SynAct: Synergistic Active Feedback Learning for LLM Agents
cs.LG
Submitted: 2026-10-08
Updated: 2026-10-08
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Test-Time Adaptation for LLM Agents via Environment Interaction
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning
- Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
- Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback
- Deep reinforcement learning from human preferences
- Uncertainty-Aware Clarification in LLM Agents with Information Gain
- Group-in-Group Policy Optimization for LLM Agent Training
- AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
- Gemma 3 Technical Report
- Bayesian Active Learning for Classification and Preference Learning
- Large Language Models Cannot Self-Correct Reasoning Yet
- Language Models (Mostly) Know What They Know
- Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems
- Let's Verify Step by Step
- NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System
- Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
- Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
- Disentangled Representation Learning for Parametric Partial Differential Equations
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks