proposer
PulseAugur coverage of proposer — every cluster mentioning proposer across labs, papers, and developer communities, ranked by signal.
-
New CHASE method improves AI agent evaluation beyond benchmark shortcuts
Researchers have developed a new method called Counterfactual Harness Search and Evolution (CHASE) to improve the reliability of AI agent evaluation. CHASE addresses the issue of "bad genius" proposers that exploit shor…
-
New frameworks enhance LLM self-evolution by mitigating overfitting and improving verification
Researchers are developing new frameworks to improve the self-evolution capabilities of large language models (LLMs). SkillBoost, a three-stage framework, aims to mitigate skill overfitting by combining structured explo…
-
CPAgents framework enhances cardiovascular disease association studies
Researchers have developed CPAgents, a novel framework for cardiovascular phenome-wide association studies (PheWAS). This system uses three coordinated agents—Analyst, Proposer, and Verifier—to automatically construct a…
-
New 'Alignment Flywheel' architecture decouples AI decision generation from safety governance
Researchers have introduced the Alignment Flywheel, a novel governance-centric hybrid multi-agent system (MAS) designed to enhance the safety of autonomous decision components. This architecture decouples decision gener…