REVIEW 22 cited by
LLM With Tools: A Survey
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
read the original abstract
The integration of tools in augmenting large language models presents a novel approach toward enhancing the efficiency and accuracy of these models in handling specific, complex tasks. This paper delves into the methodology,challenges, and developments in the realm of teaching LLMs to use external tools, thereby pushing the boundaries of their capabilities beyond pre-existing knowledge bases. We introduce a standardized paradigm for tool integration guided by a series of functions that map user instructions to actionable plans and their execution, emphasizing the significance of understanding user intent, tool selection, and dynamic plan adjustment. Our exploration reveals the various challenges encountered, such as tool invocation timing, selection accuracy, and the need for robust reasoning processes. In addressing these challenges, we investigate techniques within the context of fine-tuning and incontext learning paradigms, highlighting innovative approaches to ensure diversity, augment datasets, and improve generalization.Furthermore, we investigate a perspective on enabling LLMs to not only utilize but also autonomously create tools, which may redefine their role from mere tool users to tool creators. Finally,we reproduced Chameleon's results on ScienceQA and analyzed the code structure.
Forward citations
Cited by 22 Pith papers
-
Progressive Agent Skill Generation via Reinforcement Learning
Skill-α uses reinforcement learning with a rollback reward to progressively edit SKILL.md-style procedure files, improving downstream success rates over pipeline baselines on CL-Bench, SpreadsheetBench, and tau2-bench.
-
Controlling Tool Use with Heading-Specific Activation Steering
Heading-anchored steering vectors exert bidirectional causal control over tool-invocation behavior across five LLMs, but geometric analysis reveals diffuse, non-linear structure inconsistent with parametric concept encoding.
-
One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
Repository-level issue localization can be done by a single jump-to-definition tool trained with reinforcement learning, achieving strong results on SWE-bench despite using only open-weights models.
-
Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning
Decoupling LLM-agent planning from summarization and rewarding tool-call completeness rather than final-answer correctness improves planning by 8-12% and end-to-end answers by 5-6% over end-to-end RL baselines.
-
A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis
The paper releases MCPCorpus, a large-scale annotated dataset of MCP servers and clients with over 20 normalized attributes, plus tooling for updates and exploration.
-
Efficient Serving of LLM Applications with Probabilistic Demand Modeling
Hermes models LLM applications as probabilistic demand graphs and uses the Gittins scheduling policy plus backend prewarming to cut average completion time by over 70% in testbed runs.
-
SEM: Reinforcement Learning for Search-Efficient Large Language Models
SEM trains LLMs with a GRPO-based reward to reduce redundant web searches while preserving answer accuracy across multi-hop QA and knowledge benchmarks, though the efficiency gains largely encode the training objective.
-
RISKTAGGER: Evidence-Guided LLM Agent for Post-Incident Forensic Analysis of Money Laundering in Web3
An LLM-driven agent automatically extracts clues from incident reports, traces laundering paths on-chain, and labels accounts as high/medium/low risk, with evaluation on the Bybit hack.
-
A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models
The authors organize LLM-based time series reasoning into three exclusive topologies (direct, chain, branch) crossed with four objectives, and use them to label 125 papers, benchmarks, and resources.
-
Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
H-MEM organizes LLM agent memory into a four-level semantic hierarchy with pointer-based coarse-to-fine retrieval, improving average LoCoMo QA scores over five baselines while cutting retrieval cost.
-
From Shots to Stories: LLM-Assisted Video Editing with Unified Language Representations
LLMs operating on a text storyboard representation of video shots outperform traditional models on shot classification and next-shot selection, and a multi-temperature generate-then-select strategy improves shot seque...
-
LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
LLM-Virus uses an evolutionary algorithm with an LLM as crossover, mutation, and fitness operator to evolve jailbreak templates, reporting state-of-the-art attack success on HarmBench and AdvBench.
-
Interfaze: The Future of AI is built on Task-Specific Small Models
Interfaze-Beta uses small specialist models and tools to build a compact context that a general-purpose LLM answers from, reporting competitive benchmark scores without reproducible evidence.
-
AI Reasoning for Wireless Communications and Networking: A Survey and Perspectives
A survey that organizes LLM and AI reasoning methods into a taxonomy and maps them onto the physical, link, network, transport, and application layers of wireless networks.
-
Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling
ToolRegistry unifies LLM tool integration across Python, MCP, OpenAPI, and LangChain, claiming 60-80% less code and up to 3.1x faster concurrent execution.
-
A Novel Self-Evolution Framework for Large Language Models
A dual-phase framework that uses a Censor satisfaction scorer to expand training data and then applies SFT plus frequency-weighted DPO, reporting benchmark gains over SFT, PO, and memory baselines.
-
ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
ToolRegistry unifies LLM tool registration and execution across four protocols via an RPC-style Tool object, reporting large code reductions and concurrency speedups.
-
Foundation Model Empowered Synesthesia of Machines (SoM): AI-native Intelligent Multi-Modal Sensing-Communication Integration
The paper proposes a systematic classification and two roadmaps for using foundation models (LLMs and wireless foundation models) to design Synesthesia of Machines systems for 6G, with preliminary case-study evidence ...
-
Addressing the sustainable AI trilemma: a case study on LLM agents and RAG
LLM-dependent memory operations in agents and RAG consume orders of magnitude more energy than vector methods, and resource-constrained hardware pays higher energy for lower quality.
-
LABIIUM: AI-Enhanced Zero-configuration Measurement Automation System
An AI-assisted lab automation system generates simple instrument scripts, but its LLMs cannot yet match an expert adaptive sampling algorithm.
-
Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches
This survey argues that embodiment, symbol grounding, causality, and memory are the foundational principles needed to make large language models achieve artificial general intelligence.
-
A Survey on Large Language Models for Mathematical Reasoning
Recent advances in LLM mathematical reasoning are organized into comprehension and generation phases, covering methods from prompting to test-time scaling.
Discussion (0). Continue with ORCID to comment.