mlsanityData to 7 Oct 2026

Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model

arXiv 2502.08820 ↗First posted 12 Feb 2025cs.AI cs.CLcited by 20

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large Language Models (LLMs) with API-calling capabilities enabled building effective Language Agents (LA), while also revolutionizing the conventional task-oriented dialogue (TOD) paradigm. However, current approaches face a critical dilemma: TOD systems are often trained on a limited set of target APIs, requiring new data to maintain their quality when interfacing with new services, while LAs are not trained to maintain user intent over multi-turn conversations. Because both robust multi-turn management and advanced function calling are crucial for effective conversational agents, we evaluate these skills on three popular benchmarks: MultiWOZ 2.4 (TOD), BFCL V3 (LA), and API-Bank (LA), and our analyses reveal that specialized approaches excel in one domain but underperform in the other. To bridge this chasm, we introduce CoALM (Conversational Agentic Language Model), a unified approach that integrates both conversational and agentic capabilities. We created CoALM-IT, a carefully constructed multi-task dataset that interleave multi-turn ReAct reasoning with complex API usage. Using CoALM-IT, we train three models CoALM 8B, CoALM 70B, and CoALM 405B, which outperform top domain-specific models, including GPT-4o, across all three benchmarks. This demonstrates the feasibility of a single model approach for both TOD and LA, setting a new standard for conversational agents.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 23 of its 41 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

23 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Calling16 Feb

Other references · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2024The Llama 3 Herd of Modelscited by 14,192
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  10. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  11. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  12. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
10 more
  1. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  2. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  3. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  4. 2024ToolACE: Winning the Points of LLM Function Callingcited by 204
  5. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  6. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 86
  7. 2024Hammer: Robust Function-Calling for On-Device Language Models via Function Maskingcited by 53
  8. 2024Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Taskscited by 52
  9. 2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
  10. 2024Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channelcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 12; 2026: 8.

20 papers.

Sort:

By area:

  1. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  2. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  3. 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Datacited by 31
  4. 2025MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool usecited by 30
  5. 2025Self-Improving LLM Agents at Test-Timecited by 30
  6. 2025AgentRM: Enhancing Agent Generalization with Reward Modelingcited by 25
  7. 2025ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filteringcited by 19
  8. 2026Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Modelscited by 10
  9. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  10. 2026From Failure to Mastery: Generating Hard Samples for Tool-use Agentscited by 8
  11. 2025DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialoguescited by 6
  12. 2025PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awarenesscited by 4
8 more
  1. 2025Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performancecited by 4
  2. 2026PA3: Policy-Aware Agent Alignment through Chain-of-Thoughtcited by 4
  3. 2026Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systemscited by 3
  4. 2025Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Modelscited by 2
  5. 2026Reasoning Gets Harder for LLMs Inside A Dialoguecited by 2
  6. 2025MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversationscited by 0
  7. 2026Capability-Aligned Hierarchical Learning for Tool-Augmented LLMscited by 0
  8. 2026Unified Agent: Managing Interactions across Devicescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Multi-Turn Interaction Capabilities of Large Language Models
  2. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey
  3. 2025Small Language Models are the Future of Agentic AI
  4. 2024ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents
  5. 2025T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
  6. 2026Asymmetric Actor-Critic for Multi-turn LLM Agents
  7. 2025ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models
  8. 2026Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue