DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal
- URL: http://arxiv.org/abs/2503.14269v1
- Date: Tue, 18 Mar 2025 14:02:59 GMT
- Title: DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal
- Authors: Vaibhav Aggarwal, Ojasv Kamal, Abhinav Japesh, Zhijing Jin, Bernhard Schölkopf,
- Abstract summary: Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
- Score: 55.13854171147104
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered significant attention due to their potential to automate complex development tasks, assist in debugging, and enhance productivity. However, existing approaches often struggle with sub-optimal decision-making, requiring either extensive manual intervention or inefficient compute scaling strategies. To improve coding agent performance, we present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents, that is faster and more effective at recovering from sub-optimal decisions compared to baselines. While traditional agents either follow linear trajectories or rely on random sampling for scaling compute, our approach DARS works by branching out a trajectory at certain key decision points by taking an alternative action given the history of the trajectory and execution feedback of the previous attempt from that point. We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2. Our framework achieves a pass@1 rate of 47%, outperforming state-of-the-art (SOTA) open-source frameworks.
Related papers
- Agentic Reinforced Policy Optimization [66.96989268893932]
Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
arXiv Detail & Related papers (2025-07-26T07:53:11Z) - Scalability of Reinforcement Learning Methods for Dispatching in Semiconductor Frontend Fabs: A Comparison of Open-Source Models with Real Industry Datasets [40.434003972007744]
We compare open-source simulation models with a real industry dataset to evaluate how optimization methods scale with different levels of complexity.<n>We show that our proposed Evolution Strategies-based method scales much better than a comparable policy-gradient-based approach.<n>We observe double-digit percentage improvement in tardiness and single digit percentage improvement in throughput by use of Evolution Strategies.
arXiv Detail & Related papers (2025-05-16T11:32:29Z) - Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection [71.92083784393418]
Inference-time methods such as Best-of-N (BON) sampling offer a simple yet effective alternative to improve performance.
We propose Iterative Agent Decoding (IAD) which combines iterative refinement with dynamic candidate evaluation and selection guided by a verifier.
arXiv Detail & Related papers (2025-04-02T17:40:47Z) - 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.
Our framework incorporates two complementary strategies: internal TTC and external TTC.
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) - Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
arXiv Detail & Related papers (2025-01-31T17:19:57Z) - From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
arXiv Detail & Related papers (2024-11-06T10:35:11Z) - SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [18.84439000902905]
Current large language model (LLM)-based software agents often follow linear, sequential processes.<n>We propose SWE-Search, a multi-agent framework that integrates Monte Carlo Tree Search (MCTS) with a self-improvement mechanism.<n>This highlights the potential of self-evaluation driven search techniques in complex software engineering environments.
arXiv Detail & Related papers (2024-10-26T22:45:56Z) - Let's reward step by step: Step-Level reward model as the Navigators for
Reasoning [64.27898739929734]
Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase.
We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs.
To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
arXiv Detail & Related papers (2023-10-16T05:21:50Z) - Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm
Deployed in Ridehailing Marketplace [12.298997392937876]
This study proposes a real-time dispatching algorithm based on reinforcement learning.
It is deployed online in multiple cities under DiDi's operation for A/B testing and is launched in one of the major international markets.
The deployed algorithm shows over 1.3% improvement in total driver income from A/B testing.
arXiv Detail & Related papers (2022-02-10T16:07:17Z)
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.