… View arXiv page View PDF GitHub 7 Add to collection Community Closed-loop auto research turns agent-written code, real experiments, and evaluator feedback into an autonomous feedback loop that develops non-trivial training recipes. the most interesting nugget here is how lineage feedback lets evalu… …
… View arXiv page View PDF GitHub 3 Add to collection Community Multi-agent systems MAS have emerged as a promising paradigm for solving complex tasks. …
… Across PrivacyLens+, ConFaide+, and AgentHarm, LiSA consistently outperforms strong memory-based baselines under sparse feedback , remains robust under noisy user feedback even at 20% label-flip rates, and pushes the latency--performance frontier beyond backbone model scaling. …
… View arXiv page View PDF GitHub 245 Add to collection Community Ctx2Skill is a self-evolving framework that autonomously discovers, refines, and selects context-specific skills from complex contexts, requiring no human annotation and no external feedback. …
… Instead of free-form reasoning trajectories, \pyrag represents the reasoning process as an executable Python program over retrieval and QA tools, exposing intermediate states as variables, producing deterministic feedback through execution, and yielding an inspectable trace of the entire reasoning … …
… SimCoder self-evolves by using verifier feedback e.g., compilation errors, physics checks, VLM critiques to revise environments and autonomously add reusable tools and skills to its library. …
… However, this flexibility introduces a new optimization challenge: the model must search a combinatorial output space while receiving utility feedback only after the full ranked list is generated. …
… Recent structured approaches have further advanced this paradigm by organizing inference across multiple trajectories, refinement rounds, and verification-based feedback. …
… The key to AutoTTS lies in environment construction: the discovery environment must make the control space tractable and provide cheap, frequent feedback for TTS search. …
… It then assigns credit with Stage-Structured GRPO , which uses stagewise rubric judgments to provide denser semantic feedback for long-horizon optimization . …