Execution-First Synthetic Tool-Use Trace Generation for LLM Agents

• URL: http://arxiv.org/abs/2607.29175v1
• Date: Fri, 31 Jul 2026 08:52:26 GMT
• Title: Execution-First Synthetic Tool-Use Trace Generation for LLM Agents
• Abstract summary: 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.
• Score: 10.291533584425252
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic software-engineering and industrial systems increasingly operate through executable workflows rather than code genera- tion alone: they search artifacts, invoke tools, inspect structured observations, and query databases. Training these agents requires supervision data that captures valid tool interactions and executable workflows. However, traditional query-first data synthesis can fail because plausible user requests may not correspond to valid tool sequences, compatible parameters, or available data. To address this limitation, we propose SyntheticAgentTraceQA, an execution- first framework for generating scalable supervision data for tool- augmented agents. Our framework first constructs high-level work- flow structures, maps them to available tools through dependency- aware assignment, executes and validates the resulting traces in con- trolled environments, and only then synthesizes natural-language user tasks, teacher-generated reasoning annotations, and reference answers. We evaluate the framework across four tool ecosystems and use the resulting data to fine-tune and evaluate Qwen model variants. The results show that execution-grounded supervision improves tool execution behavior, reference-trace agreement, and answer-generation performance on the evaluated tasks. Further analysis reveals a supervision trade-off: masked supervision, which excludes reasoning annotations from the training objective, im- proves final-answer metrics, whereas full supervision, computing loss over the complete assistant output including reasoning tokens, underperforms on answer quality and does not consistently im- prove reference-trace agreement, particularly at the 9B scale. These findings highlight the importance of designing synthetic supervi- sion according to the desired capabilities of tool-augmented agents.

Related papers

• Terminal Agents: A Survey of AI Agents in Command-Line Environments [102.48222742145474]
  Large language model agents increasingly act through terminals, yet existing surveys disperse terminal-mediated behavior across software engineering, tool use, and computer-use research.<n>We regard terminal agents as systems whose dominant progress-bearing action--observation loop is mediated by terminal command execution, textual feedback, and stateful environment interaction.<n>Our synthesis shows that realized behavior is jointly shaped by the model, interface, harness, runtime, and environment.
  arXiv  Detail & Related papers  (2026-08-20T18:16:44Z)
• FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis [37.074035615771066]
  FACET (Fine-grained Agentic Construction of Executable Tasks) is a framework that addresses both information preservation and cross-artifact consistency.<n>It reconstructs related agent skills into coherent, information-rich scenarios, then realizes and repairs the execution environment.<n>It produces complex terminal tasks with dense executable checks, and successful trajectories collected from these tasks provide effective, data-efficient supervision.
  arXiv  Detail & Related papers  (2026-08-19T06:19:20Z)
• 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)
• Formal Verification of Agentic Systems over Operational Data [59.98246281888422]
  Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world where they act on persistent operational data.<n>Existing approaches do not provide such system-level guarantees.<n>We study here the verification of agentic systems comprising a single LLM and a tool orchestration harness over relational operational data.
  arXiv  Detail & Related papers  (2026-08-04T13:01:30Z)
• From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents [56.187590188698955]
  Large Language Models have enabled increasingly capable autonomous agents, yet personalization remains critical for making such agents practically useful.<n>Recent benchmarks have begun evaluating personalization in agents, but they largely rely on static preference snapshots, fixed interaction logs, or question answering over predefined user profiles.<n>We introduce IBA-Bench, a benchmark for implicit behavioral alignment constructed from longitudinal interaction histories.<n>We propose IBA-Agent, an agent framework that reconciles conflicting priorities through broad retrieval and trajectory-level alignment.
  arXiv  Detail & Related papers  (2026-08-03T12:52:04Z)
• 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)
• Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows [18.6534256358905]
  We introduce Harness-Bench, a diagnostic benchmark for evaluating configuration-level harness effects in realistic agent systems.<n>The benchmark contains 106 sandboxed offline tasks constructed from practical agent-use patterns.<n>Across 5,194 execution trajectories, we observe substantial variation in completion, process quality, efficiency, and failure behavior.
  arXiv  Detail & Related papers  (2026-05-27T03:47:35Z)
• Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception [18.565166776233223]
  Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration.<n>We propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA)<n>SPECTRA bootstraps agentic capabilities via Coldstart Reinforcement Learning for SVLMs.
  arXiv  Detail & Related papers  (2026-04-19T15:06:30Z)
• GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows [90.35728421223673]
  GTA-2 is a hierarchical benchmark for General Tool Agents (GTA)<n>Built on real-world authenticity, it leverages real user queries, deployed tools, and multimodal contexts.<n>Experiments reveal a pronounced capability cliff: while frontier models already struggle on atomic tasks, top models achieving only 14.39% success.
  arXiv  Detail & Related papers  (2026-04-17T05:36:00Z)
• Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent [45.450766613995135]
  Tool-Genesis is a diagnostic benchmark designed to quantify agent capabilities across multiple dimensions.<n>We find that even state-of-the-art models struggle to produce precise tool interfaces or executable logic in a one-shot setting.
  arXiv  Detail & Related papers  (2026-03-05T17:44:29Z)
• FABRIC: Framework for Agent-Based Realistic Intelligence Creation [3.940391073007047]
  Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments.<n>We present a unified framework for synthesizing agentic data using only LLMs, without any human-in-the-loop supervision.
  arXiv  Detail & Related papers  (2025-10-20T18:20:22Z)
• Agentic Predictor: Performance Prediction for Agentic Workflows via Multi-View Encoding [56.565200973244146]
  Agentic Predictor is a lightweight predictor for efficient agentic workflow evaluation.<n>By learning to approximate task success rates, Agentic Predictor enables fast and accurate selection of optimal agentic workflow configurations.
  arXiv  Detail & Related papers  (2025-05-26T09:46:50Z)
• Large Language Models as Realistic Microservice Trace Generators [48.730974361862366]
  This paper proposes a first-of-a-kind approach that relies on training a large language model (LLM) to generate synthetic workload traces.<n>We show that TraceLLM produces diverse, realistic traces under varied conditions, outperforming existing approaches in both accuracy and validity.<n>TraceLLM adapts to downstream trace-related tasks, such as predicting key trace features and infilling missing data.
  arXiv  Detail & Related papers  (2024-12-16T12:48:04Z)
• Learning to Use Tools via Cooperative and Interactive Agents [58.77710337157665]
  Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. We propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. Our experiments on three datasets show that the LLMs, when equipped with ConAgents, outperform baselines with substantial improvement.
  arXiv  Detail & Related papers  (2024-03-05T15:08:16Z)

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.