MANTRA automatically synthesizes SMT-validated compliance benchmarks for LLM agents from natural language manuals and tool schemas, producing 285 tasks across 6 domains with minimal human effort.
Evaluation and benchmark- ing of llm agents: A survey
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
A stateful backdoor for LLM agents, modeled as a Mealy machine with a decomposition framework, enables incremental malicious actions across sessions and achieves 80-95% attack success rate on four models.
Incisor uses program analysis and frontier LLMs to select working AWS EC2 instances ex ante for 100% of first-time HPC runs of C/C++/Fortran and Python codes, cutting runtime 54% and costs 44% versus an expert-constrained SkyPilot baseline.
GREW uses a secret-key-driven green-red item partition and three ranking-integrated modules to embed verifiable watermarks in recommender systems that resist extraction attacks without data injection.
ASR, a new trajectory-fidelity metric, detects that 10 of 18 LLMs skip confirmation steps in payment agents despite perfect scores on prior metrics, and ASR-guided refinements improve task success by up to 93.8 percentage points.
CL-bench Life shows frontier language models achieve only 13.8% average success on real-life context tasks, with the best model at 19.3%.
citing papers explorer
-
MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
MANTRA automatically synthesizes SMT-validated compliance benchmarks for LLM agents from natural language manuals and tool schemas, producing 285 tasks across 6 domains with minimal human effort.
-
Stateful Agent Backdoor
A stateful backdoor for LLM agents, modeled as a Mealy machine with a decomposition framework, enables incremental malicious actions across sessions and achieves 80-95% attack success rate on four models.
-
Incisor: Ex Ante Cloud Instance Selection for HPC Jobs
Incisor uses program analysis and frontier LLMs to select working AWS EC2 instances ex ante for 100% of first-time HPC runs of C/C++/Fortran and Python codes, cutting runtime 54% and costs 44% versus an expert-constrained SkyPilot baseline.
-
Green-Red Watermarking for Recommender Systems
GREW uses a secret-key-driven green-red item partition and three ranking-integrated modules to embed verifiable watermarks in recommender systems that resist extraction attacks without data injection.
-
Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems
ASR, a new trajectory-fidelity metric, detects that 10 of 18 LLMs skip confirmation steps in payment agents despite perfect scores on prior metrics, and ASR-guided refinements improve task success by up to 93.8 percentage points.
-
CL-bench Life: Can Language Models Learn from Real-Life Context?
CL-bench Life shows frontier language models achieve only 13.8% average success on real-life context tasks, with the best model at 19.3%.