Pith. sign in

REVIEW 7 cited by

MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use

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 2508.18669 v1 pith:GEFG2KKU submitted 2025-08-26 cs.AI

MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use

classification cs.AI
keywords learningtoolagenticmulti-turnreinforcementagentusersdynamic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

With the recent rapid advancement of Agentic Intelligence, agentic tool use in LLMs has become increasingly important. During multi-turn interactions between agents and users, the dynamic, uncertain, and stochastic nature of user demands poses significant challenges to the agent's tool invocation capabilities. Agents are no longer expected to simply call tools to deliver a result; rather, they must iteratively refine their understanding of user needs through communication while simultaneously invoking tools to resolve user queries. Existing reinforcement learning (RL) approaches for tool use lack the integration of genuinely dynamic users during the RL training process. To bridge this gap, we introduce MUA-RL (Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use), a novel reinforcement learning framework that, for the first time in the field of agentic tool use, integrates LLM-simulated users into the reinforcement learning loop. MUA-RL aims to enable autonomous learning of models to communicate with users efficiently and use various tools to solve practical problems in dynamic multi-turn interactions. Evaluations are done on several multi-turn tool-using benchmarks (see Figure 1). Specifically, MUA-RL-32B achieves 67.3 on TAU2 Retail, 45.4 on TAU2 Airline, 28.3 on TAU2 Telecom, 28.4 on BFCL-V3 Multi Turn, and 82.5 on ACEBench Agent -- outperforming or matching the performance of larger open-source models such as DeepSeek-V3-0324 and Qwen3-235B-A22B in non-thinking settings.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents

    cs.AI 2026-05 unverdicted novelty 7.0

    Tool-use agents suffer large accuracy drops from reward and transition perturbations but domain-randomized RL on static perturbations closes about 27% of the unseen transition gap while retaining most clean performance.

  2. SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators

    cs.CL 2026-05 unverdicted novelty 7.0

    SalesSim benchmarks MLLMs as retail user simulators, finds gaps in persona adherence and over-persuasion, and introduces UserGRPO RL to raise decision alignment by 13.8%.

  3. Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning

    cs.LG 2026-04 unverdicted novelty 7.0

    This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.

  4. CurateEvo: Data-Curation Evolving for Agentic Post-Training

    cs.CL 2026-07 conditional novelty 6.0

    CurateEvo evolves executable data-curation code using failed agent trajectories, improving post-training performance by 3.2 and 2.7 points over baselines on labeled and wild data respectively.

  5. Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments

    cs.CL 2026-06 unverdicted novelty 6.0

    PROVE trains LLMs on multi-step tool calls using 20 live MCP servers with 343 tools, state-grounded synthesis, and adaptive efficiency rewards, delivering gains of up to 10.2 points on BFCL Multi-Turn and similar on o...

  6. Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

    cs.AI 2026-04 unverdicted novelty 6.0

    Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.

  7. Trust Region On-Policy Distillation

    cs.LG 2026-05 unverdicted novelty 5.0

    TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.