Xinyu Tan

Yilun Yao, Xinyu Tan, Chao-Hsuan Liu et al.

LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the base model, but also on the harness: the system layer that manages context, tools, state, constraints, permissions, tracing, and recovery. However, existing benchmarks typically abstract away execution, compare complete agent systems, or hold the harness fixed, making execution-layer variation difficult to study. We introduce Harness-Bench, a diagnostic benchmark for evaluating configuration-level harness effects in realistic agent workflows. Harness-Bench evaluates representative harness configurations across multiple model backends under shared task environments, budgets, and evaluation protocols, while preserving each harness's native execution behavior. The benchmark contains 106 sandboxed offline tasks constructed from practical agent-use patterns and manually reviewed for realism, solvability, oracle-checkability, and integrity. Each run records final artifacts, execution traces, usage statistics, and validator outputs, enabling analysis beyond final completion. Across 5,194 execution trajectories, we observe substantial variation in completion, process quality, efficiency, and failure behavior across model-harness pairings. These results suggest that agent capability should be reported at the model-harness configuration level rather than attributed to the base model alone. Our analysis further identifies recurring execution-alignment failures, where plausible reasoning becomes decoupled from tool feedback, workspace state, evidence, or verifiable output contracts. Harness-Bench provides a reproducible foundation for diagnosing and improving reliable, efficient, and auditable agent execution stacks.

Xi Zhang, Meijun Gao, Yuntian Zhao et al.

Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable action. Existing skills remain largely informal: Markdown skills and instruction packs encode procedures as long natural-language documents, while function calling, Model Context Protocol (MCP) servers, and framework tools structure individual actions but usually leave workflow state, policy enforcement, and completion discipline outside the skill itself. We introduce Formal Skill, a runtime-native abstraction that represents reusable capability with JSON metadata and action schemas, reliable Python executors, hook-governed control logic, Formal Skill routing, and skill-local runtime state. By moving reusable procedure from repeated prompt text into executable state machines and hook policies, Formal Skill gives agents a token-efficient and enforceable control surface. We implement the abstraction in FairyClaw, an open-source event-driven runtime for executable, observable, and composable Formal Skills. On Harness-Bench, FairyClaw obtains highly competitive average scores while using substantially fewer tokens, with especially strong results on tasks that expose the role of Formal Skill.

Xinyu Tan, Ningwei Bai, Harry Gardener et al.

We present, to our knowledge, the first sign language-driven Vision-Language-Action (VLA) framework for intuitive and inclusive human-robot interaction. Unlike conventional approaches that rely on gloss annotations as intermediate supervision, the proposed system adopts a gloss-free paradigm and directly maps visual sign gestures to semantic instructions. This design reduces annotation cost and avoids the information loss introduced by gloss representations, enabling more natural and scalable multimodal interaction. In this work, we focus on a real-time alphabet-level finger-spelling interface that provides a robust and low-latency communication channel for robotic control. Compared with large-scale continuous sign language recognition, alphabet-level interaction offers improved reliability, interpretability, and deployment feasibility in safety-critical embodied environments. The proposed pipeline transforms continuous gesture streams into coherent language commands through geometric normalization, temporal smoothing, and lexical refinement, ensuring stable and consistent interaction. Furthermore, the framework is designed to support future integration of transformer-based gloss-free sign language models, enabling scalable word-level and sentence-level semantic understanding. Experimental results demonstrate the effectiveness of the proposed system in grounding sign-derived instructions into precise robotic actions under diverse interaction scenarios. These results highlight the potential of the framework to advance accessible, scalable, and multimodal embodied intelligence.

Feiyu Wang, Xinyu Tan, Bokai Huang et al.

Large language models (LLMs) have revolutionized artificial intelligence, yet their massive memory and computational demands necessitate aggressive quantization, increasingly pushing representations toward the theoretical limit of a single bit. While complex-valued LLMs, such as iFairy, offer a superior chance for low-bit representation compared to real-valued counterparts, they require training from scratch, preventing the utilization of the vast ecosystem of pre-trained real-valued foundation models. Here we present Fairy2i, a universal framework that transforms pre-trained real-valued layers into an equivalent widely-linear complex form, enabling extremely low-bit quantization while reusing existing checkpoints. By proving a lossless mathematical equivalence between real and widely-linear maps, we convert standard Transformers into the complex domain and employ a phase-aware quantization scheme with a highly efficient codebook of fourth roots of unity. Furthermore, we introduce a recursive residual quantization mechanism that iteratively minimizes quantization error, allowing inference to proceed via efficient multiplication-free accumulation. We demonstrate that Fairy2i restores the performance of LLaMA-2 7B at an effective 2-bit precision to levels nearly comparable with full-precision baselines, significantly outperforming state-of-the-art real-valued binary and ternary quantization methods. This work bridges the gap between the representational efficiency of complex-valued arithmetic and the practical utility of pre-trained models, paving a new way for efficient inference on commodity hardware.

Ainesh Bakshi, Xinyu Tan

Gibbs states are a natural model of quantum matter at thermal equilibrium. We investigate the role of external fields in shaping the entanglement structure and computational complexity of high-temperature Gibbs states. External fields can induce entanglement in states that are otherwise provably separable, and the crossover scale is $h\asymp β^{-1} \log(1/β)$, where $h$ is an upper bound on any on-site potential and $β$ is the inverse temperature. We introduce a quasi-local Lindbladian that satisfies detailed balance and rapidly mixes to the Gibbs state in $\mathcal{O}(\log(n/ε))$ time, even in the presence of an arbitrary on-site external field. Additionally, we prove that for any $β<1$, there exist local Hamiltonians for which sampling from the computational-basis distribution of the corresponding Gibbs state with a sufficiently large external field is classically hard, under standard complexity-theoretic assumptions. Therefore, high-temperature Gibbs states with external fields are natural physical models that can exhibit entanglement and classical hardness while also admitting efficient quantum Gibbs samplers, making them suitable candidates for quantum advantage via state preparation.

Jacob Abernethy, Cyrus Anderson, Chengyu Dai et al.

Recovery from the Flint Water Crisis has been hindered by uncertainty in both the water testing process and the causes of contamination. In this work, we develop an ensemble of predictive models to assess the risk of lead contamination in individual homes and neighborhoods. To train these models, we utilize a wide range of data sources, including voluntary residential water tests, historical records, and city infrastructure data. Additionally, we use our models to identify the most prominent factors that contribute to a high risk of lead contamination. In this analysis, we find that lead service lines are not the only factor that is predictive of the risk of lead contamination of water. These results could be used to guide the long-term recovery efforts in Flint, minimize the immediate damages, and improve resource-allocation decisions for similar water infrastructure crises.