Model, Harness
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Self-Harness: Harnesses That Improve Themselves
arXiv:2606.09498v1 Announce Type: new Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different models exhibit distinct behaviors, effective harness design is inherently model-specific. Yet agent harnesses are still largely engineered by human experts, a paradigm that scales poorly as modern LLMs become increasingly diverse and rapidly evolving.
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
Announce Type: new Abstract: LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution adapts such agents by updating these harnesses from execution evidence. Yet it remains unclear whether a model's base capability in task-solving predicts its capabilities in harness self-evolution: which models produce useful harness updates, and...
Harnessing Structural Context for Entity Alignment Foundation Models
Announce Type: new Abstract: Entity alignment (EA) aims to identify equivalent entities across heterogeneous knowledge graphs (KGs) and is a key component of knowledge fusion and cross-KG reasoning. The recent EA foundation model demonstrates that alignment knowledge, once pretrained, can be directly applied to diverse previously unseen KG pairs. However, it still underuses structural context in two places: cross-KG interaction is weak during encoding, and final candidate ranking still...
AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
arXiv:2606.08952v1 Announce Type: new Abstract: Multimodal Foundation Models (MFMs) have made substantial progress, yet remain fragile in spatial reasoning over the physical world. A key bottleneck lies in their inability to transform local egocentric observations into a global allocentric spatial representation. To address this, we propose AlloSpatial, an agentic framework for allocentric spatial cognition in foundation models.
Neither Layer Alone: Epistemic Integrity Requires Hierarchical Joint Design for Long-Running AI Agents
Announce Type: new Abstract: Long-running AI agents fail not only when inference fails or tools are underspecified, but when independently evolving model and harness layers change the semantics of belief, capability, and goal commitments across their boundary - a failure class this paper terms Interface Volatility. This paper argues that Agent Epistemic Integrity (AEI) must be treated as a first-class architectural constraint, achievable only through joint model-harness design organized...
Parthenon Law: A Self-Evolving Legal-Agent Framework
Announce Type: new Abstract: As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products -- yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism...
Rethinking Search as Code Generation
Rethinking Search as Code Generation Evolving search from monolithic services to programmable primitives for the era of agent harnesses. Search is a core primitive for AI systems. Frontier models grow more capable by the month, but they still need access to fresh, accurate, and well-curated knowledge from the wider world.
Uncertainty-Aware (Un)Supervised Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
Announce Type: new Abstract: Sensor-based Human Activity Recognition (HAR) models often degrade on unseen users due to domain shifts caused by individual movement patterns and sensor placement. Practical wearable HAR systems therefore require personalization methods that are lightweight, applicable whether calibration data is labeled, unlabeled, or unavailable, and robust under limited calibration. We present a gradient-free framework that repurposes pretrained HAR classifiers as...
'Resistance is futile,' says Qualcomm CEO. AI agents will be become invisible, inescapable, follow you across devices
In his Computex keynote speech this week Qualcomm CEO Cristiano Amon offered a glimpse of an AI-augmented future straight out of an episode of Black Mirror. According to Amon, agents — automated systems which harness AI models to automate complex tasks without the need for human supervision — will fundamentally change humanity’s relationship with technology. “The phone, today, is at the center of your digital life and therefore everything is around the phone,” he said.
Design Space Exploration of DMA based Finer-Grain Compute Communication Overlap
arXiv:2512.10236v2 Announce Type: replace Abstract: Modern ML workloads demand distributing training and inference across multiple GPUs. However, these parallelization techniques often suffer from exposed critical-path communication, leaving a potential 1.7x speedup on the table through compute-communication overlap. Prior overlapping methods harness the fact that ML model state and inputs are already sharded into the number of GPUs, and overlap the compute and communication at shard...