TRUSTDESC prevents tool poisoning in LLM applications by automatically generating accurate tool descriptions from code via a three-stage pipeline of reachability analysis, description synthesis, and dynamic verification.
Craft: Customizing llms by creating and retrieving from specialized toolsets
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
ToolHijacker optimizes malicious tool documents via a two-phase strategy to hijack LLM agents' tool selection in no-box settings.
SSL representation disentangles skill scheduling, structure, and logic using an LLM normalizer, improving skill discovery MRR@50 from 0.649 to 0.729 and risk assessment macro F1 from 0.409 to 0.509 over text baselines.
ATTC reduces 'Tool Ignored' errors in tool-integrated reasoning by adaptively trusting tool results according to generated code confidence, yielding 4.1-7.5% gains across models and datasets.
citing papers explorer
-
TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation
TRUSTDESC prevents tool poisoning in LLM applications by automatically generating accurate tool descriptions from code via a three-stage pipeline of reachability analysis, description synthesis, and dynamic verification.
-
Prompt Injection Attack to Tool Selection in LLM Agents
ToolHijacker optimizes malicious tool documents via a two-phase strategy to hijack LLM agents' tool selection in no-box settings.
-
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
SSL representation disentangles skill scheduling, structure, and logic using an LLM normalizer, improving skill discovery MRR@50 from 0.649 to 0.729 and risk assessment macro F1 from 0.409 to 0.509 over text baselines.
-
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
ATTC reduces 'Tool Ignored' errors in tool-integrated reasoning by adaptively trusting tool results according to generated code confidence, yielding 4.1-7.5% gains across models and datasets.