Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark

• URL: http://arxiv.org/abs/2608.00106v1
• Date: Fri, 31 Jul 2026 07:00:49 GMT
• Title: Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark
• Abstract summary: We introduce an executable benchmark and a budget-aware meta-router that composes heterogeneous operations from raw task text.<n>Results: learned success falls to 75.9% and trails static routing at 93.5%, while remaining 49% cheaper and exceeding one-shot routing by 34.3 points.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it. A controller may answer directly, decompose a request, retrieve evidence, execute code, delegate to a specialist, or verify an intermediate result. Existing routing work largely selects model endpoints, retrieval depth, or tools in isolation. We introduce an executable benchmark and a budget-aware meta-router that composes heterogeneous operations from raw task text. The benchmark contains 216 training, 72 development, 108 held-out test, and 108 locked lexical-shift challenge tasks across data analysis, frozen-corpus research, and document processing. Outcomes are machine checked after operations execute. Independent regularized logistic heads predict operation probabilities from word and character features, are temperature-scaled on development data, and are greedily composed under route-cost and action-count budgets. On the held-out test, the learned policy achieves 100% success versus 93.5% for strong static and fixed workflows, with 43% lower cost than the static policy; a matched learned one-shot router reaches 56.5%. On the untouched challenge split, learned success falls to 75.9% and trails static routing at 93.5%, while remaining 49% cheaper and exceeding one-shot routing by 34.3 points. The gap identifies lexical generalization, rather than route execution, as the principal limitation. These results establish a reproducible testbed and a bounded proof of concept, not evidence of live-LLM performance.

Related papers

• TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution [0.0]
  TRIAGE is a three-level routing framework that reduces token consumption by reusing historical execution trajectories.<n>Its core innovation is Tjectory-as-a-Skill, which abstracts historical execution trajectories into reusable skills.<n>In large-scale experiments on 1,007 security monitoring queries, TRIAGE achieves 62.3% token savings.
  arXiv  Detail & Related papers  (2026-09-01T15:40:09Z)
• ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts [0.0]
  Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes.<n>We present ClawProBench, a trace-aware benchmark for runtime-native agent evaluation instantiated on OpenClaw.
  arXiv  Detail & Related papers  (2026-08-23T17:09:02Z)
• Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents [60.650808962786364]
  We study whether native MoE router traces can guide steering and selection without an external judge or selection-time test execution.<n>Our analysis shows that routing provides a robust behavioral role signal; token-granular readouts and decision-matched comparison sets turn it into effective control.<n>We evaluate on SWE-bench Verified using open-weight sparse MoE agents across scales and reasoning-effort settings.
  arXiv  Detail & Related papers  (2026-08-23T03:07:03Z)
• UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations [68.29650478987561]
  UI-Mate is a foundation GUI agent that integrates an environment-grounded training stack with in-context demonstration learning.<n>It sets a new open-weight state of the art on general computer-use benchmarks, scoring 77.0% on OSWorld and 66.2% on WindowsAgentArena.
  arXiv  Detail & Related papers  (2026-08-16T20:59:59Z)
• Demystifying Agent Skills: Why They Work-Until They Don't [58.92875630998418]
  Existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: emphtextbfWhen do skills help, why do they work, and where do they fail?<n>We isolate the effects of representation, outcome annotation, retrieval difficulty, and cross-framework of skills.<n>We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes.
  arXiv  Detail & Related papers  (2026-08-14T07:26:38Z)
• MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing [0.0]
  We present MetaRoute-Bench, an open, inspectable framework for comparing meta-decision policies under a shared execution model.<n>A task-aware compositional policy achieves 79.4% success compared with 76.7% for a strong workload-specific static policy.<n>Relative to the static policy, this is a 2.7 percentage-point improvement with paired 95% CI of plus or minus 2.0 points, at 4.7% higher mean cost and 6.4% higher latency.
  arXiv  Detail & Related papers  (2026-07-31T07:01:21Z)
• Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution [1.733151600403503]
  Large language model (LLM) agents increasingly automate multi-step engineering and informatics.<n>They often follow a maximum-context-first strategy--re-reading files and dependencies they have already seen--turning a one-line edit into a small code-base audit.<n>We argue the missing capability is task-aware execution-scope estimation.
  arXiv  Detail & Related papers  (2026-07-14T17:59:31Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing [81.51044612408793]
  SkillAudit is a framework for evolving agent skills without ground-truth feedback.<n>To turn behavioral differences into edit guidance, SkillAudit uses Process-Aligned Contrastive Evaluation.<n>It routes edits through two pipelines: Refine removes noisy or irrelevant guidance from broadly useful skills, while Repair replaces passages that conflict with the task.
  arXiv  Detail & Related papers  (2026-06-12T08:20:09Z)
• Learning Agent Routing From Early Experience [55.88886987958933]
  Boundary is a training-free routing framework that uses early behavioral experience and rubric-guided reasoning to decide whether to answer a query with direct inference or escalate to an agent.<n>We show that Boundary reduces inference time by 60.6% compared to the agent while improving performance by 28.6% over direct LLM inference.
  arXiv  Detail & Related papers  (2026-05-08T03:18:40Z)
• LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents [63.75550089045995]
  Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information.<n>We propose that effective context management should be adaptive: parts of the agent's trajectory are maintained at different levels of detail depending on their current relevance to the task.<n>We develop LongSeeker, a long-horizon search agent fine-tuned from Qwen3-30B-A3B on 10k synthesized trajectories.
  arXiv  Detail & Related papers  (2026-05-06T17:54:16Z)
• Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies [29.138677906501865]
  We introduce Workspace-Bench, a benchmark for evaluating AI agents on Workspace Learning involving Large-Scale File Dependencies.<n>We construct realistic workspaces with 5 worker profiles, 74 file types, 20,476 files (up to 20GB) and curate 388 tasks, each with its own file dependency graph, evaluated across 7,399 total rubrics.
  arXiv  Detail & Related papers  (2026-05-05T10:17:06Z)
• 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)
• OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks [52.87238755666243]
  We present OmniEAR, a framework for evaluating how language models reason about physical interactions, tool usage, and multi-agent coordination in embodied tasks.<n>We model continuous physical properties and complex spatial relationships across 1,500 scenarios spanning household and industrial domains.<n>Our systematic evaluation reveals severe performance degradation when models must reason from constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:54:15Z)
• Toward Generation of Test Cases from Task Descriptions via History-aware Planning [9.483085498004508]
  In automated web testing, generating test scripts from natural language task descriptions is crucial for enhancing the test generation process.<n>This activity involves creating the correct sequences of actions to form test scripts for future testing activities.<n>We introduce HxAgent, an iterative large language model agent planning approach that determines the next action based on: 1) observations of the current contents and feasible actions, 2) short-term memory of previous web states and actions, and 3) long-term experience with (in)correct action sequences.
  arXiv  Detail & Related papers  (2025-04-19T16:03:03Z)

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.