…Unlike prior navigation benchmarks centered on long-range exploration across rooms, SleepWalk targets localized, interaction-centric embodied reasoning : given rendered visual observations and a natural-language instruction, a model must predict a…
…Wangcheng Tao , , Abstract Self-Evolving Prompt Optimization (SePO) enhances agent performance by jointly optimizing both task and prompt agent system prompts through evolutionary search, demonstrating superior accuracy across diverse benchmarks. Generated by…
…AI-generated summary Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challenging target for measuring LLM reasoning…
…improve predictive performance due to computational limitations and mismatched optimization goals. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Under standard graphical assumptions, the Markov boundary of a target variable is the…
…Zhuoming Liu , , , , , Abstract DRIFT is a framework that adapts pretrained vision-language models for continuous decoding tasks by combining coarse prediction with iterative refinement through flow matching, improving performance across perception and…
…Sanitization confines the on-device LLM to proposing which spans to mask, while a deterministic registry performs all substitution and reversal, keeping actions directly executable on device. On three agentic benchmarks under…
…Many high-performing systems rely on proprietary codebases, models, or services, while most open-source frameworks focus on orchestration and evaluation rather than scalable agent training. We present Orchard, an open-source…
…In non-stationary environments, the diverse reasoning distributions of source models often evolve unpredictably, transmitting systematic biases and drift to the target model. To address this, we formulate multi-source reasoning alignment…
…With long-context models, many-shot ICL can use dozens to hundreds of examples and achieve performance comparable to fine-tuning, yet current understanding of its scaling behavior is largely derived from…
…Zewen Liu , , , , , , , , , Abstract Adaptive Auto-Harness framework addresses dynamic task streams by decomposing performance gaps into evolution and adaptation losses, utilizing a stateful multi-agent evolver and harness tree with solve-time…