GLIDE: Generalized Layer-wise Intrinsic Distributional Evaluation for Heterogeneous LLM Agents
cs.AI, cs.MA
Submitted: 2026-09-26
Updated: 2026-09-26
Comments: Accepted by EMNLP 2026 Findings
Code: https://github.com/ZHUWEI-hub/GLIDE
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process
- InternLM2 Technical Report
- Evaluating Large Language Models Trained on Code
- The Llama 3 Herd of Models
- A Survey on LLM-as-a-Judge
- LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
- Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models
- Mistral 7B
- Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
- CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
- Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling
- Uncertainty Estimation in Autoregressive Structured Prediction
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Prompting GPT-3 To Be Reliable
- MDToC: Metacognitive Dynamic Tree of Concepts for Boosting Mathematical Problem-Solving of Large Language Models
- Gemma 3 Technical Report
- Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning
- Mixture-of-Agents Enhances Large Language Model Capabilities
- Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems