CoACT: Action-Preserving Observation Compression for Coding Agents

• URL: http://arxiv.org/abs/2607.02911v1
• Date: Fri, 03 Jul 2026 03:17:52 GMT
• Title: CoACT: Action-Preserving Observation Compression for Coding Agents
• Abstract summary: This paper proposes CoACT, an action-preserving observation compression method for coding agents.<n>CoACT is built on next-action preservation (NAP), which requires a compressed observation to induce the same next action as the raw observation.<n> Experiments on SWE-bench Verified with three agentic models show that CoACT reduces average total token consumption by 33.0%.
• Score: 8.484842324052751
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-based coding agents solve software-engineering tasks through iterative interactions with development environments, where returned observations accumulate in the context and become a major source of inference cost. Observation compression reduces this cost by shortening observations before they are appended to the context. However, existing methods still exhibit an unsatisfactory efficiency-effectiveness trade-off, as they do not explicitly model how compression affects the agent's subsequent behavior. This paper proposes CoACT, an action-preserving observation compression method for coding agents. CoACT is built on next-action preservation (NAP), which requires a compressed observation to induce the same next action as the raw observation. By checking the agent's immediate next action, NAP provides a practical signal for whether a compression preserves the information needed for continued task solving. During training, a teacher model first generates multiple compressed candidates of each observation. CoACT then uses an action-preservation reward based on NAP to filter out candidates that would change the agent's next action, and uses a length-reduction reward to choose compact candidates as supervision for a lightweight compressor. Experiments on SWE-bench Verified with three agentic models show that CoACT reduces average total token consumption by 33.0% while maintaining task-solving effectiveness close to the uncompressed agent.

Related papers

• Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models [62.522141464687195]
  We introduce Action-JND, which extends the principle of just noticeable difference (JND) to embodied perception.<n>A token change is considered tolerable only when the induced action deviation remains within a tolerated margin.<n>The resulting action-tolerance score serves as a plug-and-play criterion for VLA compression paradigms.
  arXiv  Detail & Related papers  (2026-08-21T15:59:37Z)
• Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability [7.183748353637384]
  We show that compression can weaken the influence of recent interactions, increasing blocked actions, repeated exploration, and instability across runs.<n>We introduce TRACE, a verifier-guided framework that evaluates individual compaction events through paired closed-loop continuations from the same environment state.<n>Initial results on AppWorld show improvements over existing compression baselines in task performance, multi-run reliability, and context--execution efficiency.
  arXiv  Detail & Related papers  (2026-08-06T18:42:02Z)
• On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation [22.803236151303846]
  Repository-level code intelligence tasks require large language models to process long, multi-file contexts.<n> Context compression mitigates these risks by condensing inputs.<n>We present the first systematic empirical study of context compression for repository-level code intelligence.
  arXiv  Detail & Related papers  (2026-04-15T11:00:17Z)
• Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching [42.26405543045843]
  Action-based Policy Compression (APC) is widely recognized as sample-inefficient.<n>We introduce Occupancy-based Policy Compression (OPC), which enhances APC by shifting behavior representation from immediate action-matching to long-horizon state-space coverage.<n>These modifications force the generative model to organize the latent space around true functional similarity, promoting a latent representation that generalizes over a broad spectrum of behaviors.
  arXiv  Detail & Related papers  (2026-03-27T23:16:27Z)
• AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery [5.110708177092157]
  We present AutoResearch-RL, a framework in which a reinforcement learning agent conducts open-ended neural architecture research without human supervision.<n>We formalise this as a Markov Decision Process, derive convergence guarantees under mild assumptions, and demonstrate empirically on a single GPU nanochat pretraining benchmark.
  arXiv  Detail & Related papers  (2026-03-07T17:49:44Z)
• Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation [49.48204107529758]
  We define token overflow as a regime in which compressed representations no longer contain sufficient information to answer a given query.<n>In this paper, we find that query-agnostic saturation statistics reliably separate compressed from uncompressed token representations.<n>Lightweight probing classifiers over both query and context xRAG representations detect overflow with 0.72 AUC-ROC on average.<n>These results advance from query-independent diagnostics to query-aware detectors, enabling low-cost pre-LLM gating to mitigate compression-induced errors.
  arXiv  Detail & Related papers  (2026-02-12T18:15:08Z)
• Activations and Gradients Compression for Model-Parallel Training [85.99744701008802]
  We study how simultaneous compression of activations and gradients in model-parallel distributed training setup affects convergence. We find that gradients require milder compression rates than activations. Experiments also show that models trained with TopK perform well only when compression is also applied during inference.
  arXiv  Detail & Related papers  (2024-01-15T15:54:54Z)
• ReAct: Temporal Action Detection with Relational Queries [84.76646044604055]
  This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries. We first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries.
  arXiv  Detail & Related papers  (2022-07-14T17:46:37Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning [92.05556163518999]
  MARL exacerbates matters by imposing various constraints on communication and observability. For value-based methods, it poses challenges in accurately representing the optimal value function. For policy gradient methods, it makes training the critic difficult and exacerbates the problem of the lagging critic. We show that from a learning theory perspective, both problems can be addressed by accurately representing the associated action-value function.
  arXiv  Detail & Related papers  (2021-05-31T23:08:05Z)

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.