Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
A blackboard multi-agent system parses STEP B-Reps, injects GraphSAGE feature labels, and uses Claude plus GPT-4o to reorient and modify FDM parts for overhang-free printability.
Model organism interpretability depends strongly on training methodology, with integrated training yielding less interpretable MOs than post-hoc SFT or DPO.
MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in cooperative MARL.
New MAROON-X observations of HAT-P-70b detect multiple neutral and ionized metals with day-to-night wind signatures and demonstrate that ionization-aware retrievals yield abundance ratios closer to solar values except for enhanced nickel.
No kilonova detected from sub-solar GW candidate S251112cm, but coincident IIb supernova SN 2025adtq yields suggestive evidence for the superkilonova channel, though inconclusive after accounting for chance coincidence.
Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.
A 22M-parameter hyperbolic model answers structured EHR questions with accuracy close to LLM-based systems (EHRXQA 89.5%, MIMIC-Instr 76.0%).
Audio language models are benchmarked on five semantic and paralinguistic reasoning tasks to reveal limitations in handling spoken audio evidence, accent variation, and domain shifts.
citing papers explorer
-
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
AgentsCAD: Automated Design for Manufacturing of FDM Parts via Multi-Agent LLM Reasoning and Geometric Feature Recognition
A blackboard multi-agent system parses STEP B-Reps, injects GraphSAGE feature labels, and uses Claude plus GPT-4o to reorient and modify FDM parts for overhang-free printability.
-
The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology
Model organism interpretability depends strongly on training methodology, with integrated training yielding less interpretable MOs than post-hoc SFT or DPO.
-
Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in cooperative MARL.
-
HAT-P-70b through the Eyes of MAROON-X: Constraining Elemental Abundances of Metals and Insights on Atmosphere Dynamics
New MAROON-X observations of HAT-P-70b detect multiple neutral and ionized metals with day-to-night wind signatures and demonstrate that ionization-aware retrievals yield abundance ratios closer to solar values except for enhanced nickel.
-
Electromagnetic Follow-up of the Sub-Solar Mass Gravitational Wave Candidate S251112cm: Kilonova Constraints and a Coincident IIb Supernova
No kilonova detected from sub-solar GW candidate S251112cm, but coincident IIb supernova SN 2025adtq yields suggestive evidence for the superkilonova channel, though inconclusive after accounting for chance coincidence.
-
AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks
Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
A 22M-parameter hyperbolic model answers structured EHR questions with accuracy close to LLM-based systems (EHRXQA 89.5%, MIMIC-Instr 76.0%).
-
Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents
Audio language models are benchmarked on five semantic and paralinguistic reasoning tasks to reveal limitations in handling spoken audio evidence, accent variation, and domain shifts.