Pith. sign in

REVIEW 15 cited by

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.03601 v4 pith:PLD2WB2X submitted 2025-04-04 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords datamodelsmulti-turnagentsapigen-mthttpsagenticblueprints
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Training effective AI agents for multi-turn interactions requires high-quality data that captures realistic human-agent dynamics, yet such data is scarce and expensive to collect manually. We introduce APIGen-MT, a two-phase framework that generates verifiable and diverse multi-turn agent data. In the first phase, our agentic pipeline produces detailed task blueprints with ground-truth actions, leveraging a committee of LLM reviewers and iterative feedback loops. These blueprints are then transformed into complete interaction trajectories through simulated human-agent interplay. We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters. Our models outperform frontier models such as GPT-4o and Claude 3.5 on $\tau$-bench and BFCL benchmarks, with the smaller models surpassing their larger counterparts, particularly in multi-turn settings, while maintaining superior consistency across multiple trials. Comprehensive experiments demonstrate that our verified blueprint-to-details approach yields high-quality training data, enabling the development of more reliable, efficient, and capable agents. We open-source 5K synthetic data trajectories and the trained xLAM-2-fc-r models to advance research in AI agents. Models at https://huggingface.co/collections/Salesforce/xlam-2-67ef5be12949d8dcdae354c4; Dataset at https://huggingface.co/datasets/Salesforce/APIGen-MT-5k and Website at https://apigen-mt.github.io

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation

    cs.CL 2026-07 conditional novelty 7.0 of 10

    Top-K teacher logits can preserve almost all probability mass while dropping the low-probability '<tool call>' token, biasing distilled models to over-use tools; restoring the omitted token reduces over-calling 14.2%→...

  2. ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

    cs.CL 2026-06 conditional novelty 7.0 of 10

    ISE creates 23,132 execution-grounded multi-turn OS agent trajectories via intent simulation and live execution, improving agent performance on ClawEval from 19.3 to 37.7 pass@1 with Qwen3-8B.

  3. Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL

    cs.AI 2026-05 conditional novelty 7.0 of 10

    Masked diffusion language models, not larger autoregressive LLMs, are the better building block for text-based world models in agentic RL, improving rollout fidelity, diversity, and downstream task success.

  4. rStar2-Agent: Agentic Reasoning Technical Report

    cs.CL 2025-08 conditional novelty 7.0 of 10

    A 14B model trained with agentic RL and a resample-on-correct rollout strategy scores 80.6% on AIME24 and 69.8% on AIME25, nearly matching DeepSeek-R1 (671B) in one week on 64 GPUs.

  5. Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Hidden-state traces of frozen LLMs/VLMs can be read by lightweight trained heads to predict when to defer, clarify, call tools, or abstain, cutting routed inference cost 27–90%.

  6. Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints

    eess.SP 2026-07 conditional novelty 6.0 of 10

    Pointwise constrained fine-tuning via sample-wise augmented Lagrangians and learned relaxations reduces tail constraint violations across safety, tool-calling, and re-ranking while preserving average task performance.

  7. Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls

    cs.SE 2026-02 conditional novelty 6.0 of 10

    A simulated tool environment with argument validation, response synthesis, and task-state feedback improves LLM tool-call accuracy at test time.

  8. Agent Learning via Early Experience

    cs.AI 2025-10 conditional novelty 6.0 of 10

    Training agents to predict consequences of their own alternative actions (implicit world modeling) or to reflect on why expert actions were better (self-reflection) consistently improves task success, OOD generalizati...

  9. UserBench: An Interactive Gym Environment for User-Centric Agents

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A new multi-turn agent benchmark shows that current LLMs elicit fewer than 30% of user preferences and reach full intent alignment only about 20% of the time.

  10. Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

    cs.AI 2026-02 conditional novelty 5.0 of 10

    BAO, a behavior-enhanced SFT plus regularized RL pipeline, improves proactive agents' task performance while lowering user-involvement rate, beating UserRL baselines on three UserRL gym tasks.

  11. Benchmarking and Learning Real-World Customer Service Dialogue

    cs.CL 2025-10 conditional novelty 5.0 of 10

    OlaMind, a Learn-to-Think plus basic-to-hard RL pipeline for RAG customer service, reports +28.92% issue resolution, -6.08% human transfer online, and an 8.6% offline hallucination rate.

  12. How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $\tau$-bench

    cs.CL 2025-08 conditional novelty 5.0 of 10

    IRMA reformulates tool-agent inputs with memory, domain constraints, and tool suggestions, and reports improved tau-bench pass^5 reliability over ReAct, function calling, and self-reflection.

  13. The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI

    cs.CY 2025-06 conditional novelty 4.0 of 10

    A position paper claiming existing data and AI regulations are unprepared for synthetic data generated by and for agentic AI, recommending targeted legal amendments and new standards.

  14. MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility

    cs.CL 2025-05 reject novelty 4.0 of 10

    MedOrch is a modular framework in which LLMs call medical tools to answer clinical questions; its headline results on Alzheimer's, chest X-ray, and VQA benchmarks are weakened by best-of-five scoring.

  15. CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions

    cs.CL 2025-05 conditional novelty 4.0 of 10

    CRMArena-Pro is an expert-validated benchmark showing LLM agents struggle with multi-turn business tasks and confidentiality, with top agents scoring about 58% single-turn and near-zero refusal rates.

Pith tools