On Turn-Level Best-of-N Sampling for Scaling LLM Agents
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/SWE-agent/mini-swe-agent
Terminology
Sources
- SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents
- CodeMonkeys: Scaling Test-Time Compute for Software Engineering
- SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling
- Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
- Scaling Test-Time Compute for Agentic Coding
- Kimi K3: Open Frontier Intelligence
- LLM-as-a-Verifier: A General-Purpose Verification Framework
- Agentic Test-Time Scaling for WebAgents
- Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
- $V_1$: Unifying Generation and Self-Verification for Parallel Reasoners
- Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- GTA1: GUI Test-time Scaling Agent
- Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
- WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents
- Scaling Test-time Compute for LLM 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