Insert-expansions for Tool-enabled Conversational Agents
On the map: LLM reasoning → Reasoning benchmarks and evaluation
also in 1 more
Abstract (arXiv)
This paper delves into an advanced implementation of Chain-of-Thought-Prompting in Large Language Models, focusing on the use of tools (or "plug-ins") within the explicit reasoning paths generated by this prompting method. We find that tool-enabled conversational agents often become sidetracked, as additional context from tools like search engines or calculators diverts from original user intents. To address this, we explore a concept wherein the user becomes the tool, providing necessary details and refining their requests. Through Conversation Analysis, we characterize this interaction as insert-expansion - an intermediary conversation designed to facilitate the preferred response. We explore possibilities arising from this 'user-as-a-tool' approach in two empirical studies using direct comparison, and find benefits in the recommendation domain.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 18 of its 40 references that are in the map. First posted on arXiv 4 Jul 2023.
Builds on
18 of 40 references.
Closest ancestors · 2
Same direction, newest first
- 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models23 May
- 2023Augmented Language Models: a Survey15 Feb
Other references · 16
- 2017Attention Is All You Needcited by 59,932
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2017Deep reinforcement learning from human preferencescited by 3,846
- 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
- 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
- 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
- 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
- 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 245
- 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
4 more
- 2022TALM: Tool Augmented Language Modelscited by 197
- 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
- 2023Small Models are Valuable Plug-ins for Large Language Modelscited by 42
- 2023Prompt Sapper: A LLM-Empowered Production Tool for Building AI Chainscited by 24
Built on by
Citing papers per year: 2024: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration
- 2026Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency
- 2025When Users Are Happy but Agents Are Wrong: Multi-Dimensional Evaluation of Tool-Augmented Dialogue
- 2025T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
- 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- 2025InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context
- 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
- 2024Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems