Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1

• URL: http://arxiv.org/abs/2607.06764v1
• Date: Tue, 07 Jul 2026 19:49:35 GMT
• Title: Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1
• Abstract summary: Recent progress on ARC-AGI-1 has come from two regimes: heavy test-time compute over frontier models, or benchmark-specific training in which small models are fine-tuned on ARC data.<n>We study what is recoverable through architecture alone, building agentic harnesses that decompose pattern-discovery and program-synthesis stages explicitly.
• Score: 4.486629113012585
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures. We study a third regime: an open-weight model in non-thinking mode (DeepSeek V3.2) under a strict budget, with no ARC-specific fine-tuning. We study what is recoverable through architecture alone, building agentic harnesses that decompose pattern-discovery and program-synthesis stages explicitly. First, we introduce an Explorer-Definer Pipeline that separates pattern discovery from executable transformation synthesis, implemented as a two-stage agent pipeline. Next, we present the Reflective Orchestrator, which augments the pipeline with autonomous exploration of new transformations when previous hypotheses fail on training pairs. On the ARC-AGI-1 public 400-task evaluation set, the pipeline reaches 57.50% pass@2 at \$0.25 per task, and the orchestrator reaches 67.25% pass@2 at \$0.62 per task. Together these architectures lift a 15.50% one-shot baseline by ~52 points without benchmark-specific training or heavy test-time compute. Furthermore, the orchestrator-driven lift tests a falsifiable diagnostic the pipeline produces; unbiased pass@k analysis suggests the pipeline is generation-bound, not selection-bound (selection via training-pair accuracy captures ~95% of the candidate ceiling) and predicts that significant improvement requires broader generation, not better ranking. The orchestrator implements this prediction via adaptive re-exploration and confirms it (unbiased pass@1 lift +9.81 pp, matching selection-mediated pass@2 lift). An additional pipeline ablation identifies its think tool as a significant component, with removal reducing pass@2 by 5.75 pp.

Related papers

• NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness [76.6324710887112]
  NeoHorse-1 is a family of agent-native models developed to explore this path through agentic post-training.<n>Our system combines a heterogeneous model pool with intelligent routing, recording the predicted capability demand, selected service tier, and subsequent interaction for each user turn.
  arXiv  Detail & Related papers  (2026-09-08T03:14:54Z)
• VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct [71.22358682581215]
  Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions.<n>We instantiate this as VeriEvol, an iterative framework with two components.<n>On a five-benchmark visual-math suite, scaling evolved SFT data from 10K to 250K samples raises the mean accuracy from 35.42 to 54.73.
  arXiv  Detail & Related papers  (2026-06-22T16:17:30Z)
• Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model [0.0]
  We run a controlled ablation study of a full agentic RAG pipeline evaluated on 5,000 questions.<n>We find that fixed hybrid retrieval via reciprocal rank fusion consistently outperforms rule-based adaptive routing.
  arXiv  Detail & Related papers  (2026-06-19T15:50:35Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design [9.382770582572784]
  We introduce a dual-framework approach: AIRA-Compose for high-level architecture search, and AIRA-Design for low-level mechanistic implementation.<n>AirA-Compose uses 11 agents to explore fundamental computational primitives under a 24-hour budget.<n>AirAformers (Transformer-based) and AIRAhybrids (Transformer-Mamba) consistently outperform Llama 3.2 and Composer-found baselines.
  arXiv  Detail & Related papers  (2026-05-15T11:40:41Z)
• PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents [53.369140518949656]
  We introduce PersonalAI 2.0 (PAI-2), a novel framework to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG)<n>The proposed approach addresses key limitations of existing Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage query processing pipeline.<n>We show that use of graph algorithms (e.g. BeamSearch, WaterCircles) gain superior results compared to standard flatten retriever on average 6%, while enabled search plan enhancement mechanism gain 18% boost compared to disabled one by LLM-as-a-Judge across six datasets.
  arXiv  Detail & Related papers  (2026-05-13T13:06:30Z)
• On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning [63.41902113656453]
  Supervised Fine-Tuning (SFT) on long Chain-of-Thought (CoT) trajectories has become a pivotal phase in building large reasoning models.<n>We conduct a comparative study using two sources of verified CoT trajectories generated by two competing models.<n>We find that SFT on textttDeepSeek-R1-0528 data achieves remarkably lower training loss, yet exhibits significantly worse generalization performance.
  arXiv  Detail & Related papers  (2026-04-02T07:00:54Z)
• APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay [7.370176470430802]
  LLM-based autonomous agents lack persistent procedural memory.<n>We present APEX-EM, a non-parametric online learning framework that accumulates, retrieves, and reuses structured procedural plans.
  arXiv  Detail & Related papers  (2026-03-31T00:24:56Z)
• Le-DETR: Revisiting Real-Time Detection Transformer with Efficient Encoder Design [72.55935017828891]
  We present Le-DETR (textbfLow-cost and textbfEfficient textbfDEtection textbfTRansformer)<n>It achieves a new textbfSOTA in real-time detection using only ImageNet1K and COCO 2017 training datasets.<n>It surpasses YOLOv12-L/X by textbf+0.6/-0.1 mAP while achieving similar speed and textbf+20% speedup.
  arXiv  Detail & Related papers  (2026-02-24T15:29:55Z)
• Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute [0.0]
  We empirically analyze the ARC Prize TRM checkpoint on ARC-AGI-1.<n>We show that test-time augmentation and majority-vote ensembling account for a substantial fraction of reported performance.<n>We also compare TRM with a naive QLoRA fine-tune of Llama 3 8B on canonical ARC-AGI-1.
  arXiv  Detail & Related papers  (2025-12-04T06:20:44Z)
• Relation DETR: Exploring Explicit Position Relation Prior for Object Detection [26.03892270020559]
  We present a scheme for enhancing the convergence and performance of DETR (DEtection TRansformer) Our approach, termed Relation-DETR, introduces an encoder to construct position relation embeddings for progressive attention refinement. Experiments on both generic and task-specific datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-07-16T13:17:07Z)
• Recurrent Glimpse-based Decoder for Detection with Transformer [85.64521612986456]
  We introduce a novel REcurrent Glimpse-based decOder (REGO) in this paper. In particular, the REGO employs a multi-stage recurrent processing structure to help the attention of DETR gradually focus on foreground objects. REGO consistently boosts the performance of different DETR detectors by up to 7% relative gain at the same setting of 50 training epochs.
  arXiv  Detail & Related papers  (2021-12-09T00:29:19Z)

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.