Search arXiv⌕ Search

arXiv subjects

Zhenfei Yin

Publications and source records attributed to Zhenfei Yin.

At least 19 recordsLinked to original sources
arXiv2026

CoEnv: Code-Driven Exploration in Real-to-Sim Digital Twins for Multi-Arm Manipulation

General-purpose coding agents can now write, debug, and refine entire robot programs, but only if they have somewhere to practice. Physical hardware is a poor practice ground: exploratory rollouts are slow to reset and, when several arms share a workspace, unsafe. Generic simulation benchmarks are safe but do not match the geometry, assets, or viewpoints of the workspace where the robot must actually work. We present CoEx (Code-driven Exploration), which lets the agent practice in an executable digital twin of its own deployment workspace. The twin is built by CoEnv, our real-to-sim framework, which reconstructs the physical scene from multi-view RGBD into a physics simulation. Inside it, a centralized code agent explores at the program level, writing a complete multi-arm program, running it in the twin, and refining it against grounded verification (privileged state checks, checkpoint predicates on risky steps, and adaptive viewpoints against inter-arm occlusion). Verified programs transfer to hardware through collision-checked deployment. On five real-world multi-arm tasks with up to three heterogeneous robots, CoEx reaches 70% average success, against 50% for the same system without the code agent (where a VLM must choose every primitive step by step), outperforms two prior VLM-planning frameworks, and produces verified episodes at 3.8-11.7x the ablated rate. Because every verified rollout is also a demonstration, exploration leaves reusable experience behind: a $π_{0.5}$ policy fine-tuned purely on 200 agent-generated rollouts reaches 100% and 70% real-robot success on two tasks, with no human demonstrations.

cs.RO↗
arXiv2026

RAP: Research Attention Prediction in Language Agents

LLM agents increasingly support research planning and execution, where judgments about current and anticipated research activity inform decisions. Yet whether they can infer changes across a whole field from the partial evidence they retrieve through online scholarly search remains unclear. We introduce Research Attention Prediction (RAP), a literature search benchmark for evaluating this ability. We build a local search environment from 356,357 dated arXiv papers and construct two complementary evaluation tasks. The benchmark comprises a Core set of 2,160 questions across 54 AI/ML fields and an Extended set covering 269 fields. Our evaluation and analysis of LLM agents show that search substantially improves stronger agents' recognition of recent changes, while forecasting gains remain limited or negative. Agents update forecasts across dates and adjust their investigations to forecasting goals, but these adaptations do not reliably yield accurate predictions of future shifts. Even for recent changes, final judgments can diverge from what the retrieved papers indicate. These findings show that agents can recognise some recent changes, yet reliably anticipating future research activity remains difficult despite changes in their answers and investigations.

cs.AI↗
arXiv2026

DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

Scientific discovery requires developing worthwhile hypotheses into practical investigations, yet learning from this evolving research process remains challenging. We introduce an operational definition of valuable and testable research hypotheses: evidence-grounded claims about consequential uncertainties, coupled with feasible investigations, explicit decision criteria, and alternative explanations. Our DiscoveryRSI framework develops hypothesis trees through multi-agent evolutionary search, compiles selected investigations into executable Harbor tasks, and recursively learns through three mechanisms: hypothesis credit optimization attributes scientific assessments to documented research contributions; harness replay identifies productive strategies and recurring failures to refine research workflows; and rediscovery applies accepted improvements to new investigations, generating further experience for subsequent learning. We also introduce DFM-Bench, which provides comprehensive assessment of hypothesis quality and cumulative research progress at the levels of hypotheses, revisions, development paths and research runs. Across four life-science domains, automated evaluation shows that hypothesis quality rises from 4.86 for the base model to 5.39 after two rounds of self-improvement, with the large gains in falsifiability and data resolvability. We further validate hypothesis quality through expert review, comparing our DiscoveryRSI-27B with other research agents. Preliminary human assessments show that DiscoveryRSI-27B scores higher than GPT-6 Luna on hypothesis importance and whether claims are plausible and evidence-bounded. DiscoveryRSI-27B achieved a 6.3% rate of hypothesis correspondence with research published after the model cutoff, largely outperform GPT-6 with 2.5% and Claude Opus 5 with 2.3%, while delivering greater human-rated improvement along research paths.

cs.CL↗
arXiv2026

The Weight of Teamwork: Does Communication Structure Help LLM Scientists Search for Scientific Laws?

