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

• URL: http://arxiv.org/abs/2504.14597v1
• Date: Sun, 20 Apr 2025 12:55:59 GMT
• Title: a1: Steep Test-time Scaling Law via Environment Augmented Generation
• Abstract summary: Environment Augmented Generation (EAG) is a framework that enhances large language models' reasoning through real-time environmental feedback.<n>EAG enables deliberate backtracking and strategic replanning through tight integration of execution feedback and branching exploration.<n>A1-32B model achieves state-of-the-art performance among similar-sized models across all benchmarks.
• Score: 45.19240207975418
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution [20.75638062019513]
  We propose GCA-Bench, a benchmark featuring challenging textitgrasping with complex action scenarios.<n>We implement a diverse set of baselines, ranging from traditional grasp detection pipelines to end-to-end learning methods.<n>In addition, we propose new evaluation metrics, analyze critical failure models, and provide insights to guide the development of more robust and generalizable grasping strategies.
  arXiv  Detail & Related papers  (2026-07-15T20:10:09Z)
• Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models [9.545957160908115]
  Heuristic- Classification-of-Thoughts prompting schema (HCoT)<n>Heuristic- Classification-of-Thoughts prompting schema (HCoT)<n>Heuristic- Classification-of-Thoughts prompting schema (HCoT)
  arXiv  Detail & Related papers  (2026-04-14T07:24:08Z)
• CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation [6.356820150960838]
  We introduce two complementary approaches inspired by test-time scaling to stabilize vision-language models.<n>CASHEW is an inference-time framework that stabilizes reasoning by iteratively aggregating multiple candidate trajectories into higher-quality reasoning traces.<n>CASHEW-RL is trained using Group Sequence Policy Optimization (GSPO) with a composite reward that encourages correct answers grounded in minimal yet sufficient visual evidence.
  arXiv  Detail & Related papers  (2026-01-12T21:24:45Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping [54.37497695483689]
  We propose ARES, a unified framework for adaptive reasoning that dynamically allocates exploration effort based on task difficulty.<n>Our approach is motivated by two key empirical findings: (i) while single-token entropy is noisy, high window-entropy (HWE) tokens can reliably capture reasoning-critical moments.<n>In the Adaptive Cold-Start stage, we curate multimodal and textual data paired with reasoning traces of length proportional to problem difficulty, equipping the model with initial difficulty awareness.<n>In the second stage, we develop Adaptive Entropy Policy Optimization (AEPO), which uses HWE tokens as exploration triggers
  arXiv  Detail & Related papers  (2025-10-09T17:03:28Z)
• A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning [57.727084580884075]
  Asymmetric Two-Stage Reasoning framework designed to bridge gap between a model's potential and its actual performance.<n>A2R-Efficient is a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer.<n>Results show A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.
  arXiv  Detail & Related papers  (2025-09-26T08:27:03Z)
• Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework [12.361554676966552]
  Recent advances in large language models (LLMs) have accelerated progress toward artificial general intelligence.<n>We aim to design a flexible test-time collaborative inference framework that exploits the complementary strengths of both sequential and parallel reasoning paradigms.
  arXiv  Detail & Related papers  (2025-07-09T13:28:35Z)
• GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning.<n>Using SEED-Bench-R1, we find that standard GRPO, while improving answer accuracy, often reduces logical coherence between reasoning steps and answers, with only a 57.9% consistency rate.<n>We propose GRPO-CARE, a consistency-aware RL framework optimizing both answer correctness and reasoning coherence without explicit supervision.
  arXiv  Detail & Related papers  (2025-06-19T08:49:13Z)
• Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges [6.615766570234612]
  Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models.<n>To address these challenges, the field has shifted toward Reasoning Agentic RAG, a paradigm that embeds decision-making and adaptive tool use directly into the retrieval process.
  arXiv  Detail & Related papers  (2025-06-12T07:01:56Z)
• Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning [75.04643265875072]
  Large reasoning models (LRMs) have demonstrated strong performance on complex reasoning tasks, but often suffer from overthinking.<n>Inspired by the dual process theory in cognitive science, we propose Adaptive Cognition Policy Optimization.<n>ACPO enables LRMs to achieve efficient reasoning through adaptive cognitive allocation and dynamic system switch.
  arXiv  Detail & Related papers  (2025-05-22T07:15:08Z)
• Credible plan-driven RAG method for Multi-hop Question Answering [2.5772544412212985]
  Multi-hop question answering (QA) presents a considerable challenge for Retrieval-Augmented Generation (RAG) deviations in reasoning paths or errors in intermediate results, which are common in current RAG methods, may propagate and accumulate throughout the reasoning process. We propose the Plan-then-Act-and-Review (PAR RAG) framework, which is organized into three key stages: planning, act, and review.
  arXiv  Detail & Related papers  (2025-04-23T15:03:17Z)
• AlignRAG: An Adaptable Framework for Resolving Misalignments in Retrieval-Aware Reasoning of RAG [61.28113271728859]
  Retrieval-augmented generation (RAG) has emerged as a foundational paradigm for knowledge-grounded text generation. Existing RAG pipelines often fail to ensure that the reasoning trajectories align with the evidential constraints imposed by retrieved content. We propose AlignRAG, a novel test-time framework that mitigates reasoning misalignment through iterative Critique-Driven Alignment steps.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM [18.275547804539016]
  We present two-Staged history-Resampling Policy Optimization (SRPO), which surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks.<n>We introduce two key methodological innovations: (1) a two-stage cross-domain training paradigm designed to balance the development of mathematical reasoning and coding proficiency, and (2) History Resampling (HR), a technique to address ineffective samples.
  arXiv  Detail & Related papers  (2025-04-19T13:06:03Z)
• S1-Bench: A Simple Benchmark for Evaluating System 1 Thinking Capability of Large Reasoning Models [13.083179473480705]
  Large Reasoning Models' (LRMs) reliance on deep analytical thinking may limit their system 1 thinking capabilities. We introduce S1-Bench, a novel benchmark designed to evaluate LRMs' performance on simple tasks.
  arXiv  Detail & Related papers  (2025-04-14T16:13:23Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging [17.038807261969033]
  Long-to-Short (L2S) reasoning aims to balance reasoning depth with practical efficiency.<n>Model merging offers a cost-effective and robust alternative by integrating the quick-thinking capabilities of System 1 models with the methodical reasoning of System 2 models.<n>Our experiments reveal that model merging can reduce average response length by up to 55% while preserving or even improving baseline performance.
  arXiv  Detail & Related papers  (2025-03-26T15:34:37Z)
• FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving [90.88021670297664]
  FINEREASON is a logic-puzzle benchmark for evaluation of large language models' reasoning capabilities. We introduce two tasks: state checking, and state transition, for a comprehensive evaluation of how models assess the current situation and plan the next move. We show that models trained on our state checking and transition data demonstrate gains in math reasoning by up to 5.1% on GSM8K.
  arXiv  Detail & Related papers  (2025-02-27T16:23:25Z)
• A NotSo Simple Way to Beat Simple Bench [0.0]
  This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs)<n>We propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness.<n>Our results reveal model-specific strengths: Claude excels in maintaining logical consistency, while GPT-4o exhibits exploratory creativity but struggles with ambiguous prompts.
  arXiv  Detail & Related papers  (2024-12-12T16:04:31Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)

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.