arXiv subjects

Xiangru Tang

Publications and source records attributed to Xiangru Tang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery

Scientific discovery demands intelligence, perseverance, and serendipity across vast search spaces. Today, top scientific capabilities remain siloed--one AI system for biological analysis, another for clinical reasoning, mathematical derivation, or materials simulation--and no pre-designed team can anticipate every skill a question will need. Science Earth is a planet-scale scientific runtime in which any capability--a simulation cluster, a wet-lab robot, a proof engine, a single-cell pipeline--can connect to any other, with collaboration structure emerging from the question itself. Its underlying EACN protocol lets capabilities discover one another, negotiate task ownership, and adjudicate across incompatible evidentiary standards without prior knowledge of who will meet whom. This shifts the organizing challenge from workflow design to open-ended connectivity. Two runs validate this under structurally distinct conditions. In a trans-Pacific higher-order Kuramoto synchronization study, agents identified and corrected a closure-ratio assumption in Ott-Antonsen analytic theory that fails outside the Lorentzian limit, within thirty minutes. In an eight-agent single-cell run on the 4.88M-cell Kang 2024 pan-cancer atlas, heterogeneous capabilities coupled over a 64.9-hour window with one structural external instruction, producing three new result layers and anchoring findings against an independent wet-lab study on an adjacent CCR8- TIGIT+ Treg subset. These cases are a first empirical reading, not a benchmark sweep. They show that when AI capabilities are truly connectable and coordination emerges from the problem, scientific reasoning becomes a distributed, self-correcting process--a step towards scaling AI-native discovery to the planet.

cs.AI↗

arXiv2026

MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks

Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps. Large language models (LLMs) now approach this through two routes: internalized reasoning and externalized agent scaffolding (frameworks that decompose problems collaboratively amongst multiple LLMs). To determine whether these routes are exclusive or complementary, we introduce MedicalAgentsBench, a filtered benchmark of 862 complex clinical questions drawn from the union of eight medical datasets via difficulty-aware curation and contamination screening. Evaluating three internalized reasoning models (DeepSeek-R1, o1-mini, and o3-mini), seven base models, and nine externalized agent-based methods, we find that internalized and externalized approaches each independently improve performance, and that their benefits compound: the highest accuracy is achieved by layering agent workflows onto an internalized reasoning model (i.e., o3-mini + MDAgents with 35.1%). Pareto analysis shows this combination dominates the cost-performance frontier; moreover, lightweight optimization on inexpensive models offers an entry point for resource-constrained settings. Our benchmark is at https://github.com/gersteinlab/MedicalAgentsBench.

cs.CL↗

arXiv2026

ProtocolBench: Which LLM MultiAgent Protocol to Choose?

As large-scale multi-agent systems evolve, the communication protocol layer has become a critical yet under-evaluated factor shaping performance and reliability. Despite the existence of diverse protocols (A2A, ACP, ANP, Agora, etc.), selection is often intuition-driven and lacks standardized guidance. We introduce ProtocolBench, a benchmark that systematically compares agent protocols along four measurable axes: task success, end-to-end latency, message or byte overhead, and robustness under failures. On ProtocolBench, protocol choice significantly influences system behavior. In the Streaming Queue scenario, overall completion time varies by up to 36.5% across protocols, and mean end-to-end latency differs by 3.48 s. Under Fail-Storm Recovery, resilience also differs consistently across protocols. Beyond evaluation, we present ProtocolRouter, a learnable protocol router that selects per-scenario (or per-module) protocols from requirement and runtime signals. ProtocolRouter reduces Fail-Storm recovery time by up to 18.1% versus the best single-protocol baseline, and achieves scenario-specific gains such as higher success in GAIA. We also release ProtocolRouterBench to standardize protocol evaluation and improve reliability at scale.

