paper-with-me

홈 › Papers

a1: Steep Test-time Scaling Law via Environment Augmented Generation

2025-04-20 · Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Yuyao Ge, Jun Wan, Yurong Wu, Xueqi Cheng

Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks. Current approaches like chain-of-thought prompting offer limited reasoning capabilities that fail when precise step validation is required. We propose Environment Augmented Generation (EAG), a framework that enhances LLM reasoning through: (1) real-time environmental feedback validating each reasoning step, (2) dynamic branch exploration for investigating alternative solution paths when faced with errors, and (3) experience-based learning from successful reasoning trajectories. Unlike existing methods, EAG enables deliberate backtracking and strategic replanning through tight integration of execution feedback with branching exploration. Our a1-32B model achieves state-of-the-art performance among similar-sized models across all benchmarks, matching larger models like o1 on competition mathematics while outperforming comparable models by up to 24.4 percentage points. Analysis reveals EAG's distinctive scaling pattern: initial token investment in environment interaction yields substantial long-term performance dividends, with advantages amplifying proportionally to task complexity. EAG's theoretical framework demonstrates how environment interactivity and systematic branch exploration together establish a new paradigm for reliable machine reasoning, particularly for problems requiring precise multi-step calculation and logical verification.

📄 PDF Abstract BibTeX arXiv:2504.14597

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Budget-Aware Tool Use Enables Effective Agent Scaling

2025-11-21 · Tengxiao Liu, Zifeng Wang, Jin Miao, I-Hung Hsu 외 arxiv

Scaling test-time computation has been extended from language model reasoning to tool-augmented agents, where scaling involves not only thinking in tokens but also acting via tool calls that directly constrain environmen…

Efficient Test-Time Scaling for Small Vision-Language Models

2025-10-03 · Mehmet Onurcan Kaya, Desmond Elliott, Dim P. Papadopoulos arxiv

Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed …

Computational EfficiencyTest-time Adaptation

On the Optimizer Dependence of Neural Scaling Laws

2026-05-28 · Vansh Ramani, Shourya Vir Jain arxiv

The scaling exponent $α$ in neural scaling laws $L(N) \propto N^{-α}$ is commonly treated as a fixed constant set by architecture and data. We present evidence that $α$ depends systematically on the optimizer. In control…

Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming

2026-04-01 · Qianfan Zhang, Tianyu Guo, Xuandi Ren, Jiale Chen 외 arxiv

We study how to scale reasoning token budgets for competitive programming through two complementary approaches: training-time reinforcement learning (RL) and test-time parallel thinking. During RL training, we observe an…

Reinforcement Learning

Hologram: Realtime Holographic Overlays via LiDAR Augmented Reconstruction

2024-05-12 · Ekansh Agrawal

Guided by the hologram technology of the infamous Star Wars franchise, I present an application that creates real-time holographic overlays using LiDAR augmented 3D reconstruction. Prior attempts involve SLAM or NeRFs wh…

3D Reconstruction