…Empirically, the two-loop variant delivers broad gains over the non-looped baseline across code generation, code reasoning, agentic software engineering, and tool-use benchmarks, improving SWE-bench Verified from 43.0…
…We evaluated 24 LLMs for instruction and reasoning on Multi-LCB, uncovering evidence of Python overfitting , language-specific contamination , and substantial disparities in multilingual performance . Our results establish Multi-LCB as a…
…Seojeong Park , Jiho Choi , , , , Abstract Researchers identify a perceptual judgment bias in multimodal large language models where visual evidence is overlooked for textual plausibility, and propose a training framework using a perturbed…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Reinforcement learning (RL) has become a representative post-training paradigm for LLMs, enabling strong reasoning and agentic capabilities. However, rollout generation remains a dominant…
…A Live Benchmark for Mathematician-Level Reasoning with Proof Sketches (2026) AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model (2026) Please give a thumbs up to this comment…
…Consequently, models can achieve high scores through fact recall rather than genuine retrieval, obscuring true browsing competence via reasoning shortcuts. In this paper, we introduce Evo BrowseComp , an evolving benchmark of 400…
…early layers form coarse guesses, intermediate layers refine reasoning-relevant semantics, and final layers can perturb these refined predictions toward generic or alignment-preferred tokens. We introduce Confident Decoding , a training-free…
…Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation (2026) ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation (2026) MoGeFlow: Flowing Through Motion Codebook Geometry for Text-to-Motion Generation…
…Approximating Global Activation for Long-Context Understanding Published on May 7 Submitted by Yuqing Li on May 8 Tencent Authors: , Jiangnan Li , Mo Yu , , , Abstract Researchers propose a compressed representation method for…
…Evidence-Grounded Reasoning Improves Decision Alignment (2026) Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models (2026) DRInQ: Evaluating Conversational Implicature with Controlled Context Variation (2026) Investigating Counterfactual Unfairness in LLMs…