Agent Harness Awareness: Turning Verified Telemetry into Operational Control for Tool-Using Agents
cs.AI, cs.CL
Submitted: 2026-09-13
Updated: 2026-09-13
Code: https://github.com/manu2/scac-dynamic-agentharness
Terminology
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- Toolformer: Language Models Can Teach Themselves to Use Tools
- AgentBench: Evaluating LLMs as Agents
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditions
- When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents
- Budget-Aware Tool-Use Enables Effective Agent Scaling
- Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability
- Substrate-Aware AI Agents: Execution Context as a First-Class Input
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