Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering
cs.LG, cs.AI
Submitted: 2026-10-03
Updated: 2026-10-08
Code: https://github.com/rlisml/decisionsteer
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- KV-Skill: Forging Expertise in the Model's Native Language
- Training Large Language Models to Reason in a Continuous Latent Space
- LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
- SkillsInjector: Dynamic Skill Context Construction for LLM Agents
- LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception
- Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
- Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
- SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- Steer LLM Latents for Hallucination Detection
- Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
- SoftSkill: Behavioral Compression for Contextual Adaptation
- Steering Language Models With Activation Engineering
- SkillX: Automatically Constructing Skill Knowledge Bases for Agents
- System 2 Attention (is something you might need too)
- Qwen3 Technical Report
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
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