cs.AI↗

arXiv2026

Lessons from the Trenches on Reproducible Evaluation of Language Models

Reliable evaluation of language models (LMs) remains an open challenge. Re- searchers and engineers face methodological issues such as the sensitivity of models to evaluation setup, difficulty of proper comparisons across methods, and the lack of reproducibility and transparency. Evaluation difficulties are exacer- bated by the fracturing and siloing of information about conventions and common practices. In this paper we draw on three years of experience in evaluating large lan- guage models (LMs) as developers of the popular Language Model Evaluation Harness (lm-eval) (Gao et al., 2023) framework to provide guidance and lessons for the field moving forward. We document a variety of challenges faced by prac- titioners and provide concrete instances where these challenges or the absence of best practices have come into effect. We make recommendations to the field for improving evaluation rigor and confidence, and attempt to codify much of the tacit or folk knowledge surrounding LM evaluation, for a solid ground to move forward.

cs.CL↗

arXiv2026

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue that many headline RLVR gains are not yet well validated because reports often conflate policy improvement with three confounds: (i) budget mismatch between RLVR and baseline evaluations, (ii) attempt inflation and calibration drift that convert abstentions into confident answers, and (iii) benchmark data contamination. Using budget-matched reproductions and partial-prompt contamination probes, we find that several widely cited gaps shrink substantially or disappear once budgets, prompts, and dataset versions are matched and contaminated sets are treated as memorization probes rather than evidence of reasoning. This does not mean that RLVR is ineffective, but it implies that current measurements often overstate capability gains and obscure reliability costs. We therefore propose a compact, tax-aware minimum standard for RLVR training and evaluation: budget-matched saturation curves with variance, calibration, and abstention tracking, a judge-robustness stress test when LLM judges are used, and an explicit contamination screen. With these controls, RLVR remains effective and deployable in verifiable domains, but reasoning gains should be treated as provisional without them.

cs.LG↗

arXiv2026

SurfDesign: Effective Protein Design on Molecular Surfaces

Protein function is largely determined by molecular surface geometry and physicochemical complementarity, yet most protein design methods condition only on backbone structure. We introduce SurfDesign, a surface-conditioned protein design framework that models molecular surfaces as continuous geometric manifolds and integrates them with pretrained protein language models. SurfDesign employs surface-based equivariant message passing to capture surface normals, curvature, and directional geometry, together with a parameter-efficient fine-tuning strategy. Focusing on functional protein design, we show that SurfDesign consistently outperforms prior surface-conditioned and backbone-only methods on de novo binder and enzyme design benchmarks. We also report strong performance on inverse-folding benchmarks as a diagnostic of structural compatibility. Our results highlight manifold-aware surface representations as a principled foundation for functional protein and enzyme design. Code is available at https://github.com/smiles724/SurfDesign.

q-bio.BM↗

arXiv2026

The Last Human-Written Paper: Agent-Native Research Artifacts

Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation imposes two structural costs: a Storytelling Tax, where failed experiments, rejected hypotheses, and the branching exploration process are discarded to fit a linear narrative; and an Engineering Tax, where the gap between reviewer-sufficient prose and agent-sufficient specification leaves critical implementation details unwritten. Tolerable for human readers, these costs become critical when AI agents must understand, reproduce, and extend published work. We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with a machine-executable research package structured around four layers: scientific logic, executable code with full specifications, an exploration graph that preserves the failures compilation discards, and evidence grounding every claim in raw outputs. Three mechanisms support the ecosystem: a Live Research Manager that captures decisions and dead ends during ordinary development; an ARA Compiler that translates legacy PDFs and repos into ARAs; and an ARA-native review system that automates objective checks so human reviewers can focus on significance, novelty, and taste. On PaperBench and RE-Bench, ARA raises question-answering accuracy from 72.4% to 93.7% and reproduction success from 57.4% to 64.4%. On RE-Bench's five open-ended extension tasks, preserved failure traces in ARA accelerate progress, but can also constrain a capable agent from stepping outside the prior-run box depending on the agent's capabilities. Our code is open-sourced at https://github.com/Orchestra-Research/Agent-Native-Research-Artifact.

