AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents

Haotian Chen; Xin Cong; Shengda Fan; Yuyang Fu; Ziqin Gong; Yaxi Lu; Yishan Li; Boye Niu; Chengjun Pan; Zijun Song; Huadong Wang; Yesai Wu; Yueying Wu; Zihao Xie; Yukun Yan; Zhong Zhang; Yankai Lin; Zhiyuan Liu; Maosong Sun

arXiv · 2602.06485

AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents

Haotian Chen·Xin Cong·Shengda Fan·Yuyang Fu·Ziqin Gong·Yaxi Lu·Yishan Li·Boye Niu·Chengjun Pan·Zijun Song·Huadong Wang·Yesai Wu·Yueying Wu·Zihao Xie·Yukun Yan·Zhong Zhang·Yankai Lin·Zhiyuan Liu·Maosong Sun

View original source ↗Read source document ↗Export metadata ↓

Abstract

While Large Language Model (LLM)-based agents have shown remarkable potential for solving complex tasks, existing systems remain heavily reliant on large-scale models, leaving the capabilities of edge-scale models largely underexplored. In this paper, we present the first systematic study on training agentic models at the 4B-parameter scale. We identify three primary bottlenecks hindering the performance of edge-scale models: catastrophic forgetting during Supervised Fine-Tuning (SFT), sensitivity to reward signal noise during Reinforcement Learning (RL), and reasoning degradation caused by redundant information in long-context scenarios. To address the issues, we propose AgentCPM-Explore, a compact 4B agent model with high knowledge density and strong exploration capability. We introduce a holistic training framework featuring parameter-space model fusion, reward signal denoising, and contextual information refinement. Through deep exploration, AgentCPM-Explore achieves state-of-the-art (SOTA) performance among 4B-class models, matches or surpasses 8B-class SOTA models on four benchmarks, and even outperforms larger-scale models such as Claude-4.5-Sonnet or DeepSeek-v3.2 in five benchmarks. Notably, AgentCPM-Explore achieves 97.09% accuracy on GAIA text-based tasks under pass@64. These results provide compelling evidence that the bottleneck for edge-scale models is not their inherent capability ceiling, but rather their inference stability. Based on our well-established training framework, AgentCPM-Explore effectively unlocks the significant, yet previously underestimated, potential of edge-scale models.

Explore related subjects

cs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Haotian Chen, Xin Cong, Shengda Fan, Yuyang Fu, Ziqin Gong, Yaxi Lu, Yishan Li, Boye Niu, Chengjun Pan, Zijun Song, Huadong Wang, Yesai Wu, Yueying Wu, Zihao Xie, Yukun Yan, Zhong Zhang, Yankai Lin, Zhiyuan Liu, Maosong Sun. 2026-02-06. AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents. https://arxiv.org/abs/2602.06485

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

Organic reaction mechanisms describe the step-wise elementary processes by which reactants transform into intermediates and products, and are fundamental to understanding chemical reactivity and guiding molecular and reaction de-sign. While large language models (LLMs) have shown promise on chemical tasks such as synthesis design, it remains unclear to what extent this reflects genuine chemical reasoning capabilities: the ability to generate chemically valid intermediates, maintain consistency across reaction steps, and follow logically coherent multi-step pathways. To investigate this, we introduce oMeBench, the first large-scale, expert-curated benchmark for organic mechanism reasoning, comprising over 10,000 annotated mechanistic steps with reaction type labels, intermediate structures, and difficulty ratings. To enable fine-grained evaluation, we further propose oMeS, a dynamic scoring framework that jointly assesses step-level logical consistency and chemical structural similarity. Systematic evaluation of state-of-the-art LLMs reveals that while current models exhibit promising chemical intuition, they struggle to produce correct and consistent reasoning across multi-step mechanisms. Notably, combining prompting strategies with fine-tuning enables smaller-scale models to achieve performance comparable to closed-source frontier models. We hope oMeBench will serve as a rigorous foundation for advancing AI systems toward genuine chemical reasoning.

cs.AI↗

arXiv2026

TripScore: Aligning LLMs for Real-World Travel Planning via Expert-Calibrated Reward

In our deployed travel-planning service, most users give minimal inputs or free-form requests rather than the structured constraint checklists assumed by existing benchmarks. We therefore present TripScore, a behavior-grounded benchmark and evaluation framework built from real user logs and calibrated against 1,468 pairwise judgments by 203 travel experts. TripScore couples a hierarchical feasibility gate (format and commonsense) with a unified, point-wise reward that aggregates soft quality and preference fulfillment. Using TripScore as both evaluator and reward signal, we benchmark direct prompting, test-time compute, neuro-symbolic solvers, code agents, and fine-tuning. We find that reinforcement learning fine-tuning (e.g., GRPO) provides consistent gains over other approaches under the same base model and practical latency.

cs.AI↗

arXiv2026

Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance

While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and data limitations in few shot scenarios. Existing selection methods fail to fully address this: they either rely on data-intensive proxies or use symmetric textual descriptors that neglect the inherently directional and model-specific nature of transferability. To address this problem, we propose a framework that grounds model selection in the internal functional dynamics of the visual encoder. Our approach represents each task via layer wise conductance and derives a target-conditioned block importance distribution through entropy regularized alignment. Building on this, we introduce Directional Conductance Divergence (DCD), an asymmetric metric that quantifies how effectively a source task covers the target's salient functional blocks. This allows for predicting target model rankings by aggregating source task ranks without direct inference. Experimental results on 48 VLMs across 21 datasets demonstrate that our method outperforms state-of-the-art baselines, achieving a 14.7% improvement in NDCG@5 over SWAB.

cs.AI↗