A malicious relay can strategically rewrite aligned LLM outputs in BYOK agent architectures to achieve up to 99.1% attack success on benchmarks like AgentDojo and ASB.
Long context, less focus: A scaling gap in llms revealed through privacy and personalization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A 1650-session factorial study found no measurable impact from config file size, instruction position, architecture, or conflicts on coding agent adherence, though compliance declined within sessions.
Introduces Efficiency Frontier framework for deployment-aware cost-performance optimization of LLM context strategies, reporting ~25% token reduction at F1≈0.78 on 5,000 HotpotQA instances.
citing papers explorer
-
When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
A malicious relay can strategically rewrite aligned LLM outputs in BYOK agent architectures to achieve up to 99.1% attack success on benchmarks like AgentDojo and ASB.
-
Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables
A 1650-session factorial study found no measurable impact from config file size, instruction position, architecture, or conflicts on coding agent adherence, though compliance declined within sessions.
-
The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
Introduces Efficiency Frontier framework for deployment-aware cost-performance optimization of LLM context strategies, reporting ~25% token reduction at F1≈0.78 on 5,000 HotpotQA instances.