The paper presents UniPPTBench and UniPPTEval, a unified benchmark and scenario-aware evaluation framework for presentation generation from vague prompts, long documents, multimodal documents, and multi-source inputs.
A survey on large language model based autonomous agents
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
PRGA gates wireless intent execution with progressive evidence stages, cutting time-to-first-safe-action by 23-27% and control-plane bytes by 52-54% on 3GPP benchmarks while rejecting all stale inputs and staying within a 0.5pp unsafe-action margin.
TraceToChain models LLM agent traces as absorbing DTMCs using automatic clustering and smoothed MLE, with KS and AIC validation, to reconcile pass@k, pass^k, and RDC as projections of a single first-passage success-time distribution.
Proprietary LLM agent skills can be extracted via black-box prompt attacks using an automated generation pipeline, creating serious copyright risks that partial defenses do not fully eliminate.
LanG presents a governance-aware agentic AI platform for unified security operations that reports strong performance on incident correlation, rule generation, attack reconstruction, and AI safety guardrails in an open-source package.
citing papers explorer
-
UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings
The paper presents UniPPTBench and UniPPTEval, a unified benchmark and scenario-aware evaluation framework for presentation generation from vague prompts, long documents, multimodal documents, and multi-source inputs.
-
Executor-Side Progressive Risk-Gated Actuation for Agentic AI in Wireless Supervisory Control
PRGA gates wireless intent execution with progressive evidence stages, cutting time-to-first-safe-action by 23-27% and control-plane bytes by 52-54% on 3GPP benchmarks while rejecting all stale inputs and staying within a 0.5pp unsafe-action margin.
-
Measuring the Unmeasurable: Markov Chain Reliability for LLM Agents
TraceToChain models LLM agent traces as absorbing DTMCs using automatic clustering and smoothed MLE, with KS and AIC validation, to reconcile pass@k, pass^k, and RDC as projections of a single first-passage success-time distribution.
-
Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
Proprietary LLM agent skills can be extracted via black-box prompt attacks using an automated generation pipeline, creating serious copyright risks that partial defenses do not fully eliminate.
-
LanG -- A Governance-Aware Agentic AI Platform for Unified Security Operations
LanG presents a governance-aware agentic AI platform for unified security operations that reports strong performance on incident correlation, rule generation, attack reconstruction, and AI safety guardrails in an open-source package.