Test-Time Compute Scales Better with Parallel Agent Teams
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/modal-projects/parallel-agent-teams-scaling
Terminology
Sources
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
- Why Do Multi-Agent LLM Systems Fail?
- Multi-scale Topology Optimization using Neural Networks
- Evaluating Large Language Models Trained on Code
- Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
- Training Verifiers to Solve Math Word Problems
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- Automated Design of Agentic Systems
- AI Agents That Matter
- Towards a Science of Scaling Agent Systems
- Measuring AI Ability to Complete Long Software Tasks
- ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
- More Agents Is All You Need
- Predicting and improving test-time scaling laws via reward tail-guided search
- Competition-Level Code Generation with AlphaCode
- When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis
- MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
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