cs.LG↗

arXiv2026

Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions

Hypergraphs model higher-order relations that drive real-world decisions, from drug prescriptions to recommendations. A central structural signal in such data, beyond what pairwise relations can express, is interaction compositionality: whether a higher-order relation is compositional, emergent, or inhibitory with respect to its observed or unobserved sets. In polypharmacy, the regime decides whether a drug should be dropped, kept, or excluded: a compositional drug triple can be safely simplified, an emergent triple requires all drugs jointly, and an inhibitory triple flags a drug that disrupts an existing interaction. However, existing hypergraph learning methods, which merely propagate messages over observed hyperedges, leave this compositional signal unmodeled, allowing dangerous drug combinations to slip through and be misclassified. To this end, we propose the Hypergraph Pattern Machine (HGPM), shifting the paradigm from message passing to learning the compositional pattern of subsets. It tokenizes compositional subsets, organizes them in an inclusion DAG, and trains an inclusion-aware Transformer under masked reconstruction. On ten hypergraph benchmarks, HGPM matches or exceeds state-of-the-art methods. Notably, in a real adverse-event prediction case, HGPM correctly identifies the drug addition that inhibits the side effect among feature-identical candidates, a discrimination existing methods cannot make. The code and data are in https://github.com/KryieZhao/HGPM.git.

cs.LG↗

arXiv2026

D-Flow: Multi-modality Flow Matching for D-peptide Design

Among these, D-peptides are resistant to proteolysis, exhibit greater in vivo stability, and are easier to synthesize. Despite advances in deep learning for peptide discovery, the scarcity of natural D-protein data limits the transfer of existing generative models to the D-peptide chemical space. We propose D-Flow, a full-atom flow-based framework for de novo D-peptide design. Conditioned on receptor binding, D-Flow uses structural representations incorporating backbone frames, side-chain angles, and discrete amino acid types. A mirror-image algorithm is implemented to address the lack of training data for D-proteins by converting the chirality of L-receptors. Furthermore, we enhance D-Flow's capacity by integrating protein language models (PLMs) with structural awareness through a lightweight structural adapter that injects structural representations into PLM embeddings. This enables D-Flow to learn conformational priors in the D-peptide chemical space and to accommodate the chiral selectivity of binding sites, thereby mitigating the scarcity of D-peptide data. A two-stage training pipeline and a control toolkit enable D-Flow to transition from general protein design to targeted binder design while preserving pre-training knowledge. Results on the PepMerge benchmark show D-Flow's effectiveness. D-peptides generated by D-Flow align more closely with native sequences and structures, with sequence identity improving by 10.2% over the best baseline, and the top affinity score reaching 24.31%. Overall, D-Flow shows potential for D-peptide design, facilitating the development of bioorthogonal and stable molecular tools and diagnostics. Code is available at https://github.com/smiles724/PeptideDesign.

cs.CE↗

arXiv2026

ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows

Large Language Models (LLMs) have extended their impact beyond Natural Language Processing, substantially fostering the development of interdisciplinary research. Recently, various LLM-based agents have been developed to assist scientific discovery progress across multiple aspects and domains. Among these, computer-using agents, capable of interacting with operating systems as humans do, are paving the way to automated scientific problem-solving and addressing routines in researchers' workflows. Recognizing the transformative potential of these agents, we introduce ScienceBoard, which encompasses two complementary contributions: (i) a realistic, multi-domain environment featuring dynamic and visually rich scientific workflows with integrated professional software, where agents can autonomously interact via different interfaces to accelerate complex research tasks and experiments; and (ii) a challenging benchmark of 169 high-quality, rigorously validated real-world tasks curated by humans, spanning scientific-discovery workflows in domains such as biochemistry, astronomy, and geoinformatics. Extensive evaluations of agents with state-of-the-art backbones (e.g., GPT-4o, Claude 3.7, UI-TARS) show that, despite some promising results, they still fall short of reliably assisting scientists in complex workflows, achieving only a 15% overall success rate. In-depth analysis further provides valuable insights for addressing current agent limitations and more effective design principles, paving the way to build more capable agents for scientific discovery. Our code, environment, and benchmark are at https://qiushisun.github.io/ScienceBoard-Home/.

