Exploration and Exploitation Errors Are Measurable for Language Model Agents
cs.AI
Submitted: 2026-04-14
Updated: 2026-10-29
Terminology
Sources
- gpt-oss-120b & gpt-oss-20b Model Card
- Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents
- AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation
- Should You Use Your Large Language Model to Explore or Exploit?
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
- AutoFlow: Automated Workflow Generation for Large Language Model Agents
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- Expanding LLM Agent Boundaries with Strategy-Guided Exploration
- Voyager: An Open-Ended Embodied Agent with Large Language Models
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