TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints
cs.AI
Submitted: 2026-05-13
Updated: 2026-11-07
Terminology
Sources
- Evidence for Limited Metacognition in LLMs
- Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
- Do Large Language Models Know What They Are Capable Of?
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- Adaptively Robust LLM Inference Optimization under Prediction Uncertainty
- The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
- Efficient LLM Scheduling by Learning to Rank
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
- S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
- Language Models (Mostly) Know What They Know
- AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
- SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
- Humanity's Last Exam
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents