10 papers
JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs
Kunlun Zhu, Tao Feng, Xu Han +5
Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large LLM at every step, which ma…
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Shuhan Xue, Jianyuan Zhong, Ziyuan Nan +10
We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. Scienc…
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
Zhaochen Yu, Yingcheng Wu, Zhenfei Yin +5
Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive…
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Yinghui He, Ling Yang, Jiarui Liu +6
Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain, such as first doing a math derivation, then using the result t…
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
Shuhan Xue, Zixin Ding, Yichen Shen +6
Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI agents offer a concrete setting for studying this capability beca…
CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration
Jiayao Gu, Kexin Chu, Peidong Liu +5
LLM-based agents excel at writing articles, coding and information retrieval. However, they fail to form strong collaborations within the scientific community due to the bidirectio…
AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation
Yunxiao Shi, Wujiang Xu, Tingwei Chen +7
LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a principled way to choose among an exploding space of deployable configuration…
GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
Jiacheng Guo, Ling Yang, Peter Chen +6
Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenE…
AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
Jiahao Qiu, Xinzhe Juan, Yimin Wang +11
While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the dis…
Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
Jiahao Qiu, Xuan Qi, Tongcheng Zhang +15
Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually…