HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention
cs.AI
Submitted: 2026-10-05
Updated: 2026-10-05
Comments: 23 pages. Project page: https://hera-bench.github.io/
Project page: https://hera-bench.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
- Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
- Bench2Robust: Scenario-Controlled Recovery for Tool-Using Agents
- Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- GLM-5: from Vibe Coding to Agentic Engineering
- Continual Harness: Online Adaptation for Self-Improving Foundation Agents
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Kimi K3: Open Frontier Intelligence
- AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
- MiniMax Sparse Attention
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- BAGEN: Are LLM Agents Budget-Aware?
- AgentAbstain: Do LLM Agents Know When Not to Act?
- The Tool Illusion: Rethinking Tool Use in Web Agents
- Agentic Abstention: Do Agents Know When to Stop Instead of Act?
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
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