Unverified50% confidenceFactExact time
Agima was validated in four environments—Maze2D, Sokoban, Pacman and PushT—and can generalize to harder settings unseen in training.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLoopWAM's above results were obtained without additional embodied pretraining, and its overall performance on the three benchmarks is the best among the compared methods.62% similarUnverifiedARC-AGI-2, as an upgraded benchmark, raises the difficulty threshold and deliberately circumvents the shortcut of large language models memorizing answers through large-scale pretraining data.62% similarUnverifiedOpenAI的GPT-4o mini、Anthropic的Claude 3.5 Haiku等策略遵循'一次预训练、多次后训练'的成本摊薄逻辑61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073375API
curl https://kongchang.com/api/v1/knowledge/claims/1073375MCP
get_claim(id=1073375)