arXiv:2606.04769v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as a critical standard empowering Large Language Models (LLMs) to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool descriptions faithfully reflect their underlying implementations, […]
VAMPS: Visual-Assisted Mathematical Problem Solving Benchmark
arXiv:2606.04244v1 Announce Type: new Abstract: Multimodal large language models are increasingly capable of complex reasoning, yet their performance often degrades when they must externalize a problem through a tool and then reason over the tool’s output, specifically when they rely on visual aids. This gap is especially important because real engineering and scientific workflows often […]
Uncertainty-Aware End-to-End Co-Design of Neural Network Processors: From Training and Mapping to Fabrication
arXiv:2606.04850v1 Announce Type: cross Abstract: Designing a neural network processor is an end-to-end co-design problem: network architecture and training budget determine the inference workload; hardware mapping decisions determine chip area, latency, and energy; and these characteristics govern fabrication yield and manufacturing cost. In practice, these decisions are made in separate stages, and existing co-design methodologies […]
Synthesize and Reward — Reinforcement Learning for Multi-Step Tool Use in Live Environments
arXiv:2606.03892v2 Announce Type: replace-cross Abstract: Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server’s actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns. We […]
AdaKoop: Efficient Modeling of Nonlinear Dynamics from Nonstationary Data Streams with Koopman Operator Regression
arXiv:2606.04930v1 Announce Type: cross Abstract: Real-time data analysis requires the ability to accurately and adaptively address nonlinear dynamics in a nonstationary data stream while preserving computational efficiency. However, nonlinear dynamics are so complex that capturing dynamically changing nonlinear patterns and utilizing them for downstream tasks under strict time constraints is nontrivial. To bridge the gap […]
StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis
arXiv:2606.04246v1 Announce Type: new Abstract: Automatic generation of RTL code for digital hardware designs remains challenging due to long-horizon reasoning, multi-step dependencies, and strict correctness constraints in Verilog and VHDL. We present StepPRM-RTL, a novel framework that combines stepwise trajectory modeling, process-reward modeling (PRM), and retrieval-augmented fine-tuning (RAFT) to enhance both the functional correctness and […]
Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)
arXiv:2606.05145v1 Announce Type: cross Abstract: When post-trained language models fail on reasoning problems, the common test-time-scaling response is to spend more compute on additional attempts, and the failed traces play no further role. We argue this discards a crucial signal; some failures come from unlucky sampling, where more rollouts help, while others are structural and […]
Can Generalist Agents Automate Data Curation?
arXiv:2606.04261v1 Announce Type: new Abstract: Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback. We ask whether generalist coding agents can automate this data-curation loop. We introduce *Curation-Bench*, an agent-centric benchmark that fixes the model, training […]
Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection
arXiv:2601.13735v2 Announce Type: replace Abstract: Probabilistic confidence metrics are increasingly adopted as proxies for reasoning quality in Best-of-N selection, under the assumption that higher confidence reflects higher reasoning fidelity. In this work, we challenge this assumption by investigating whether these metrics truly capture inter-step causal dependencies necessary for valid reasoning. We introduce three classes of […]
From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments
arXiv:2606.04275v1 Announce Type: cross Abstract: We present a novel theoretical framework for deep reinforcement learning (RL) in continuous environments by modeling the problem as a continuous-time stochastic process, drawing on insights from stochastic control. Building on previous work, we introduce a viable model of actor-critic algorithm that incorporates both exploration and stochastic transitions. For single-hidden-layer […]
Characterizing initial human-AI proof formalization workflows
arXiv:2606.04273v1 Announce Type: new Abstract: For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been a challenge. Advances in AI systems’ ability to generate code and engage in increasingly high-level mathematical reasoning promise to transform people’s ability to formalize and […]
Anycast Performance in Context
arXiv:2606.04298v1 Announce Type: cross Abstract: IP anycast lets a service advertise one address from many physical sites, leaving BGP to map each client to a site. It is central to the DNS root server system, public resolvers, and some content delivery networks, yet the same routing mechanism has very different consequences across applications. This paper […]