cs.AI↗

arXiv2026

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

With the growing adoption of large language model agents in persistent real-world roles, they naturally encounter continuous streams of tasks. A key limitation, however, is their failure to learn from the accumulated interaction history, forcing them to discard valuable insights and repeat past errors. We propose ReasoningBank, a novel memory framework that distills generalizable reasoning strategies from an agent's self-judged successful and failed experiences. At test time, an agent retrieves relevant memories from ReasoningBank to inform its interaction and then integrates new learnings back, enabling it to become more capable over time. Building on this powerful experience learner, we further introduce memory-aware test-time scaling (MaTTS), which accelerates and diversifies this learning process by scaling up the agent's interaction experience. By allocating more compute to each task, the agent generates abundant, diverse experiences that provide rich contrastive signals for synthesizing higher-quality memory. The better memory in turn guides more effective scaling, establishing a powerful synergy between memory and test-time scaling. Across web browsing and software engineering benchmarks, ReasoningBank consistently outperforms existing memory mechanisms that store raw trajectories or only successful task routines, improving both effectiveness and efficiency; MaTTS further amplifies these gains. These findings establish memory-driven experience scaling as a new scaling dimension, enabling agents to self-evolve with emergent behaviors naturally arise. Our code can be found at https://github.com/google-research/reasoning-bank.

cs.AI↗

arXiv2026

Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents

Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horizons. We argue that this failure reflects a fundamental mismatch: step-wise reasoning induces a form of step-wise greedy policy that is adequate for short horizons but fails in long-horizon planning, where early actions must account for delayed consequences. From this planning-centric perspective, we study LLM-based agents in deterministic, fully structured environments with explicit state transitions and evaluation signals. Our analysis reveals a core failure mode of reasoning-based policies: locally optimal choices induced by step-wise scoring lead to early myopic commitments that are systematically amplified over time and difficult to recover from. We introduce FLARE (Future-aware Lookahead with Reward Estimation) as a minimal instantiation of future-aware planning to enforce explicit lookahead, value propagation, and limited commitment in a single model, allowing downstream outcomes to influence early decisions. Across multiple benchmarks, agent frameworks, and LLM backbones, FLARE consistently improves task performance and planning-level behavior, frequently allowing LLaMA-8B with FLARE to outperform GPT-4o with standard step-by-step reasoning. These results establish a clear distinction between reasoning and planning.

cs.AI↗

arXiv2026

Molecular Representations in Implicit Functional Space via Hyper-Networks

Molecular representations fundamentally shape how machine learning systems reason about molecular structure and physical properties. Most existing approaches adopt a discrete pipeline: molecules are encoded as sequences, graphs, or point clouds, mapped to fixed-dimensional embeddings, and then used for task-specific prediction. This paradigm treats molecules as discrete objects, despite their intrinsically continuous and field-like physical nature. We argue that molecular learning can instead be formulated as learning in function space. Specifically, we model each molecule as a continuous function over three-dimensional (3D) space and treat this molecular field as the primary object of representation. From this perspective, conventional molecular representations arise as particular sampling schemes of an underlying continuous object. We instantiate this formulation with MolField, a hyper-network-based framework that learns distributions over molecular fields. To ensure physical consistency, these functions are defined over canonicalized coordinates, yielding invariance to global SE(3) transformations. To enable learning directly over functions, we introduce a structured weight tokenization and train a sequence-based hyper-network to model a shared prior over molecular fields. We evaluate MolField on molecular dynamics and property prediction. Our results show that treating molecules as continuous functions fundamentally changes how molecular representations generalize across tasks and yields downstream behavior that is stable to how molecules are discretized or queried.

cs.LG↗

arXiv2026

MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning

Medical Large Vision-Language Models (Med-LVLMs) have shown strong potential in multimodal diagnostic tasks. However, existing single-agent models struggle to generalize across diverse medical specialties, limiting their performance. Recent efforts introduce multi-agent collaboration frameworks inspired by clinical workflows, where general practitioners (GPs) and specialists interact in a fixed sequence. Despite improvements, these static pipelines lack flexibility and adaptability in reasoning. To address this, we propose MMedAgent-RL, a reinforcement learning (RL)-based multi-agent framework that enables dynamic, optimized collaboration among medical agents. Specifically, we train two GP agents based on Qwen2.5-VL via RL: the triage doctor learns to assign patients to appropriate specialties, while the attending physician integrates the judgments from multi-specialists and its own knowledge to make final decisions. To address the inconsistency in specialist outputs, we introduce a curriculum learning (CL)-guided RL strategy with dynamic entropy regulation, progressively teaching the attending physician to balance between imitating specialists and correcting their mistakes. Experiments on five medical VQA benchmarks demonstrate that MMedAgent-RL outperforms both open-source and proprietary Med-LVLMs. Notably, it achieves an average performance gain of 23.6% over strong baselines.

