Self-Evaluating Recursive Agents
cs.AI
Submitted: 2026-10-04
Updated: 2026-10-04
Code: https://github.com/OliverLeeXZ/SERA
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- The Era of Agentic Organization: Learning to Organize with Language Models
- EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning
- Recursive Agent Optimization
- RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
- What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Scaling Long-Horizon LLM Agent via Context-Folding
- Kimi K3: Open Frontier Intelligence
- Kimi K2.5: Visual Agentic Intelligence
- ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents
- AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
- Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
- Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
- Qwen3 Technical Report
- Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL
- Recursive Language Models
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