Self-Compacting Language Model Agents

• URL: http://arxiv.org/abs/2606.23525v1
• Date: Mon, 22 Jun 2026 16:08:34 GMT
• Title: Self-Compacting Language Model Agents
• Abstract summary: SelfCompact is a scaffold that allows the model itself to decide when and how to compact.<n>It elicits effective adaptive compaction without any fine-tuning or external supervision.<n>Our results show that SelfCompact matches or exceeds fixed-interval summarization at a fraction of the token cost.
• Score: 44.3231488987671
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaffolds mitigate it with fixed-interval compaction triggered at a token threshold. Such triggers pay no heed to trajectory structure, risking discard of partial results mid-derivation or mid-search. We propose SelfCompact, a scaffold that allows the model itself to decide when and how to compact. Specifically, it pairs two inference-time elements: (i) a compaction tool the model invokes to summarize the accumulated context, and (ii) a lightweight rubric specifying when to fire (a sub-task has resolved, or the trajectory is converging) and when to suppress (mid-derivation, or when stuck). Both are needed. The tool alone is unevenly used across open-weight models, often invoked at unhelpful moments or not at all; the rubric alone cannot act. Together, they elicit effective adaptive compaction without any fine-tuning or external supervision. We present empirical results on six benchmarks (competitive math and agentic search) and seven models. Our results show that SelfCompact matches or exceeds fixed-interval summarization at a fraction of the token cost, improving over a no-summarization baseline by up to 18.1 points on math and 5-9 points on agentic search at 30-70% lower per-question cost. Our results expose a meta-cognitive gap: although unprompted models cannot reliably tell when their own context is rotting, a lightweight rubric closes this gap, reframing when to compact as a capability that scaffolds can supply without training.

Related papers

• WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents [53.426679066400844]
  We introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery.<n>We develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout.<n>We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image.
  arXiv  Detail & Related papers  (2026-08-28T08:28:43Z)
• When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecasting [10.826557947047933]
  Multi-modal time series forecasting methods integrate auxiliary context into temporal predictions through increasingly sophisticated fusion mechanisms.<n>We ask a narrower, checkable question: when can auxiliary context help a forecaster at all?<n>We identify two dataset-level conditions that must both hold: (1) the target is not dominated by a last-value shortcut (low autocorrelation rho_h), and (2) the context carries information about the target beyond history.
  arXiv  Detail & Related papers  (2026-08-25T20:25:49Z)
• DoublesEval: Diagnosing Multi-Agent Tactical Reasoning in Vision-Language Models via Professional Doubles Badminton [1.6892008660392037]
  Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions.<n>We formalize this capability as textbfmulti-agent tactical reasoning and introduce textbfDoublesEval, a diagnostic evaluation framework.<n>DoublesEval employs a key-moment-based protocol that decomposes rallies into tactically salient instants and probes models across four interpretable dimensions.
  arXiv  Detail & Related papers  (2026-08-25T11:51:01Z)
• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism [23.342723567214733]
  Long-horizon search agents accumulate large amounts of retrieved content across many tool calls.<n>We study observation masking through a systematic sweep over various agent backbones and three retrievers on offline and live-web agentic search benchmarks.<n>We find that the accuracy gain from masking follows an asymmetric inverted-U shape when plotted against the model's accuracy without context management.
  arXiv  Detail & Related papers  (2026-05-29T22:51:58Z)
• Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents [0.4666493857924357]
  We study whether inference-time scaffolding alone, without any additional training compute, can improve the performance of a small model in complex multi-step environments.<n>We evaluate Qwen3-8B on the AppWorld benchmark under both full-precision and 4-bit quantized configurations.<n>On full-precision inference, our scaffolded 8B model surpasses DeepSeek-Coder 33B Instruct (7.1%) from the original AppWorld evaluation.
  arXiv  Detail & Related papers  (2026-04-13T13:40:33Z)
• Label-Free Cross-Task LoRA Merging with Null-Space Compression [50.63908869296697]
  We introduce Null-Space Compression (NSC) Merging, a label-free, output-agnostic method that sets merge weights from adapter geometry.<n>NSC achieves state-of-the-art performance across twenty heterogeneous vision tasks with balanced gains where prior methods overfit subsets of tasks.
  arXiv  Detail & Related papers  (2026-03-27T11:34:41Z)
• On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering [29.633206995806542]
  In-time steering enables pretrained diffusion/flow models to be adapted to new tasks without retraining.<n>This construction harbors a critical and previously unformalized failure mode: Marginal Path Collapse.<n>We introduce Adaptive path Correction with Exponents (ACE), which extends Feynman-Kac steering to time-varying exponents.
  arXiv  Detail & Related papers  (2025-12-11T06:44:08Z)
• Multi-Level Collaboration in Model Merging [56.31088116526825]
  This paper explores the intrinsic connections between model merging and model ensembling.<n>We find that even when previous restrictions are not met, there is still a way for model merging to attain a near-identical and superior performance similar to that of ensembling.
  arXiv  Detail & Related papers  (2025-03-03T07:45:04Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Single-Stage Visual Relationship Learning using Conditional Queries [60.90880759475021]
  TraCQ is a new formulation for scene graph generation that avoids the multi-task learning problem and the entity pair distribution. We employ a DETR-based encoder-decoder conditional queries to significantly reduce the entity label space as well. Experimental results show that TraCQ not only outperforms existing single-stage scene graph generation methods, it also beats many state-of-the-art two-stage methods on the Visual Genome dataset.
  arXiv  Detail & Related papers  (2023-06-09T06:02:01Z)
• Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis [69.07674653828565]
  Machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances. In this paper, we examine the implications of spurious correlations through a novel perspective called neighborhood analysis. We propose a family of regularization methods, NFL (doN't Forget your Language) to mitigate spurious correlations in text classification.
  arXiv  Detail & Related papers  (2023-05-23T03:55:50Z)

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.