cs.LG↗

arXiv2026

SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks

We present SciArena, an open and collaborative platform for evaluating foundation models on scientific literature-grounded tasks. Unlike traditional benchmarks for scientific literature understanding and synthesis, SciArena engages the research community directly, following the Chatbot Arena evaluation approach of community voting on model comparisons. By leveraging collective intelligence, SciArena offers a community-driven evaluation of model performance on open-ended scientific tasks that demand literature-grounded, long-form responses. The platform currently supports 47 foundation models and has collected over 20,000 votes from human researchers across diverse scientific domains. Our analysis of the data collected so far confirms its high quality. We discuss the results and insights based on the model ranking leaderboard. To further promote research in building model-based automated evaluation systems for literature tasks, we release SciArena-Eval, a meta-evaluation benchmark based on collected preference data. It measures the accuracy of models in judging answer quality by comparing their pairwise assessments with human votes. Our experiments highlight the benchmark's challenges and emphasize the need for more reliable automated evaluation methods.

cs.CL↗

arXiv2026

Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations

While large language models (LLMs) with Chain-of-Thought (CoT) reasoning excel in mathematics and coding, their potential for systematic reasoning in chemistry, a domain demanding rigorous structural analysis for real-world tasks like drug design and reaction engineering, remains untapped. Current benchmarks focus on simple knowledge retrieval, neglecting step-by-step reasoning required for complex tasks such as molecular optimization and reaction prediction. To address this, we introduce ChemCoTBench, a reasoning framework that bridges molecular structure understanding with arithmetic-inspired operations, including addition, deletion, and substitution, to formalize chemical problem-solving into transparent, step-by-step workflows. By treating molecular transformations as modular "chemical operations", the framework enables slow-thinking reasoning, mirroring the logic of mathematical proofs while grounding solutions in real-world chemical constraints. We evaluate models on two high-impact tasks: Molecular Property Optimization and Chemical Reaction Prediction. These tasks mirror real-world challenges while providing structured evaluability. By providing annotated datasets, a reasoning taxonomy, and baseline evaluations, ChemCoTBench bridges the gap between abstract reasoning methods and practical chemical discovery, establishing a foundation for advancing LLMs as tools for AI-driven scientific innovation.

cs.AI↗

arXiv2025

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.

cs.AI↗

arXiv2025

Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts

Large Language Model (LLM)-powered multi-agent systems (MAS) have rapidly advanced collaborative reasoning, tool use, and role-specialized coordination in complex tasks. However, reliability-critical deployment remains hindered by a systemic failure mode: hierarchical compliance under instruction conflicts (system-user, peer-peer), where agents misprioritize system-level rules in the presence of competing demands. Moreover, widely used macro-level metrics (e.g., pass@k) obscure these micro-level violations and offer little actionable guidance for remedy. In this work, we present a full-stack, three-stage framework: (1) Diagnose - Contextualized Role Adherence Score (CRAS), a query-wise, context-aware scoring metric that decomposes role adherence into four measurable dimensions; (2) Localize - attention drift analysis revealing that instruction conflicts are resolved by attention heads that are largely concentrated in middle layers; (3) Align - Surgical Alignment of Instruction Layers (SAIL), which installs LoRA only on the localized focal layers and optimizes a token-weighted DPO-style preference objective that credits tokens by their focal attentional contribution. Across standard benchmarks and MAS frameworks, our surgical approach improves instruction hierarchy compliance (e.g., +5.60% with AutoGen on MedQA) without full-model finetuning.

cs.CL↗