Paritok-4B: Intent-Conditioned Context Compression for Coding Agents

arXiv:2608.24188 · cs.AI, cs.CL, cs.LG, cs.SE · Submitted 2026-08-25 · Read on arXiv

cs.AI, cs.CL, cs.LG, cs.SE

Submitted: 2026-08-25

Updated: 2026-08-25

Code: https://github.com/Paritok-official/paritok-4b-v1

Terminology

• Distillation — 10× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• AUC — 1× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
• LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
• Compressing Context to Enhance Inference Efficiency of Large Language Models
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• Training Software Engineering Agents and Verifiers with SWE-Gym
• SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents
• ReAct: Synergizing Reasoning and Acting in Language Models
• Qwen3 Technical Report
• LoRA: Low-Rank Adaptation of Large Language Models
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection