Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Fantastic Adaptive Taxonomies and How to Use Them
- From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
- The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
- MemPro: Agentic Memory Systems as Evolvable Programs
- UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- Kosmos: An AI Scientist for Autonomous Discovery
- MemGPT: Towards LLMs as Operating Systems
- AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs
- HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- The Art of Building Verifiers for Computer Use Agents
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Solving math word problems with process- and outcome-based feedback
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection