Multi-Turn Agent Self-Distillation with Compressed Hindsight
cs.AI
Submitted: 2026-06-10
Updated: 2026-11-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
- Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
- Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
- Measuring Massive Multitask Language Understanding
- GPT-4o System Card
- Reinforcement Learning via Self-Distillation
- DistiLLM: Towards Streamlined Distillation for Large Language Models
- Privileged Information Distillation for Language Models
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- Self-critiquing models for assisting human evaluators
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distillation Enables Continual Learning
- Learning by Distilling Context
- RLVF: Learning from Verbal Feedback without Overgeneralization
- Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
- Qwen3 Technical Report
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- ReAct: Synergizing Reasoning and Acting in Language Models
- On-Policy Context Distillation for 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