited by 44
2025The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Managementcited by 40
2026AgentOCR: Reimagining Agent History via Optical Self-Compressioncited by 22
2025Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinementcited by 17
2026Trajectory-Informed Memory Generation for Self-Improving Agent Systemscited by 16
2025Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimizationcited by 15
2026Active Context Compression: Autonomous Memory Management in LLM Agentscited by 15
2026LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growthcited by 12
2025Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewritingcited by 10
2026AgentStepper: Interactive Debugging of Software Development Agentscited by 8
2026AgentTrace: A Structured Logging Framework for Agent System Observabilitycited by 8
2025Solving Context Window Overflow in AI Agentscited by 4
2026TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Tracescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

2026From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flawscited by 21

Similar, not cited

Close in wording, no citation either way