61 citations · 118 across the 23 of their papers we have counts for
9 papers · 1 filter
PLE: Physical-Engineering's Last Exam
Rujun Han, Yufan Zhuang, Arijit Ray +10
Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no existing be…
Harness^2: Recursive Agent Harnessing for an Open World
Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu +6
LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatic…
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Peng Xia, Rujun Han, Zifeng Wang +11
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Rece…
EnvHarness: Awakening Static Worlds for Agent Learning
Chengsong Huang, Zifeng Wang, Rujun Han +14
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While r…
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Ye Liu, Srijan Bansal, Bo Pang +6
Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the policy fr…
The Illusion of Multi-Agent Advantage
Prathyusha Jwalapuram, Hehai Lin, Chuyuan Li +7
Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed d…
Harnessing LLM Agents with Skill Programs
Hongjun Liu, Yifei Ming, Shafiq Joty +1
Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lesso…
SkillOrchestra: Learning to Route Agents via Skill Transfer
Jiayu Wang, Yifei Ming, Zixuan Ke +3
Compound AI systems promise capabilities beyond those of individual models, yet their success depends critically on effective orchestration. Existing routing approaches face two li…
MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
Zixuan Ke, Yifei Ming, Austin Xu +7
While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliver. Such shortcomings stem from…