CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents

• URL: http://arxiv.org/abs/2607.22711v1
• Date: Mon, 20 Jul 2026 23:01:39 GMT
• Title: CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents
• Abstract summary: CORVUS is a novel trajectory architecture that decouples file-read actions from their observations.<n>It produces significantly lighter-weight trajectories that remain synchronized with the actual state by construction.
• Score: 8.604672064317235
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making. However, the conventional append-only trajectory architecture found in practice tightly couples file-read actions with their observations, capturing snapshots that become permanently fixed in the chronological history. As files change through agent edits or concurrent human modifications, these snapshots become stale, causing reasoning errors and causing agents to redundantly re-read files, with each re-read appending yet another copy to the trajectory. To mitigate this, we propose CORVUS, a novel trajectory architecture that decouples file-read actions from their observations by maintaining a synchronized registry of relevant files and injecting only their current contents at each reasoning cycle. This structural change produces significantly lighter-weight trajectories that remain synchronized with the actual codebase state by construction, eliminating redundant file copies and stale snapshots that bloat conventional trajectories. We evaluated CORVUS on SWE- POLYBENCH_VERIFIED and SWE-BENCH PRO across four LLMs, achieving 9-50% reduction in average input tokens per task, 15-32% shorter final prompts, and up to 37% fewer reasoning cycles while maintaining comparable pass rates.

Related papers

• Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior [107.2098567818173]
  Latent Recurrent Transformer (LRT) is a lightweight augmentation of autoregressive transformers.<n>LRT reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token.
  arXiv  Detail & Related papers  (2026-05-26T10:10:26Z)
• Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning [14.508049757681862]
  LLM-powered coding agents spend the majority of their token budget reading repository files.<n>We show that this formulation creates a modeling bottleneck.<n>We propose LaMR, a structured pruning framework that decomposes code relevance into two interpretable quality dimensions.
  arXiv  Detail & Related papers  (2026-05-14T18:30:10Z)
• Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents [8.880437352929315]
  Slipstream is a trajectory-grounded compaction system that uses a judge to validate the candidate summary against the agent's continued reasoning.<n>It improves task accuracy by up to 8.8 percentage points while reducing end-to-end latency by up to 39.7%.
  arXiv  Detail & Related papers  (2026-05-09T00:47:43Z)
• A Parametric Memory Head for Continual Generative Retrieval [52.66674234249913]
  Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from queries.<n>We show that sequential adaptation improves retrieval on newly added documents but substantially degrades performance on earlier slices.<n>We propose post-adaptation memory tuning (PAMT), a memory-only stabilization stage that augments an adapted model with a modular parametric memory head.
  arXiv  Detail & Related papers  (2026-04-25T17:38:51Z)
• DiffuRank: Effective Document Reranking with Diffusion Language Models [71.16830004674513]
  We propose DiffuRank, a reranking framework built upon diffusion language models (dLLMs)<n>dLLMs support more flexible decoding and generation processes that are not constrained to a left-to-right order.<n>We show dLLMs achieve performance comparable to, and in some cases exceeding, that of autoregressive LLMs with similar model sizes.
  arXiv  Detail & Related papers  (2026-02-13T02:18:14Z)
• Accelerating Structured Chain-of-Thought in Autonomous Vehicles [55.78214218065611]
  Chain-of-Thought (CoT) reasoning enhances the decision-making capabilities of vision-language-action models in autonomous driving.<n>FastDriveCoT is a novel parallel decoding method that accelerates template-structured CoT.
  arXiv  Detail & Related papers  (2026-02-02T22:14:26Z)
• DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding [66.40658898418316]
  We present DiffuSpec, a training-free drop-in framework that uses a pretrained diffusion language model (DLM) to produce multi-token drafts in a single forward pass.<n>Across benchmarks, DiffuSpec yields up to 3x wall-clock speedup, establishing diffusion-based drafting as a robust alternative to autoregressive drafters for speculative decoding.
  arXiv  Detail & Related papers  (2025-09-28T07:00:15Z)
• FastEagle: Cascaded Drafting for Accelerating Speculative Decoding [6.482154864678126]
  We present FastEagle, a non-autoregressive cascaded drafter that emits an entire draft in a single forward pass.<n>FastEagle delivers substantial wall-clock speedups over strong autoregressive drafters while maintaining competitive acceptance behavior.
  arXiv  Detail & Related papers  (2025-09-24T09:38:32Z)
• Tracezip: Efficient Distributed Tracing via Trace Compression [26.353398496686854]
  Distributed tracing serves as a fundamental building block in the monitoring and testing of cloud service systems.<n>Head-based sampling indiscriminately selects requests to trace when they enter the system, which may miss critical events.<n> tail-based sampling first captures all requests and then selectively persists the edge-case traces.<n>We propose Tracezip to enhance the efficiency of distributed tracing via trace compression.
  arXiv  Detail & Related papers  (2025-02-10T10:13:57Z)
• Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster [61.83949316226113]
  FastCoT is a model-agnostic framework based on parallel decoding. We show that FastCoT saves inference time by nearly 20% with only a negligible performance drop compared to the regular approach.
  arXiv  Detail & Related papers  (2023-11-14T15:56:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.