Adversarial Speculative Reasoning Improves Long Horizon Agents
Training draft models to reject at critical decision points improves agent accuracy by training 0.06% to 0.28% of parameters on agentic coding benchmarks.
Stories per day · 30 days
2 RSS
Relatedbenchmarks2adversarial-preference1draft-models1harness1long-horizon-agents1multimodal1spatial-reasoning1speculative-decoding1tool-use1video-world-model1visual-reasoning1vlm1
5 stories, newest first · one card per story
Stories tagged #agentic-reasoning
OpenVLHarness adds tool use and memory for visual agent reasoning
On 22 benchmarks it lifts matched no-tool baselines by 9.7 to 12.6 points across eight backbones.
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
CoWorld Reasoner lets a VLM call a video world model as a tool, lifting accuracy on all seven reasoning benchmarks.
HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis
HARMONY reconstructs indoor 3D scenes from one image using hierarchical agentic reasoning and geometry refinement.
Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism
New DiG-bench benchmark of 70 hidden-rule games shows only Opus 5 and Fable 5 solving the hardest tiers, probing AI discovery and creativity.
3