When Successful Strategies Fail: Adaptation to Environmental Novelty in Terminal Agents
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
- Improved Regularization of Convolutional Neural Networks with Cutout
- Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity
- Endless Terminals: Scaling RL Environments for Terminal Agents
- Can LLMs Perceive Time? An Empirical Investigation
- SEAL: Synergistic Co-Evolution of Agents and Learning Environments
- Tmax: A simple recipe for terminal agents
- Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
- RMA: Rapid Motor Adaptation for Legged Robots
- RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
- PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
- Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ECHO: Terminal Agents Learn World Models for Free
- Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability
- OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
- PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection