cs.AIMay 14, 2026

Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning

Authors: Jingjing WangXiwen ChenWenhui ZhuHuayu LiZhengxiao HeFeiyang CaiAna S. Carreon-RasconXuanzhao Dong+1 more

Organizations: Clemson University · Morgan Stanley · Arizona State University · University of Arizona

Abstract

LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned pruners compress this context with a single-objective sequence labeler, collapsing all facets of code relevance into one score and one transition matrix. We show that this formulation creates a modeling bottleneck: a single CRF transition prior must serve heterogeneous retention patterns, including contiguous semantic spans and sparse structural support lines. We propose LaMR (Latent Multi-Rubric), a structured pruning framework that decomposes code relevance into two interpretable quality dimensions, semantic evidence and dependency support, each modeled by a dedicated CRF with dimension-specific transition dynamics. A mixture-of-experts gating network dynamically weights the per-rubric emissions conditioned on the query, and a final CRF layer on the fused emissions produces the aggregate keep-or-prune decision. To supervise each dimension without additional annotation cost, we derive multi-rubric labels from the existing training corpus via AST-based program analysis, simultaneously denoising the teacher's binary labels. By effectively filtering distracting noise, LaMR frequently matches or even outperforms unpruned full-context baselines. Experiments on four benchmarks (SWE-Bench Verified, SWE-QA, LCC, LongCodeQA) show that LaMR wins 12 of 16 head-to-head multi-turn comparisons. It saves up to 31% more tokens on multi-turn agent tasks and improves Exact Match by up to +3.5 on single-turn tasks, while performance is frequently enhanced by denoising the context, and any remaining drops are marginal.

Explore similar work

CardsList
  1. SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

    Jul 20, 2026Yuhang Wang, Yuling Shi, Shaoqiu Zhang +6Coding AgentsPruning