Crafter
PulseAugur coverage of Crafter — every cluster mentioning Crafter across labs, papers, and developer communities, ranked by signal.
- 2026-05-28 research_milestone Researchers introduced Crafter, a multi-agent system for generating editable scientific figures, along with CraftEditor and the CraftBench benchmark. source
1 day(s) with sentiment data
-
New LAMB framework enhances long-horizon language agents with latent multi-hypothesis beliefs
Researchers have introduced LAMB, a novel recurrent framework designed for latent multi-hypothesis beliefs in long-horizon language agents. This system utilizes a Common--Delta factorization to maintain a shared state f…
-
New RL methods enhance LLM reasoning with fine-grained credit assignment · 9 sources tracked
Researchers are developing new methods for credit assignment in reinforcement learning (RL) for large language models (LLMs) to improve their reasoning and decision-making capabilities. Several papers propose novel fram…
-
New CIVA attack method targets visual world-model agents
Researchers have developed a new method called Critic-Induced Value-Subspace Attacks (CIVA) to target visual world-model agents. These agents, like DreamerV3, operate using a recurrent latent state, making them resilien…
-
New CRAFTER system improves frozen forecasters with LLM-generated corrective features
Researchers have developed a new method called CRAFTER (Corrective Residual Agent with Feature-based Temporal Exploration and Reasoning) to improve the performance of frozen, pretrained forecasters. This system mines in…
-
New framework enables agents to evolve executable skills via symbolic programs
Researchers have introduced the Programmatic Skill Network (PSN), a novel framework designed for continual skill acquisition in embodied environments. PSN enables agents to build, refine, and reuse an evolving library o…
-
New S3MEM framework enhances AI agent memory for long-horizon question answering
Researchers have introduced S3MEM, a novel memory framework designed to improve long-horizon interactive question answering for AI agents. Traditional methods struggle with large trajectory histories, often retrieving i…
-
New system automates scientific figure generation with editable output
Researchers have developed Crafter, a multi-agent system designed to automate the creation of scientific figures from various inputs. This system addresses the limitations of existing tools that are often restricted to …
-
New research explores advanced reinforcement learning techniques for multi-agent systems and LLMs
Multiple research papers published on arXiv explore advancements in reinforcement learning (RL) and multi-agent systems. One paper introduces an axiomatic framework for RL in open multi-agent systems, leveraging Shapley…