Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
hub
Tool learning with large language models: A survey
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 1
dataset 1
method 1
citation-polarity summary
representative citing papers
SkillComposer performs task-conditioned skill sequence prediction with a constrained autoregressive decoder to jointly output skill subset, count, and order, raising pass rates by 23.1 and 18.2 percentage points on two production coding agents over no-skill baselines.
IoT-Brain uses a neuro-symbolic Spatial Trajectory Graph to ground LLMs for verifiable semantic-spatial sensor scheduling, achieving 37.6% higher task success with lower resource use on a campus-scale benchmark.
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.
ToolHijacker optimizes malicious tool documents via a two-phase strategy to hijack LLM agents' tool selection in no-box settings.
Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.
Introduces NoisyToolBench benchmark and Ask-when-Needed framework to improve LLM tool-use performance when user instructions are unclear or incomplete.
An adaptive compute-optimal strategy for scaling LLM test-time compute achieves over 4x efficiency gains versus best-of-N and lets smaller models outperform 14x larger ones on some problems.
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
A CPST-based taxonomy sorts autonomous systems into Confined Actors, Socially-Aware Interactors, and CPST-Integrated Agents to enable proportional governance from enhanced liability to qualified personhood.
Structured reflection makes error diagnosis and repair an explicit trainable step that improves reliability and reduces redundant calls in tool-using LLM agents.
citing papers explorer
-
IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling
IoT-Brain uses a neuro-symbolic Spatial Trajectory Graph to ground LLMs for verifiable semantic-spatial sensor scheduling, achieving 37.6% higher task success with lower resource use on a campus-scale benchmark.