Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks

arXiv:2610.02001 · cs.AI, cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: 44 pages, 9 figures. Code, benchmark protocol, scoring code, and all 288 per-cell results: https://github.com/Mingbird/Mingbird-agent

Code: https://github.com/Mingbird/Mingbird-agent

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 63× in this paper · explained in 2 episodes
• Ablation — 35× in this paper · explained in 1 episode
• Verification — 16× in this paper · explained in 2 episodes
• Agent Harness — 6× in this paper · explained in 2 episodes
• Quantization — 5× in this paper · explained in 12 episodes
• Core — 4× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Agentic System — 2× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• External Validation — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Progressive Disclosure — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Task Decomposition — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Alternation — 1× in this paper · explained in 1 episode
• Failure Taxonomy — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Meeting of the Association for Computational Linguistics — 1× in this paper
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Twelfth International Conference on Learning Representations — 1× in this paper

Sources

• Small Language Models: Survey, Measurements, and Insights
• SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
• Gemma 4 Technical Report
• Qwen2.5 Technical Report
• TinyAgent: Function Calling at the Edge
• Small Language Models are the Future of Agentic AI
• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• ReAct: Synergizing Reasoning and Acting in Language Models
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Gorilla: Large Language Model Connected with Massive APIs
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Self-Refine: Iterative Refinement with Self-Feedback
• AgentBench: Evaluating LLMs as Agents
• AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
• WebArena: A Realistic Web Environment for Building Autonomous Agents
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• GAIA: a benchmark for General AI Assistants
• $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
• Qwen3 Technical Report
• 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
• 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