How Efficient Is Your Agent? Online Predictive Bounds under Budget Constraints
cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Spend Where It Counts: Dynamic Budget Allocation for Multi-Turn LLM Evaluation
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Certifying LLM Safety against Adversarial Prompting
- Active Evaluation Acquisition for Efficient LLM Benchmarking
- A Conformal Prediction Score that is Robust to Label Noise
- Red Teaming Language Models with Language Models
- SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
- Doubly Robust Conformalized Survival Analysis with Right-Censored Data
- Conformal Survival Bands for Risk Screening under Right-Censoring
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models
- Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs
- Adaptive Experimentation for Censored Survival Outcomes
- History-Aware Conformal Prediction Sets for Censored Time-to-Event Outcomes
- Efficient Evaluation of LLM Performance with Statistical Guarantees
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis