Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics
cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
- The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
- Large Language Models Are Human-Level Prompt Engineers
- Large Language Models as Optimizers
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- TextGrad: Automatic "Differentiation" via Text
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- Guiding Large Language Models via Directional Stimulus Prompting
- How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
- Hindsight Experience Replay
- The Wisdom of Hindsight Makes Language Models Better Instruction Followers
- STaR: Bootstrapping Reasoning With Reasoning
- Unifying distillation and privileged information
- Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback
- The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents
- The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
- FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents
- Qwen3 Technical Report
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