SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling

• URL: http://arxiv.org/abs/2604.14820v1
• Date: Thu, 16 Apr 2026 09:41:47 GMT
• Title: SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling
• Abstract summary: Current pipelines are bottlenecked by unoptimized demonstration data, sparse execution rewards, and computationally prohibitive inference scaling.<n>We present SWE-TRACE, a unified framework optimizing the SWE agent lifecycle across data curation, reinforcement learning (RL), and test-time inference.<n> experiments on standard SWE benchmarks demonstrate that SWE-TRACE significantly advances the state-of-the-art, maximizing resolution rates while drastically reducing both token consumption inference latency.
• Score: 13.335296846555204
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Resolving real-world software engineering (SWE) issues with autonomous agents requires complex, long-horizon reasoning. Current pipelines are bottlenecked by unoptimized demonstration data, sparse execution rewards, and computationally prohibitive inference scaling, which collectively exacerbate token bloat, reward hacking, and policy degradation. We present SWE-TRACE (Trajectory Reduction and Agentic Criteria Evaluation), a unified framework optimizing the SWE agent lifecycle across data curation, reinforcement learning (RL), and test-time inference. First, we introduce an LLM multi-task cascading method, utilizing stepwise oracle verification to distill a 60K-instance Supervised Fine-Tuning (SFT) corpus strictly biased toward token-efficient, shortest-path trajectories. Second, to overcome the instability of sparse outcome rewards, we design a MemoryAugmented Agentic RL pipeline featuring a Rubric-Based Process Reward Model (PRM). An auxiliary Rubric-Agent provides dense, fine-grained heuristic feedback on intermediate steps, guiding the model through long-horizon tasks. Finally, we bridge training and inference by repurposing the PRM for heuristic-guided Test-Time Scaling (TTS). By dynamically evaluating and pruning action candidates at each step, SWE-TRACE achieves superior search efficiency without the latency overhead of standard parallel sampling. Extensive experiments on standard SWE benchmarks demonstrate that SWE-TRACE significantly advances the state-of-the-art, maximizing resolution rates while drastically reducing both token consumption and inference latency.

Related papers

• Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models [56.67321805551389]
  Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.<n>The sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy.<n>We propose a new sampler that balances effective exploration with stability.
  arXiv  Detail & Related papers  (2026-05-22T11:37:22Z)
• SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents [0.31034395048547575]
  Existing approaches rely on static prompting strategies or handcrafteds to select actions such as code editing, file navigation, and test execution.<n>We propose SWE-Shepherd, a framework that introduces Process Reward Models (PRMs) to provide dense, step-level supervision for repository-level code agents.<n>Experiments on SWE-Bench Verified demonstrate improved interaction efficiency and action quality, while also highlighting challenges in aligning intermediate rewards with final task success.
  arXiv  Detail & Related papers  (2026-04-12T06:51:47Z)
• Agentic Test-Time Scaling for WebAgents [65.5178428849495]
  We present Confidence-Aware Test-Time Scaling (CATTS), which uses vote-derived uncertainty to allocate compute only when decisions are genuinely contentious.<n>CATTS improves performance on WebArena-Lite and GoBrowse by up to 9.1% over React while using up to 2.3x fewer tokens than uniform scaling.
  arXiv  Detail & Related papers  (2026-02-12T18:58:30Z)
• SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents [12.355536750226555]
  Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering tasks.<n>We introduce SWE-Replay, the first efficient and generalizable test-time scaling technique for modern agents without reliance on potentially noisy value estimates.<n>Our evaluation shows that, on SWE-Bench Verified, SWE-Replay consistently outperforms naive scaling, reducing costs by up to 17.4% while maintaining or even improving performance by up to 3.8%.
  arXiv  Detail & Related papers  (2026-01-29T18:50:29Z)
• Scaling Unverifiable Rewards: A Case Study on Visual Insights [29.54766251030519]
  Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS)<n>We propose Selective TTS, a process-based refinement framework that scales inference across different stages in multi-agent pipeline.<n>Our proposed selective TTS then improves insight quality under a fixed compute budget, increasing mean scores from 61.64 to 65.86 while reducing variance.
  arXiv  Detail & Related papers  (2025-12-27T17:01:38Z)
• Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization [13.475938754147625]
  Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks.<n>Agentic Reinforcement Learning (Agentic RL) optimize such models over full tool-interaction trajectories.<n>Two key challenges hinder effectiveness: (1) Sparse, non-instructive rewards, such as binary 0-1 verifiable signals, provide limited guidance for intermediate steps and slow convergence.<n>We propose two complementary techniques: Progressive Reward Shaping (PRS) and Value-based Sampling Policy Optimization (VSPO).
  arXiv  Detail & Related papers  (2025-12-08T11:59:25Z)
• Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning [71.30276778807068]
  We propose a unified framework that strategically coordinates sample pruning and token pruning.<n>Q-Tuning achieves a +38% average improvement over the full-data SFT baseline using only 12.5% of the original training data.
  arXiv  Detail & Related papers  (2025-09-28T13:27:38Z)
• EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving [64.15371139980802]
  Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP)<n>We show that different test-time scaling strategies for ATP models introduce significant computational overhead for inference.<n>We propose two complementary methods that can be integrated into a unified EconRL pipeline for amplified benefits.
  arXiv  Detail & Related papers  (2025-09-16T03:00:13Z)
• 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)
• ConSol: Sequential Probability Ratio Testing to Find Consistent LLM Reasoning Paths Efficiently [3.6393221632527686]
  Small language models (LLMs) solve complex tasks by generating intermediate reasoning steps prior to providing answers.<n>The widely-used self-consistency method further exacerbates these costs by aggregating multiple reasoning paths to improve accuracy.<n>We propose leveraging Sequential Probability Ratio Testing (SPRT) to dynamically terminate sampling once sufficient consistency is achieved.
  arXiv  Detail & Related papers  (2025-03-22T00:07:28Z)
• Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization [67.8738082040299]
  Self-Sampling Preference Optimization (SSPO) is a new alignment method for post-training reinforcement learning.<n>SSPO eliminates the need for paired data and reward models while retaining the training stability of SFT.<n>SSPO surpasses all previous approaches on the text-to-image benchmarks and demonstrates outstanding performance on the text-to-video benchmarks.
  arXiv  Detail & Related papers  (2024-10-07T17:56:53Z)

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.