Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents

• URL: http://arxiv.org/abs/2604.04979v1
• Date: Sat, 04 Apr 2026 18:52:44 GMT
• Title: Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
• Abstract summary: Coding agents repeatedly consume long tool observations even though only a small fraction of each observation matters for the next step.<n>We study task-conditioned tool-output pruning: given a focused query and one tool output, return the smallest verbatim evidence block the agent should inspect next.
• Score: 0.8714519393367773
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Coding agents repeatedly consume long tool observations even though only a small fraction of each observation matters for the next step. We study task-conditioned tool-output pruning: given a focused query and one tool output, return the smallest verbatim evidence block the agent should inspect next. We introduce a benchmark of 11,477 examples built from SWE-bench repository interactions and synthetic multi-ecosystem tool outputs, with a manually curated 618-example test set. We fine-tune Qwen 3.5 2B with LoRA and compare it against larger zero-shot models and heuristic pruning baselines. Our model reaches 0.86 recall and 0.80 F1 while removing 92% of input tokens, outperforming zero-shot Qwen 3.5 35B A3B by 11 recall points and all heuristic baselines by a wide margin.

Related papers

• One Policy Is Enough: Single-Agent Reinforcement Learning Outperforms Tree Search for Chemistry Tool Learning [24.13351033268791]
  CheMatAgent searches tool-call trees under two learned critics, one regressed partly onto GPT-assigned scores.<n>Our model interleaves reasoning, tool calls, and returns in one left-to-right generation, trained by a supervised warm-up and then outcome-level reinforcement learning.<n>On ChemToolBench multiple-tool comprehensive chemistry, on both backbones CheMatAgent use, we improve Tool F1 by 5.5% and Return F1 by 9.6% on Qwen-2.5-7B, and by 3.7% and 3.9% on Llama-3.1-8B, compared with their strongest search configuration
  arXiv  Detail & Related papers  (2026-08-31T15:22:19Z)
• Joint Optimization of Tool Creation and Use for Large Language Model Agents [69.07066297088187]
  SMITH (-grounded Multi-task Iterative Tool Honing) trains tool creation and tool use inside a single policy.<n>A 4B Qwen3 trained with SMITH on 13 procedural reasoning tasks with exact verifiers reaches 79.8 macro-average accuracy on held-out tasks.<n>It also reaches 40.4 on TabMWP-Hard and 42.6 on out-of-domain GQA (+7.6 over the best same-backbone inference-time baseline)
  arXiv  Detail & Related papers  (2026-08-25T13:59:34Z)
• SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents [64.59100414726556]
  Large language model (LLM) agents increasingly rely on harnesses that manage context, tools, and multi-turn execution.<n>Retrieval-augmented tool selection offers a natural alternative, but existing one-shot retrieval methods fail to align isolated tool descriptions with the agent's true task intention.<n>We propose SING, an intention-aware active tool discovery framework that builds an intention-tool graph linking user intentions, tool capabilities, and tool collaboration patterns.
  arXiv  Detail & Related papers  (2026-06-15T11:37:37Z)
• Agent Explorative Policy Optimization for Multimodal Agentic Reasoning [97.64835302176056]
  Agentic reasoning interleaves two behaviors with a structural asymmetry: thinking and tool use.<n>Under standard RL recipes like GRPO, the gap manifests as two diagnostic symptoms during training.<n>We propose AXPO (Agent eXplorative Policy Optimization) for each all-wrong tool-using subgroup.
  arXiv  Detail & Related papers  (2026-05-27T17:36:39Z)
• LLM Agents Already Know When to Call Tools -- Even Without Reasoning [25.40369702634587]
  LLM agents tend to call tools indiscriminately, even when the model can answer directly.<n>No existing benchmark systematically studies when a tool call is actually needed.<n>We propose When2Tool, a benchmark of 18 environments spanning three categories of tool necessity.
  arXiv  Detail & Related papers  (2026-05-10T01:37:40Z)
• Understanding NPM Malicious Package Detection: A Benchmark-Driven Empirical Analysis [10.599261033874884]
  NPM ecosystem has become a primary target for software supply chain attacks.<n>We conduct a benchmark-driven empirical analysis of NPM malware detection.<n>We build a dataset of 6,420 malicious and 7,288 benign packages annotated with 11 behavior categories and 8 evasion techniques.
  arXiv  Detail & Related papers  (2026-03-29T07:04:31Z)
• SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans [65.19021035010059]
  Research Agents enable models to gather information from the web using tools to answer user queries.<n>We observe that agents often exhibit poor exploration behaviors, including premature termination and biased tool usage.<n>We propose SynPlanResearch-R1, a framework that synthesizes tool-use trajectories that encourage deeper exploration.
  arXiv  Detail & Related papers  (2026-03-09T00:05:29Z)
• ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents [31.77712252239516]
  Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents.<n>There is a lack of systematic and reliable evaluation benchmarks for PRMs in tool-using settings.<n>We introduce ToolPRMBench, a large-scale benchmark specifically designed to evaluate PRMs for tool-using agents.
  arXiv  Detail & Related papers  (2026-01-18T07:48:36Z)
• RSAgent: Learning to Reason and Act for Text-Guided Segmentation via Multi-Turn Tool Invocations [52.752467948588816]
  We propose RSAgent, an agentic Multimodal Large Language Model (MLLM) which interleaves reasoning and action for segmentation via multi-turn tool invocations.<n> RSAgent queries a segmentation toolbox, observes visual feedback, and revises its spatial hypothesis using historical observations to re-localize targets and iteratively refine masks.<n>Extensive experiments show that RSAgent achieves a zero-shot performance of 66.5% gIoU on ReasonSeg test, improving over Seg-Zero-7B by 9%, and reaches 81.5% cIoU on RefCOCOg, demonstrating state-of-the-art performance
  arXiv  Detail & Related papers  (2025-12-30T06:50:11Z)
• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
  Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
  arXiv  Detail & Related papers  (2025-10-30T06:08:27Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)
• Tool-Augmented Reward Modeling [58.381678612409]
  We propose a tool-augmented preference modeling approach, named Themis, to address limitations by empowering RMs with access to external environments. Our study delves into the integration of external tools into RMs, enabling them to interact with diverse external sources. In human evaluations, RLHF trained with Themis attains an average win rate of 32% when compared to baselines.
  arXiv  Detail & Related papers  (2023-10-02T09:47:40Z)

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.