Verify by Doing: Co-Evolving Agent Execution and Evaluation without External Feedback
cs.AI
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
- EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning
- Large Language Models Cannot Self-Correct Reasoning Yet
- The Red Queen G"odel Machine: Co-Evolving Agents and Their Evaluators
- Prover-Verifier Games improve legibility of LLM outputs
- Recursive Harness Self-Improvement
- Let's Verify Step by Step
- Self-Refine: Iterative Refinement with Self-Feedback
- TTHE: Test-Time Harness Evolution
- Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
- GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
- AutomationBench
- $\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- The Verification Horizon: No Silver Bullet for Coding Agent Rewards
- Voyager: An Open-Ended Embodied Agent with Large 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