2 citations · 7 across the 26 of their papers we have counts for
29 papers
Same Space or Not: Benchmarking Spatial Intelligence Through Cross-View Contradictions
Huizi Cao, Guanyu Xu, Zhixuan Liang +5
Spatial intelligence, the capacity to represent and reason about physical space, underlies embodied perception and real-world visual understanding. Existing benchmarks probe it thr…
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
Python Song, Zhixuan Liang, Kelsey Fu +3
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require p…
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…
EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents
Weixian Xu, Shilong Liu, Mengdi Wang
In this paper, we propose EEVEE, the first multi-dataset test-time prompt learning framework for LLM agents, enabling test-time prompt learning under real-world task streams. Exist…
Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
Jui-Hui Chung, Ziyang Cai, Zihao Li +14
We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint is a dependency graph of defin…
AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?
Zhangchen Xu, Junda Chen, Yue Huang +16
Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifac…
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Minghao Guo, Qingyue Jiao, Zeru Shi +14
Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many…
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…
OpenClaw-RL: Train Any Agent Simply by Talking
Yinjie Wang, Xuyang Chen, Xiaolong Jin +2
Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system…
RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
Yinjie Wang, Tianbao Xie, Ke Shen +2
We propose RLAnything, a reinforcement learning framework that dynamically forges environment, policy, and reward models through closed-loop optimization, amplifying learning signa…
AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
Jiaru Zou, Ling Yang, Yunzhe Qi +5
Agentic reinforcement learning has advanced large language models (LLMs) to reason through long chain-of-thought trajectories while interleaving external tool use. Existing approac…
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Ye Tian, Ling Yang, Jiongfan Yang +10
While thinking-aware generation aims to improve performance on complex tasks, we identify a critical failure mode where existing sequential, autoregressive approaches can paradoxic…
Latent Collaboration in Multi-Agent Systems
Jiaru Zou, Ruizhong Qiu, Gaotang Li +10
Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on…
Demystifying Reinforcement Learning in Agentic Reasoning
Zhaochen Yu, Ling Yang, Jiaru Zou +2
Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practice…
Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Yinjie Wang, Ling Yang, Bowen Li +3
We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, an…
Preacher: Paper-to-Video Agentic System
Jingwei Liu, Ling Yang, Hao Luo +3
The paper-to-video task converts a research paper into a structured video abstract, distilling key concepts, methods, and conclusions into an accessible, well-organized format. Whi…
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…
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
Jiaru Zou, Ling Yang, Jingwen Gu +4
Process Reward Models (PRMs) have recently emerged as a powerful framework for supervising intermediate reasoning steps in large language models (LLMs). Previous PRMs are primarily…
Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
Yinjie Wang, Ling Yang, Ye Tian +2
We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction out…
MMaDA: Multimodal Large Diffusion Language Models
Ling Yang, Ye Tian, Bowen Li +4
We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal un…
EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
Jiahao Qiu, Yinghui He, Xinzhe Juan +7
The rise of LLM-driven AI characters raises safety concerns, particularly for vulnerable human users with psychological disorders. To address these risks, we propose EmoAgent, a mu…
Temporal Consistency for LLM Reasoning Process Error Identification
Jiacheng Guo, Yue Wu, Jiahao Qiu +4
Verification is crucial for effective mathematical reasoning. We present a new temporal consistency method where verifiers iteratively refine their judgments based on the previous…