Trace Evolution Bench: Measuring Whether Agents Improve from Their Own Environment Traces
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Terminology
Sources
- Non-Determinism of "Deterministic" LLM Settings
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
- EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer
- SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment
- Beyond Endpoint Performance: Process-Level Evaluation of Self-Evolving Agents
- Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
- Quantifying Variance in Evaluation Benchmarks
- RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
- The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
- Recursive Self-Evolving Agents via Held-Out Selection
- MemGPT: Towards LLMs as Operating Systems
- Qwen2.5 Technical Report
- When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents
- S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
- PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
- Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
- SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization
- AgentEvolver: Towards Efficient Self-Evolving Agent System
- SEAGym: An Evaluation Environment for Self-Evolving LLM Agents
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
- Agents' Last Exam
- 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