COVENANT: Natural-Language Workflow Compilation for Aligned Agent Execution

• URL: http://arxiv.org/abs/2607.25400v1
• Date: Tue, 28 Jul 2026 07:59:50 GMT
• Title: COVENANT: Natural-Language Workflow Compilation for Aligned Agent Execution
• Abstract summary: We propose COVENANT, a compiler-and-interpreter architecture for workflow-aligned agent execution.<n>Our key insight is to treat workflow instructions as source programs rather than prompts.<n>COVENANT converts the instructions into a workflow abstract syntax tree (WAST) and lowers it to a workflow control-flow graph (WCFG)
• Score: 12.755574564434788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) agents are increasingly entrusted with natural-language workflow instructions (e.g., retail-payment policies) that specify not only what outcome to achieve, but also which steps, branches, and tool interactions are permitted. When these instructions are supplied as prompt context, however, the model retains control over both procedure selection and step execution. As interactions accumulate, an agent can skip required steps, take unsupported branches, or execute a valid step with unsupported arguments or effects--a failure mode we call workflow misalignment. In this work, we propose COVENANT, a compiler-and-interpreter architecture for workflow-aligned agent execution. Our key insight is to treat workflow instructions as source programs rather than prompts. COVENANT converts the instructions into a workflow abstract syntax tree (WAST) and lowers it to a workflow control-flow graph (WCFG). At runtime, a controller interprets the WCFG one node at a time, checks each proposal against requirements extracted from the instructions before committing controller state or advancing the graph, and returns diagnostic feedback for repair. To evaluate COVENANT, we use 120 cases from three existing benchmarks, spanning seven workflow scenarios. Compared with state-of-the-art LLM agents, COVENANT improves benchmark success from 50.00% to 83.33% and reduces the workflow-misalignment failure rate from 42.50% to 15.83% (62.75% relative). These results show that COVENANT substantially mitigates workflow misalignment, moving LLM-agent alignment beyond isolated prompt following toward reliable execution of complex and multi-step workflows.

Related papers

• Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution [23.207195503032136]
  Artic is an artifact-driven workflow compiler that transforms a natural-language workflow into an artifact-driven workflow.<n>We show that compiled by Artic are 32 and 56 percentage points more consistent in cross-model and repeated-execution setups.
  arXiv  Detail & Related papers  (2026-08-21T17:47:47Z)
• FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows [6.767792769288717]
  FlowScout is an execution-guided framework for generating tool-integrated agentic from historical task-solving records.<n>It first mines a common tool coordination from historical records to construct an initial workflow.<n>It then refines the workflow topology through Monte Carlo tree search guided by execution feedback.
  arXiv  Detail & Related papers  (2026-08-10T08:41:59Z)
• 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)
• ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents [61.184954205350984]
  ClawArena-Team is a benchmark of 41 multi-turn, multimodal, multi-agent scenarios spanning 258 evaluation rounds and 72 staged updates.<n>All scoring is execution-based with no LLM judge: an overall score -- the Subagent-Management Score (SMS) -- multiplies task correctness by a least-privilege and modality-routing factor.
  arXiv  Detail & Related papers  (2026-06-30T06:06:08Z)
• GraphFlow: An Architecture for Formally Verifiable Visual Workflows Enabling Reliable Agentic AI Automation [0.0]
  GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in mission-critical processes.<n>Existing workflow platforms provide durable execution and observability but offer few semantic correctness guarantees.<n>A year-long pilot across three clinical sites executed 8,728 cohort-enrolled workflow runs with a 97.08% completion rate.
  arXiv  Detail & Related papers  (2026-05-14T15:33:05Z)
• Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows [67.92316850084575]
  We introduce Claw-Eval-Live, a live benchmark for workflow agents.<n>Each release is constructed from public workflow-demand signals.<n>Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts.
  arXiv  Detail & Related papers  (2026-04-30T17:23:19Z)
• AgentSPEX: An Agent SPecification and EXecution Language [17.439531520677594]
  We introduce AgentSPEX, an agent framework with explicit control flow and modular structure.<n>AgentSPEX supports typed steps, branching and loops, parallel execution, reusable submodules, and explicit state management.<n>We show through a user study that AgentSPEX provides a more interpretable and accessible workflow-authoring paradigm than a popular existing agent framework.
  arXiv  Detail & Related papers  (2026-04-14T23:16:25Z)
• Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL [0.15199492741752027]
  We propose an Information-Flow-Orchestrated Multi-Agent Paradigm via Agent-to-Agent (A2A) Communication.<n>We evaluate our approach on the general-purpose benchmark GAIA, using the representative workflow-based MAS as the baseline.<n>Our method achieves 63.64% accuracy, outperforming OWL's 55.15% by 8.49 percentage points with comparable token consumption.
  arXiv  Detail & Related papers  (2026-01-14T21:35:51Z)
• Monadic Context Engineering [59.95390010097654]
  This paper introduces Monadic Context Engineering (MCE) to provide a formal foundation for agent design.<n>We demonstrate how Monads enable robust composition, how Applicatives provide a principled structure for parallel execution, and crucially, how Monad Transformers allow for the systematic composition of these capabilities.<n>This layered approach enables developers to construct complex, resilient, and efficient AI agents from simple, independently verifiable components.
  arXiv  Detail & Related papers  (2025-12-27T01:52:06Z)
• A Declarative Language for Building And Orchestrating LLM-Powered Agent Workflows [0.0]
  We present a declarative system that separates agent workflow specification from implementation.<n>Our results demonstrate 60% reduction in development time, and 3x improvement in deployment velocity compared to imperative implementations.<n>We show that complex involving product search, personalization, and cart management can be expressed in under 50 lines of DSL compared to 500+ lines of imperative code.
  arXiv  Detail & Related papers  (2025-12-22T05:03:37Z)
• FlowAgent: Achieving Compliance and Flexibility for Workflow Agents [31.088578094151178]
  FlowAgent is a novel agent framework designed to maintain both compliance and flexibility.<n>Building on PDL, we develop a comprehensive framework that empowers LLMs to manage OOW queries effectively.<n>We present a new evaluation methodology to rigorously assess an LLM agent's ability to handle OOW scenarios.
  arXiv  Detail & Related papers  (2025-02-20T07:59:31Z)
• Flow: Modularized Agentic Workflow Automation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)

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.