mlsanityData to 14 Oct 2026

OrchDAG: Complex Tool Orchestration in Multi-Turn Interactions with Plan DAGs

arXiv 2510.24663 ↗First posted 28 Oct 2025cs.AIcited by 1

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Agentic tool use has gained traction with the rise of agentic tool calling, yet most existing work overlooks the complexity of multi-turn tool interactions. We introduce OrchDAG, a synthetic data generation pipeline that models tool execution as directed acyclic graphs (DAGs) with controllable complexity. Using this dataset, we benchmark model performance and propose a graph-based reward to enhance RLVR training. Experiments show that the dataset presents a challenging but solvable benchmark, and the proposed reward is effective when combined with GRPO-style algorithms, highlighting the importance of leveraging topological structure and data complexity in multi-turn tool use.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 11 of its 22 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

11 of 22 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Tool-Planner: Task Planning with Clusters across Multiple Tools6 Jun
  2. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models12 Mar

Other references · 9

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  4. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  5. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  6. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 627
  7. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  8. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systemscited by 111
  9. 2025A Technical Survey of Reinforcement Learning Techniques for Large Language Modelscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DAGent: Evaluate-then-Grow Planning for Deep Research Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues
  2. 2026PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
  3. 2026Simulating Complex Multi-Turn Tool Calling Interactions in Stateless Execution Environments
  4. 2025Procedural Environment Generation for Tool-Use Agents
  5. 2026UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
  6. 2026OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction
  7. 2026RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents
  8. 2026The World Won't Stay Still: Programmable Evolution for Agent Benchmarks