REVIEW 12 cited by
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
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
Signed reviews
abstract
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to solving complex problems. However, traditional methods, which finetune LLMs with tool demonstration data, can be both costly and restricted to a predefined set of tools. Recent in-context learning paradigm alleviates these issues, but the limited context length only allows for a few shots of demonstrations, leading to suboptimal understandings of the tools. Moreover, when there are numerous tools to choose from, in-context learning could completely fail to work. In this paper, we propose an alternative approach, $\textbf{ToolkenGPT}$, which combines the benefits of both sides. Our approach represents each $\underline{tool}$ as a to$\underline{ken}$ ($\textit{toolken}$) and learns an embedding for it, enabling tool calls in the same way as generating a regular word token. Once a toolken is triggered, the LLM is prompted to complete arguments for the tool to execute. ToolkenGPT offers the flexibility to plug in an arbitrary number of tools by expanding the set of toolkens on the fly. In addition, it improves tool use by allowing extensive demonstration data for learning the toolken embeddings. In diverse domains, including numerical reasoning, knowledge-based question answering, and embodied plan generation, our approach effectively augments LLMs with tools and substantially outperforms various latest baselines. ToolkenGPT demonstrates the promising ability to use relevant tools from a large tool set in complex scenarios.
Forward citations
Cited by 12 Pith papers
-
Hell or High Water: Evaluating Agentic Recovery from External Failures
Language-model agents fail badly at finding backup plans when a planned function is disabled, even when a correct alternative is guaranteed to exist.
-
SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information
A new human-curated benchmark for LLM mobile assistants shows models struggle to locate scattered personal information, with the best model at 57.3% accuracy.
-
Replacing thinking with tool usage enables reasoning in small language models
Small language models can improve code repair by spending inference compute on tool-usage traces (Chain-of-Edits) rather than on natural-language reasoning tokens.
-
Reducing Tool Hallucination via Reliability Alignment
A reliability alignment framework, Relign, that expands the LLM tool-use action space with indecisive actions reduces tool hallucination rates and improves task success on the new RelyToolBench benchmark.
-
SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling
A LoRA update split into several fixed, differently-scaled low-rank experts with orthogonal input directions improves fine-tuning accuracy at the same parameter count.
-
MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
MemTool is a short-term memory framework with three modes (autonomous, workflow, hybrid) that lets LLM agents add and remove tools across multi-turn conversations, evaluated over 100 turns on 13+ models.
-
Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
Voila presents a unified voice-language model family with a hierarchical multi-scale Transformer, claiming 195 ms latency and a million customizable voices, with new benchmark and ASR/TTS evaluations.
-
DBRouting: Routing End User Queries to Databases for Answerability
The paper introduces DB routing, a task of ranking databases for answerability, with synthesized benchmarks from Spider and BIRD showing that LLMs outperform embeddings but both struggle with many or similar databases.
-
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
TL-Training, a task-feature-based training framework, lets a 7B CodeLLaMA-2 model reach competitive tool-use performance using only 1,217 training trajectories.
-
ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents
ScaleMCP describes an agentic MCP tool-retrieval system, but its experiments show the proposed TDWA embedding loses to concatenation and the agentic retrieval loop is not evaluated.
-
Integrating External Tools with Large Language Models to Improve Accuracy
A tool-augmented LLM framework, Athena, reports 83% math and 88% science accuracy on small MMLU subsets, beating GPT-4o, LLaMA-Large, Mistral-Large, Phi-Large, and GPT-3.5.
-
LLMs are Also Effective Embedding Models: An In-depth Overview
A structured survey of using decoder-only LLMs as text embedding models, covering prompting, fine-tuning, data construction, benchmarks, and open problems.
Discussion (0). Continue with ORCID to comment.