Agent Architecture Cost-Success Trade-offs: A Controlled Evaluation across Enterprise-Style SOPs
cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/openai/swarm
Terminology
Sources
- Why Do Multi-Agent LLM Systems Fail?
- The Scaling Laws of Skills in LLM Agent Systems
- SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
- An LLM Compiler for Parallel Function Calling
- Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
- When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail
- From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
- Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents
- Beyond Accuracy: A Multi-Dimensional Framework for Evaluating Enterprise Agentic AI Systems
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
- SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
- SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
- WebArena: A Realistic Web Environment for Building Autonomous Agents
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