inference-compute

Tag

Cards List
#inference-compute

Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds

arXiv cs.AI · 3d ago Cached

This paper introduces critique refinement and DISH to enhance the realism of alignment evaluations by mitigating evaluation awareness, demonstrating that combining both techniques yields significant improvements over using either alone.

0 favorites 0 likes
#inference-compute

@DSPyOSS: a crisper operationalization of continual learning that matches problems that are inaccurately treated as "RAG" or "RL"…

X AI KOLs Following · 2026-06-17 Cached

Introduces 'Machine Studying' as a new formulation of continual learning where AI systems autonomously develop expertise from a corpus, and presents StudyBench for evaluation.

0 favorites 0 likes
#inference-compute

@lateinteraction: putting the link here for those that want to jump right into the long form: https://jacobxli.com/blog/2026/machine-stud…

X AI KOLs Following · 2026-06-17 Cached

Introduces 'Machine Studying' as a problem where AI agents must autonomously develop expertise from a corpus, beyond RAG or long-context, and presents the StudyBench benchmark for evaluation.

0 favorites 0 likes
#inference-compute

How Inference Compute Shapes Frontier LLM Evaluation

arXiv cs.AI · 2026-06-17 Cached

This paper systematically studies how inference-time compute (token budgets, context compaction, repeated submissions) affects frontier LLM performance on challenging benchmarks, demonstrating that scores are protocol-dependent and advocating for evaluations that report capability as a function of inference compute.

0 favorites 0 likes
#inference-compute

TMAS: Scaling Test-Time Compute via Multi-Agent Synergy

Hugging Face Daily Papers · 2026-05-11 Cached

TMAS introduces a multi-agent framework that enhances large language model reasoning by scaling test-time compute through structured collaboration and hierarchical memory systems. The approach uses specialized agents, cross-trajectory information flow, and hybrid reward reinforcement learning to improve iterative scaling and stability on challenging reasoning benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback