arXiv AI
Jul 21
SCA: Segment-Wise CoT Compression with Answer Alignment
arXiv:2603. 07598v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning improves problem solving, but long think traces increase inference cost.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jul 21
Structure-Induced Information for Rerooting Levin Tree Search
arXiv:2605. 30664v2 Announce Type: replace Abstract: Subgoal-based policy tree search, which uses a policy to guide search, is effective for complex single-agent deterministic problems but often relies on explicit subgoal generation that can incur substantial overhead and hinders scalability.
arXiv Machine Learning
Jul 21
Adaptive Mamba Neural Operators
arXiv:2607. 18043v1 Announce Type: new Abstract: Accurately solving partial differential equations (PDEs) on arbitrary geometries and a variety of meshes is an important task in science and engineering applications.
arXiv Machine Learning
Jul 21
ClouDens: Operational Context-Aware Anomaly Detection for Large-scale Cloud System Monitoring
arXiv:2607. 18127v1 Announce Type: cross Abstract: With the rapid growth of cloud computing infrastructures in scale and complexity, network monitoring for Large-scale Cloud Systems (LCSs) has become increasingly challenging, requiring automated and reliable anomaly detection to maintain service availability.
arXiv Machine Learning
Jul 21
Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization
arXiv:2601. 13359v3 Announce Type: replace-cross Abstract: Prefill attacks are an effective and low-cost jailbreaking method, as they directly insert an acceptance sequence (e.
arXiv Machine Learning
Jul 21
LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
arXiv:2607. 17653v1 Announce Type: cross Abstract: Source-free universal domain adaptation (SF-UniDA) adapts a pre-trained source model to an unlabeled target domain under both covariate and label shifts, without access to source data.
arXiv AI
Jul 21
LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning
arXiv:2607. 17243v1 Announce Type: new Abstract: Multi-view spatial reasoning requires vision-language models to compare visual evidence across images, align object correspondences, and infer spatial relations over long visual contexts, a setting where chain-of-thought reasoning tends to grow verbose without becoming more accurate.
arXiv AI
Jul 21
SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling
arXiv:2607. 16252v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method for large language models.
arXiv AI
Jul 21
LaT: LLM-as-Trainer for Multi-Task Vehicle Routing Solvers
arXiv:2607. 17708v1 Announce Type: new Abstract: Multi-task neural solvers aim to handle multiple Vehicle Routing Problem (VRP) variants within a unified model, avoiding separate training for each constraint combination.
arXiv AI
Jul 21
TAPAS: Throughput-adaptive Perception for Autonomous Systems
arXiv:2607. 17317v1 Announce Type: cross Abstract: Autonomous systems rely on a perception module to navigate through dynamic environments.
arXiv Machine Learning
Jul 21
Discrete Ricci Curvature on Protein Contact Graphs for Lightweight Fold Classification
arXiv:2607. 16553v1 Announce Type: new Abstract: Protein fold classification can be approached via sequence-based representations or structural descriptors, but direct comparisons between lightweight handcrafted descriptors and pretrained protein language model embeddings remain limited.
arXiv Machine Learning
Jul 21
ProtoTSNet: Interpretable Multivariate Time Series Classification With Prototypical Parts
arXiv:2511. 02152v2 Announce Type: replace Abstract: Time series data is one of the most popular data modalities in critical domains such as industry and medicine.
arXiv Machine Learning
Jul 21
Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding
arXiv:2607. 16721v1 Announce Type: new Abstract: The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of "expert" subnetworks, of which only a few act on any token.
arXiv AI
Jul 21
Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones
arXiv:2607. 17419v1 Announce Type: cross Abstract: Linear attention promises constant-time recurrent inference but degrades sharply on associative recall.
arXiv AI
Jul 21
Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment
arXiv:2607. 17188v1 Announce Type: new Abstract: Test-time scaling empowers Large Reasoning Models (LRMs) to tackle complex tasks via extensive Chain-of-Thought (CoT).
arXiv AI
Jul 21
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
arXiv:2509. 00930v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general reasoning, yet the community lacks controllable, scalable, and verifiable tools to analyze and improve these abilities.
arXiv AI
Jul 21
A Systematic Evaluation of Trajectory Data Curation for LoRA Fine-Tuning of Code Agents
arXiv:2607. 17205v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) of open-weight LLMs on expert agent trajectories has emerged as a prominent approach to building capable code agents without reliance on proprietary models.
arXiv AI
Jul 21
Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
arXiv:2607. 18144v1 Announce Type: cross Abstract: Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial constraints, to generate candidate binding molecules.
arXiv AI
Jul 21
Probing the Difficulty Perception Mechanism of Large Language Models
arXiv:2510. 05969v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient resource allocation.
arXiv AI
Jul 21
Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration
arXiv:2607. 16352v1 Announce Type: cross Abstract: A fundamental intent asymmetry plagues modern 3D asset creation: while state-of-the-art 3D toolchains demand precise, executable parameters, ordinary users typically provide vague, underspecified instructions.