Beneath the Surface: What We Overlook When We Talk About Agent Evolution
cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/simple-agent-lab/RSIHub
Terminology
Sources
- EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer
- DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
- Towards a Science of Scaling Agent Systems
- RAM: Towards an Ever-Improving Memory System by Learning from Communications
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- Position: Agentic Evolution is the Path to Evolving LLMs
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement
- Rethinking the Evaluation of Harness Evolution for Agents
- Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?
- CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
- Hyperagents
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
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