FirmCure uses LLM-based adaptive perception, reflective synthesis, and autonomous runtime intervention to rehost 21 firmware images at 100% port opening and 90.5% interactivity rates across 5 architectures.
hub Canonical reference
Llm with tools: A survey
Canonical reference. 100% of citing Pith papers cite this work as background.
15
Pith papers citing it
2
external citations · Pith
Background
100% of classified citations
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.
hub tools
citation-role summary
background 8
citation-polarity summary
roles
background 8polarities
background 8representative citing papers
LLMs extract explicit constraints effectively but struggle with implicit open-world requirements, structural biases in plans, and ineffective self-correction during travel planning.
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
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.
GRAFT internalizes tool dependency graphs via dedicated special tokens in LLMs and applies on-policy context distillation to achieve higher exact sequence matching and dependency legality than prior external-graph methods.
A two-stage multi-agent LLM converts structural inputs to JSON then platform-specific scripts for ETABS, SAP2000, and OpenSees, achieving over 90% accuracy on 20 frame problems across ten trials.
Creates a five-dimension taxonomy (counterparty, payload, interaction state, discovery mechanism, schema flexibility) from nine protocols and identifies architectural patterns plus convergence trends.
SLIM dynamically optimizes the active external skill set in agentic RL via leave-one-skill-out marginal contribution estimates and lifecycle operations, delivering a 7.1% average gain over baselines on ALFWorld and SearchQA while showing some skills remain externally useful.
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
Analysis of ClawHub shows language-based functional divides in agent skills, with over 30% flagged suspicious and submission-time documentation enabling 73% accurate risk prediction.
Indirect prompt injection attacks remain effective on LLMs using web search tools, allowing data exfiltration and exposing ongoing weaknesses in current model defenses.
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.
A survey categorizing LLM-powered agent systems into software-based, physical, and hybrid types, covering industrial applications and challenges such as latency and security.
citing papers explorer
-
FirmCure:Towards Autonomous and Adaptive Rehosting of Linux-Based Firmware
FirmCure uses LLM-based adaptive perception, reflective synthesis, and autonomous runtime intervention to rehost 21 firmware images at 100% port opening and 90.5% interactivity rates across 5 architectures.
-
Revisiting the Travel Planning Capabilities of Large Language Models
LLMs extract explicit constraints effectively but struggle with implicit open-world requirements, structural biases in plans, and ineffective self-correction during travel planning.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
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.
-
GRAFT: Graph-Tokenized LLMs for Tool Planning
GRAFT internalizes tool dependency graphs via dedicated special tokens in LLMs and applies on-policy context distillation to achieve higher exact sequence matching and dependency legality than prior external-graph methods.
-
Automating Structural Analysis Across Multiple Software Platforms Using Large Language Models
A two-stage multi-agent LLM converts structural inputs to JSON then platform-specific scripts for ETABS, SAP2000, and OpenSees, achieving over 90% accuracy on 20 frame problems across ten trials.
-
A Technical Taxonomy of LLM Agent Communication Protocols
Creates a five-dimension taxonomy (counterparty, payload, interaction state, discovery mechanism, schema flexibility) from nine protocols and identifies architectural patterns plus convergence trends.
-
Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning
SLIM dynamically optimizes the active external skill set in agentic RL via leave-one-skill-out marginal contribution estimates and lifecycle operations, delivering a 7.1% average gain over baselines on ALFWorld and SearchQA while showing some skills remain externally useful.
-
Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
-
Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub
Analysis of ClawHub shows language-based functional divides in agent skills, with over 30% flagged suspicious and submission-time documentation enabling 73% accurate risk prediction.
-
Exploiting Web Search Tools of AI Agents for Data Exfiltration
Indirect prompt injection attacks remain effective on LLMs using web search tools, allowing data exfiltration and exposing ongoing weaknesses in current model defenses.
-
Large Language Model-Brained GUI Agents: A Survey
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
-
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.
-
LLM-Powered AI Agent Systems and Their Applications in Industry
A survey categorizing LLM-powered agent systems into software-based, physical, and hybrid types, covering industrial applications and challenges such as latency and security.
- Tools as Continuous Flow for Evolving Agentic Reasoning