Related papers: ToolWeaver: Weaving Collaborative Semantics for Sc…

Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities, and specialized models -- to solve complex tasks beyond the reach of standalone language…

Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) for generating more factual, accurate, and up-to-date content. Existing methods either optimize prompts to guide LLMs in leveraging retrieved…

While the recent developments in large language models (LLMs) have successfully enabled generative recommenders with natural language interactions, their recommendation behavior is limited, leaving other simpler yet crucial components such…

Utilizing tools with Large Language Models (LLMs) is essential for grounding AI agents in real-world applications. The prevailing approach involves few-shot prompting with demonstrations or fine-tuning with expert annotations. However, mere…

Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this challenge, previous…

The discovery of symbolic solutions -- mathematical expressions, logical rules, and algorithmic structures -- is fundamental to advancing scientific and engineering progress. However, traditional methods often struggle with search…

The computational complexity of large language model (LLM) inference significantly constrains their deployment efficiency on edge devices. In contrast, small language models offer faster decoding and lower resource consumption but often…

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Generative retrieval for search and recommendation is a promising paradigm for retrieving items, offering an alternative to traditional methods that depend on external indexes and nearest-neighbor searches. Instead, generative models…

SOAR, a classic symbol-based cognitive architecture, has been fostering the development of general, human-like intelligent agents. Nevertheless, its practical adoption is hindered by the laborious manual rule coding. Emerging Large Language…

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extend their utility, enabling them to solve practical tasks. Previous methods manually parse tool documentation and create in-context…

Large language models (LLMs) excel at processing and generating both text and code. However, LLMs have had limited applicability in grounded task-oriented dialogue as they are difficult to steer toward task objectives and fail to handle…

Despite being pretrained on multilingual corpora, large language models (LLMs) exhibit suboptimal performance on low-resource languages. Recent approaches have leveraged multilingual encoders alongside LLMs by introducing trainable…

Tool learning can further broaden the usage scenarios of large language models (LLMs). However most of the existing methods either need to finetune that the model can only use tools seen in the training data, or add tool demonstrations into…

Empowering large language models (LLMs) with effective tool utilization capabilities is crucial for enabling AI agents to solve complex problems. However, current models face two major limitations: (1) unreliable tool planning and…

The rapid advancement of large language models (LLMs) has revolutionized code generation tasks across various programming languages. However, the unique characteristics of programming languages, particularly those like Verilog with specific…

Recently, large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL). However, leveraging the RL algorithm to empower effective multi-tool collaborative reasoning in LLMs remains an…

We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the seamless integration of generative models with a diverse…

Recent work demonstrates that, after instruction tuning, Code Large Language Models (Code LLMs) can obtain impressive capabilities to address a wide range of code-related tasks. However, current instruction tuning methods for Code LLMs…

This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…