2 citations · 3 across the 20 of their papers we have counts for
26 papers
ReTTT: Reflection-Driven Test-Time Training via Experience-Based Parametric Memory
Kangcong Li, Hangfan Zhang, Shuyue Hu +2
LLM agents accumulate valuable task-specific information through their actions, observations, and environmental feedback during multi-turn task execution. When effectively used, th…
Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching
Yang Chen, Yang chen, Yitan Zhang +2
Inverse Reinforcement Learning (IRL) aims to recover a reward function that explains expert demonstrations. Existing IRL methods typically rely on a bi-level optimization procedure…
RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents
Hao Li, Hangfan Zhang, Zhiyao Cui +5
Practical deployment of large language model (LLM) agents requires strong task performance at affordable inference cost. For long-horizon agentic tasks, this performance-cost trade…
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
Haoyang Yan, Min-le Su, Hangfan Zhang +6
This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems withou…
JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills
Xiaoyu Wen, Jiajia Li, Zhida He +11
Automated red-teaming has produced a growing collection of attack strategies, yet they typically remain scattered across prompts and workflows, making them difficult to systematica…
AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions
Zhiyao Cui, Qianyi Wang, Haoyang Yan +26
Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a s…
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
Zelin Tan, Yiqun Zhang, Hao Li +11
Agent skills have become an important mechanism for equipping language-model agents with reusable procedural knowledge. However, providing skills alone does not guarantee that curr…
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Lei Bai, Zongsheng Cao, Yang Chen +50
We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling…
Self-Harness: Harnesses That Improve Themselves
Hangfan Zhang, Shao Zhang, Kangcong Li +5
The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different models exhibit d…
MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings
Yiqun Zhang, Hao Li, Zihan Wang +6
Multi-turn, long-horizon tasks are increasingly common for large language models (LLMs), but solving them typically requires many sequential model invocations, accumulating substan…
Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
Hao Li, Chunjiang Mu, Jianhao Chen +5
The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propos…
PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization
Zelin Tan, Zhouliang Yu, Bohan Lin +9
We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage no…
Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale
Shengji Tang, Weihao Lin, Peng Ye +9
Large Language Models (LLMs) have rapidly advanced, with Gemini-3-Pro setting a new performance milestone. In this work, we explore collective intelligence as an alternative to mon…
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
Shiyang Feng, Runmin Ma, Xiangchao Yan +53
We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architec…
MARTI-MARS: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation
Shijie Wang, Pengfei Li, Yikun Fu +21
While the complex reasoning capability of Large Language Models (LLMs) has attracted significant attention, single-agent systems often encounter inherent performance ceilings in co…
LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing
Hao Li, Yiqun Zhang, Zhaoyan Guo +9
Large language model (LLM) routing assigns each query to the most suitable model from an ensemble. We introduce LLMRouterBench, a large-scale benchmark and unified framework for LL…
Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence
Shuyue Hu, Haoyang Yan, Yiqun Zhang +3
Foundation models (FMs) are increasingly assuming the role of the ''brain'' of AI agents. While recent efforts have begun to equip FMs with native single-agent abilities -- such as…
ICL-Router: In-Context Learned Model Representations for LLM Routing
Chenxu Wang, Hao Li, Yiqun Zhang +6
Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a…
The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
Hangfan Zhang, Siyuan Xu, Zhimeng Guo +8
Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial effo…
Learning Compact Representations of LLM Abilities via Item Response Theory
Jianhao Chen, Chenxu Wang, Gengrui Zhang +5
Recent years have witnessed a surge in the number of large language models (LLMs), yet efficiently managing and utilizing these vast resources remains a significant challenge. In t…
PhysicsMinions: Winning Gold Medals in the Latest Physics Olympiads with a Coevolutionary Multimodal Multi-Agent System
Fangchen Yu, Junchi Yao, Ziyi Wang +10
Physics is central to understanding and shaping the real world, and the ability to solve physics problems is a key indicator of real-world physical intelligence. Physics Olympiads,…
Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
Yiqun Zhang, Hao Li, Jianhao Chen +4
Balancing performance and efficiency is a central challenge in large language model (LLM) advancement. GPT-5 addresses this with test-time routing, dynamically assigning queries to…
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
Shengji Tang, Jianjian Cao, Weihao Lin +7
Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks, leading to suboptimal performance. To address this, we propose…
Scaling Physical Reasoning with the PHYSICS Dataset
Shenghe Zheng, Qianjia Cheng, Junchi Yao +9
Large Language Models (LLMs) have achieved remarkable progress on advanced reasoning tasks such as mathematics and coding competitions. Meanwhile, physics, despite being both reaso…