Hugging Face Trending Papers
Paritok-4B: Intent-Conditioned Context Compression for Coding Agents
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Aug 26
Paritok-4B: Intent-Conditioned Context Compression for Coding Agents
Paritok-4B is a 4‑billion‑parameter LoRA compressor designed for coding agents, which extracts and retains key spans of code rather than paraphrasing them. It is intent‑conditioned, selecting lines that are most relevant to the agent’s current task, and achieves high fidelity with 96% of identifiers, paths, and numbers preserved. Trained on 67,074 real OpenHands trajectories and fine‑tuned on Qwen3‑4B, it compresses agent context to about 25.7% of its original size while keeping 86.5% of the uncompressed solve quality across 300 SWE‑bench Lite instances.
arXiv Computation and Language
Sep 22
An Empirical Cost Attribution of Context-Compression Gateways in Multi-Turn Coding Agents
arXiv:2609.22114v1 Announce Type: new Abstract: Context compression is widely proposed as a way to cut the token bill of LLM coding agents, and public benchmarks report that aggressive compression pr...
arXiv AI
Sep 28
Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents
The paper introduces LOHA, a context layout that compresses older tool observations into soft tokens while keeping the agent’s own turns and the last K observations in plain text, and ACD, a training method that distills full‑text predictions into this latent representation while anchoring behavior on plain text. This approach reduces context per call by up to 57% without significant loss in resolve rates, and improves instance throughput in single‑GPU serving. Experiments on SWE‑bench Verified show that K=3 yields a 43–57% compression with only modest performance impact, while larger windows favor task performance over compression.
arXiv Computation and Language
Sep 28
KuaFu: Compressing Long User Behavior into Understanding at Billion Scale
KuaFu is a unified behavior‑compression layer that reduces each user behavior item to 2–4 tokens, dramatically shrinking per‑item cache size while preserving fidelity through a four‑stage training process. In production across four profiling tasks, it matches or outperforms uncompressed single‑task models, boosts GPU throughput by 37–350%, and saves 190 GPUs. On public benchmarks it consistently beats prior compressors at the same compression ratio, and on RecBench a 4B KuaFu model outperforms its 8B counterpart by 1.90 points, contributing to a 1.37% lift in overall GMV on Tencent’s advertising and recommendation platform.
arXiv Computation and Language
Sep 15
Lexical Prompt Compression for Large Language Models: A Training-Free, Deterministic Pipeline with Empirical Pareto Analysis Across Eleven Task Categories
arXiv:2609.13154v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have made prompts increasingly large and complex. Techniques such as chain-of-thought reasoning (Wei et...
Hugging Face Trending Papers
Aug 6
CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents
Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it. On SWE-Bench Verified, a 30B OpenHands agent averages 23 rounds and 631K tokens per resolved issue, with many calls spent on grep, glob, and view_file during repository exploration.