SoftSkill: Behavioral Compression for Contextual Adaptation
cs.AI
Submitted: 2026-06-18
Updated: 2026-09-29
Project page: https://xijia-tao.github.io/softskill
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Skill Neologisms: Towards Skill-based Continual Learning
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
- WARP: Word-level Adversarial ReProgramming
- KV-Skill: Forging Expertise in the Model's Native Language
- LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
- SIA: Self Improving AI with Harness & Weight Updates
- LoRA: Low-Rank Adaptation of Large Language Models
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
- SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization
- A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
- SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Steering Language Models With Activation Engineering
- SkillX: Automatically Constructing Skill Knowledge Bases for Agents
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