…The performance of agent systems built on LLMs depends on both the model weights and the harness around them, which governs what information to store, retrieve, and present to the model. For…
…A Probabilistic Inconsistency Framework for Neuro-Symbolic QA (2026) How Transformers Learn to Plan via Multi-Token Prediction (2026) Quantifying Cross-Query Contradictions in Multi-Query LLM Reasoning (2026) Dual Path Attribution…
…AI-generated summary Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain…
…AI-generated summary Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The typical industry recipe involves a…
…AI-generated summary Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights , a process that inherently incurs quadratic computational complexity . In this work…
…The bottleneck is not raw capability, but judgment: knowing when to act autonomously and when to ask for help. Current benchmarks are blind to this failure mode. They supply unambiguous detailed instructions…
…Therefore, we introduce MemEye, a framework that evaluates memory capabilities from two dimensions: one measures the granularity of decisive visual evidence (from scene-level to pixel-level evidence), and the other measures…
…Improving Long-Horizon LLM Agents (2026) PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory (2026) Toward Autonomous Long-Horizon Engineering for ML Research (2026) Scaling Agentic Capabilities, Not Context: Efficient…
…first, supervised bootstrapping projects the target model into the capability union of source models; second, constraint-aware optimization synthesizes a consistent consensus manifold by explicitly suppressing drifting trajectories via a multi-negative…
…View arXiv page View PDF Add to collection Community Studied consensus based black box optimization from a learning perspective and proposed LAC MAS, an LLM assisted multi-agent framework that jointly learns…