Papers

Filtered to evaluation benchmarks · clear filter

Browse by term

continual learning 91reinforcement learning 43vision-language models 18benchmarking 12benchmarks 11robotics 11large language models 10language models 9world models 9video generation 6generative models 5multimodal models 5natural language processing 5recursive self-improvement 5video world models 5agents 4dialogue systems 4diffusion models 4foundation models 4multimodal large language models 4on-policy distillation 4reasoning 4self-distillation 4self-supervised learning 4conversational AI 3evaluation benchmarks 3human-computer interaction 3LLMs 3multi-agent systems 3policy optimization 3

Matching papers

Memory Tax: Dissecting the Net Value of Agent Memory

150 upvotes · 25 OCT 2026 · Xuan He, Sining Zhoubian, Ruozhen Yang et al.

This paper investigates the net value of agent memory in long-horizon agents, finding that dedicated memory systems often underperform without memory in many cases. Practitioners may care because understanding the net value of memory can help design more reliable and effective memory systems.

continual learningagent architecturememory-augmented modelsevaluation benchmarksreinforcement learning

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

115 upvotes · 21 SEP 2026 · Yiran Wang, Xingyilang Yin, Junfu Pu et al.

This paper introduces a new dataset and evaluation suite for video games, allowing AI models to be tested across different horizons and tasks, and providing a standardized way to evaluate their capabilities. Practitioners can use this work to improve their models' performance in complex gameplay scenarios.

gameplayAI modelsmultimodal learningvideo gamesevaluation benchmarks

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

108 upvotes · 17 AUG 2026 · Weiliang Chen, Haowen Sun, Jun Gao et al.

This paper develops a new method for evaluating world models, called HarnessEval-W, which provides more detailed and justifiable results than existing benchmarks. Practitioners might care about HarnessEval-W because it can help them build more trustworthy world models that better align with human preferences.

world modelsevaluation benchmarkshierarchical reasoningagentified evaluationdiagnostic tools