18 papers
MELD: Recursive Self-Improvement via Hierarchical Coordination for Multi-Agent Scientific Discovery
Sizhe Tang, Zuyuan Zhang, Zeyu Fang +1
Multi-agent scientific discovery with large language models raises a coupled learning problem: research assignments determine both which experiments are pursued and the experiences…
PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking
Qiufeng Li, Chengxuan Wang, Rongqian Chen +6
Automated macro placement remains a fundamental challenge in VLSI physical design. Despite decades of research, existing approaches predominantly optimize hand-crafted proxy object…
Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry
Zuyuan Zhang, Zeyu Fang, Mahdi Imani +2
Learning-based control is increasingly central to automating network operations. A learned policy, however, must satisfy cross-layer constraints on interference, power-rate couplin…
Augmented Backpressure for Decentralized Management of Agentic Networks
Zuyuan Zhang, Sizhe Tang, Tian Lan
Agentic foundation-model service networks handle requests spanning retrieval, planning, generation, verification, and tool use. Unlike traditional communication networks, control p…
TIPS: Topological Ill-Posedness Probing and Steering in Large Language Models
Guangyu Jiang, Sizhe Tang, Mahdi Imani +2
Ill-posed questions, including those involving ambiguity, under-specification, or conflicting statements, may admit no valid answer or multiple plausible answers, posing a signific…
FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts
Sizhe Tang, Guangyu Jiang, Yu Li +3
Large Language Models (LLMs) perform strongly on well-specified reasoning tasks with a feasible answer. However, problems encountered in the open world can become ill-posed due to…
PDAGENT-BENCH: Characterizing, Grounding, and Architecting LLM/VLM Agents for VLSI Physical Design
Qiufeng Li, Rongqian Chen, Quan Cheng +6
Large Language Models and vision-language models have shown remarkable success in the front-end design of Very Large-Scale Integrated Circuits, yet their capabilities for VLSI phys…
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
Rongqian Chen, Yu Li, Zeyu Fang +3
Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to…
OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
Yu Li, Rui Miao, Tian Lan +1
Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a single trajectory-level advanta…
Metric-Gradient Projection for Stable Multi-Agent Policy Learning
Zuyuan Zhang, Sizhe Tang, Mahdi Imani +1
General-sum multi-agent learning is often governed by a stacked update field in which each agent's policy update changes the optimization landscape faced by the others. This coupli…
NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
Sizhe Tang, Zuyuan Zhang, Mahdi Imani +1
Monte Carlo Tree Search (MCTS) scales poorly in cooperative multi-agent domains because expansion must consider an exponentially large set of joint actions, severely limiting explo…
Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
Yu Li, Sizhe Tang, Tian Lan
Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group Relative Policy Optimizatio…
Reasoning Knowledge-Gap in Drone Planning via LLM-based Active Elicitation
Zeyu Fang, Beomyeol Yu, Cheng Liu +5
Human-AI joint planning in Unmanned Aerial Vehicles (UAVs) typically relies on control handover when facing environmental uncertainties, which is often inefficient and cognitively…
Knowing When to Ask: Resolving Uncertainty in Human-Robot Joint Planning via Explicit Dialogue and Implicit Intent Cues
Zeyu Fang, Yuxin Lin, Cheng Liu +6
Effective human-robot collaboration in open-world environments requires joint planning under uncertainty about the task, the environment, and the human teammate. Communication is t…
Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents
Sizhe Tang, Rongqian Chen, Tian Lan
While scaling test-time compute through trajectory-level sampling has significantly improved Graphical User Interface (GUI) agents, the lack of regressive ability prevents the reus…
ACDZero: MCTS Agent for Mastering Automated Cyber Defense
Yu Li, Sizhe Tang, Rongqian Chen +5
Automated cyber defense (ACD) seeks to protect computer networks with minimal or no human intervention, reacting to intrusions by taking corrective actions such as isolating hosts,…
MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning
Sizhe Tang, Jiayu Chen, Tian Lan
Monte Carlo Tree Search (MCTS), which leverages Upper Confidence Bound for Trees (UCTs) to balance exploration and exploitation through randomized sampling, is instrumental to solv…
AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AI
Qiufeng Li, Shu Hong, Tian Lan +1
Recent advances in generative AI (GenAI) have shown transformative potential for modern hardware design. However, existing GenAI-driven approaches fall short of enabling large-scal…