AgentDojo introduces an extensible evaluation framework populated with realistic agent tasks and security test cases to measure prompt injection robustness in tool-using LLM agents.
(a) Did you state the full set of assumptions of all theoretical results? [N/A] (b) Did you include complete proofs of all theoretical results? [N/A]
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
BEIR is a heterogeneous zero-shot benchmark showing BM25 as a robust baseline while re-ranking and late-interaction models perform best on average at higher cost, with dense and sparse models lagging in generalization.
τ-bench shows state-of-the-art agents like GPT-4o succeed on under 50% of tool-using, rule-following tasks and are inconsistent across repeated trials.
Adding the fixed prompt 'Let's think step by step' enables large language models to achieve substantial zero-shot gains on arithmetic, symbolic, and logical reasoning benchmarks without any task-specific examples.
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
HPD v2 is the largest human preference dataset for text-to-image images with 798k choices, and HPS v2 is the resulting CLIP-based scorer that better predicts human judgments and responds to model improvements.
citing papers explorer
-
LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
-
$\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
τ-bench shows state-of-the-art agents like GPT-4o succeed on under 50% of tool-using, rule-following tasks and are inconsistent across repeated trials.