SWE-Touch is introduced, a framework that stress-tests this setting through validated Counter-Edits: plausible edits to task-relevant code that conflict with task completion, and point to detecting workspace changes, reconciling conflicting edits with the task, and verifying the affected behavior as key capabilities for future optimization.
Yuqiao Tan, Jinxiang Meng, Fangyu Lei et al.· 0 citations
Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. However, reasoning-oriented post-training for dLLMs remains challenging. Supervised fine-tuning (SFT) for dLLMs requires dense but often off-policy masked states, while reinforcement learning (RL) relies on sparse rewards or value modeling. This paper proposes \textbf{trace-based on-policy distillation (TOPD)}, a teacher-supervised framework that transfers reasoning ability to a target dLLM without reward estimation. The key idea is to supervise a dLLM on its own denoising trajectory, focusing on the trace-aligned token decisions that form the final response. Specifically, TOPD samples on-policy diffusion trajectories from the target dLLM, obtains teacher token distributions from a teacher model on the corresponding partially denoised states, and updates the target dLLM with a token-level Reverse Kullback-Leibler (Reverse-KL) objective. This design preserves dense teacher supervision while aligning training with the model's own denoising states. On mathematical reasoning benchmarks, TOPD enables SDAR-4B-Chat to match the MATH500 accuracy of its RL-trained counterpart TraDo-4B-Instruct, with gains of +5.7 under static evaluation and +4.5 under dynamic evaluation. Compared with the RL-trained counterpart, TOPD achieves this with 4$\times$ fewer rollout rounds, corresponding to an estimated 96.0$\times$ to-accuracy model-compute speedup.
Haolin Ren, Ziyang Huang, Chenhao Yuan et al.· 0 citations
Continual Learning (CL) for Large Language Models (LLMs) faces a fundamental Stability-Plasticity Dilemma : balancing the plasticity to acquire new capabilities with the stability to preserve prior knowledge. While Parameter-Efficient Fine-Tuning methods, such as LoRA, enable efficient adaptation, we identify a critical flaw in current approaches termed Rank-Blindness : the enforcement of a single rank constraint across diverse tasks, which entangles task-shared and task-specific knowledge, leading to catastrophic forgetting of earlier tasks and underfitting on complex new ones. To address this, we propose S PA RTA, a novel rehearsal-free framework guided by a rank-spectrum perspective that explicitly dis-entangles knowledge into two orthogonal sub-spaces. Specifically, S PA RTA employs a low-rank branch to capture task-shared representations and a high-rank branch to model task-specific features. To integrate these complementary representations, we introduce a context-aware dynamic router that adaptively fuses the two branches based on input semantics, while an explicit orthogonality constraint minimizes interference between shared and specific parameter subspaces. This design effectively isolates task-specific updates from shared knowledge, preventing the overwriting of prior capabilities while preserving strong adaptation capacity. Extensive experiments demonstrate that S PA RTA achieves a superior stability-plasticity balance compared to single-rank baselines. Notably, the proposed spectral disentanglement strategy substantially reduces inter-task interference and yields strong zero-shot generalization on unseen tasks. Our code will be available at https://github. com/Xnhyacinth/SpaRTA .
Huanxuan Liao, Shizhu He, Yupu Hao et al.· Annual Meeting of the Associ...· 1 citation· ⚡1
