ECOS: Environment-Calibrated On-Policy Self-Distillation for Language Agents
cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents
- Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation
- Group-in-Group Policy Optimization for LLM Agent Training
- PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- Reinforcement Learning via Self-Distillation
- Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
- Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
- PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
- Agentic Reinforcement Learning with Self-Distilled Reward Shaping
- Group-Reflective Self-Distillation for Agentic Reinforcement Learning
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- StepOPSD: Step-Aware Online Preference Self-Distillation for Agent Reinforcement Learning
- Self-Distilled Agentic Reinforcement Learning
- Large Language Models Cannot Self-Correct Reasoning Yet
- RUDDER: Return Decomposition for Delayed Rewards
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