Human Feedback and Eval Paper Explorer

Match reason: Keyword overlap 2/2 across title and protocol fields.

• To address the challenge, in this work, we propose StitchCUDA, a multi-agent framework for end-to-end GPU program generation, with three specialized agents: a Planner to orchestrate whole system design, a Coder dedicated to implementing it…
• Experiments on KernelBench show that StitchCUDA achieves nearly 100% success rate on end-to-end GPU programming tasks, with 1.72x better speedup over the multi-agent baseline and 2.73x than the RL model baselines.

Match reason: Keyword overlap 2/2 across title and protocol fields.

• Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning.
• To fill this gap, we introduce OneManCompany (OMC), a framework that elevates multi-agent systems to the organisational level.

Match reason: Keyword overlap 2/2 across title and protocol fields.

• While a multi-agent approach based on large language models (LLMs) represents a promising strategy to surpass the capabilities of single models, its success is critically dependent on synergistic team composition.
• Priming conversations with specific topics identified synergistic teams which outperform random baselines on downstream benchmarks and achieve comparable accuracy to that of manually-curated teams based on known model specializations.

Match reason: Keyword overlap 2/2 across title and protocol fields.

• We present a hierarchical multi-agent LLM-based planner with prompt optimization: an upper layer decomposes tasks and assigns them to lower-layer agents, which generate PDDL problems solved by a classical planner.
• When plans fail, the system applies TextGrad-inspired textual-gradient updates to optimize each agent's prompt and thereby improve planning accuracy.

Match reason: Keyword overlap 2/2 across title and protocol fields.

• We introduce Whisper: Courtside Edition, a novel multi-agent large language model (LLM) pipeline that enhances Whisper transcriptions without retraining.
• The pipeline intercepts Whisper's initial transcript, applies specialized LLM agents for domain context identification, named entity recognition, and jargon detection, and generates compact prompts that guide Whisper's decoder.

Match reason: Keyword overlap 2/2 across title and protocol fields.

• In this work, we introduce a more robust and flexible paradigm: enabling agents to use coding as a enhanced action.
• We evaluate our system on the challenging OSWorld benchmark, where CoAct-1 achieves a new state-of-the-art success rate of 60.76%, significantly outperforming prior methods.

Match reason: Matched by broad semantic/index fallback.

• Drawing inspiration from Hal Gregersen's "Questions Are the Answer" theory, we design a multi-agent debate framework comprising four specialized components: a question outline generator, text segmenter, integrity reviewer, and knowledge…
• Additionally, to handle long evaluation chains and low efficiency in existing chunking evaluation methods, which overly rely on downstream QA tasks, we introduce a novel direct evaluation metric, ChunkScore.

Match reason: Matched by broad semantic/index fallback.

• In this work, we propose ChemMAS, a multi-agent system that reframes condition prediction as an evidence-based reasoning task.
• Experiments show that ChemMAS achieves 20-35% gains over domain-specific baselines and outperforms general-purpose LLMs by 10-15% in Top-1 accuracy, while offering falsifiable, human-trustable rationales, which establishes a new paradigm…

Match reason: Matched by broad semantic/index fallback.

• Emergent Communication (EmCom) investigates how agents develop symbolic communication through interaction without predefined language.
• In this work, we propose the SimSiam Naming Game (SSNG), a feedback-free EmCom framework that replaces sampling-based updates with a symmetric, self-supervised representation alignment objective between autonomous agents.