Team performance is often reported as one delivered score, even though that score is produced in two stages: a system generates candidate answers and a selection rule returns one of them. We use symbolic regression as an observable scientific-search setting and compare fixed-budget LLM teams that differ in peer visibility and update timing, evaluating both their frozen candidate archives and the expressions selected from those archives. Distributing the call budget across more independent trajectories produced the largest measured gain, improving mean held-out fitting score Q by 0.70 at the widest tested allocation. Under a common archive-wide selector, the implemented Ring policy reduced mean Q by 0.33 relative to Independent, while Star and Complete remained unresolved. Holding the generated archives fixed, changing the delivery rule changed the measured architecture gaps, including the sign of the Complete point estimate. These results support reporting candidate generation and final selection as separate endpoints. They do not identify a communication mechanism or a universally preferred topology; rather, they show that an architecture ranking is not identified by communication structure alone when the rule that returns the final answer is left unspecified.

cs.MA↗
arXiv2026

Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG

Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second, multi-agent pipelines often dilute strong solutions by averaging across all candidates. We address these challenges with a unified framework that combines implicit retrieval and structured collaboration. At its foundation, a Monitor-based retrieval module operates at the token level, integrating external knowledge with minimal disruption to reasoning. On top of this substrate, Hierarchical Solution Refinement (HSR) iteratively designates each candidate as an anchor to be repaired by its peers, while Quality-Aware Iterative Reasoning (QAIR) adapts refinement to solution quality. On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy - the highest reported to date, surpassing the strongest agent baseline by 13.4 points and leading frontier LLMs by up to 18.1 points, while simultaneously reducing token usage by 53.5% and agent steps by 43.7%. Results on SuperGPQA and TRQA confirm robustness across domains. Error analysis shows that reasoning failures and knowledge gaps co-occur in over 85% of cases, while diversity analysis reveals a clear dichotomy: retrieval tasks benefit from solution variety, whereas reasoning tasks favor consensus. Together, these findings demonstrate how implicit augmentation and structured refinement overcome the inefficiencies of explicit tool use and uniform aggregation. The code is available at https://github.com/tangxiangru/Eigen-1.

cs.CL↗
arXiv2026

False Belief Dissemination, Persistence and Mitigation in Multi-Agent Social Networks Through the Lens of the Mandela Effect

Multi-agent social networks are emerging as communities in which agents communicate, retain memories, and publish information that others can find as evidence. These interactions create opportunities for false claims to spread and remain influential beyond their original sources, analogous to the Mandela effect in human societies, in which many people recall the same false memory. In this paper, we systematically study false-belief dynamics through the lens of the Mandela effect, focusing on dissemination, persistence, and mitigation. Specifically, we build a controlled framework connecting agent communication, private memory, and a shared simulated web to mimic information dissemination in practical social networks, supported by 540 fabricated claims spanning 8 domains and 4 plausibility levels. For dissemination, we measure how widely and quickly claims gain acceptance across models and communication topologies. For persistence, we withdraw agents promoting fabricated claims while retaining existing articles and memories, and track subsequent acceptance. For mitigation, we compare preventive measures applied before implantation with corrective interventions introduced after claims have spread. Experimental results show that evaluated models readily accept and disseminate fabricated claims, with dissemination reach as high as 96.0%. Dissemination reach varies with claim plausibility, domain, and network size and composition, while communication topology shapes dissemination speed across model families. Acceptance barely declines after fabricators withdraw, and targeted corrective interventions outperform the preventive measures without eliminating false beliefs. These findings identify persistent false beliefs as a safety challenge for multi-agent social networks and highlight the need to address both their initial dissemination and the accumulated evidence that sustains them.

cs.SI↗
arXiv2026

Think3D: Thinking with Space for Spatial Reasoning

While Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by 2D-centric paradigm that severely limits genuine 3D spatial reasoning. To bridge this gap, we introduce Think3D, a novel framework that equips VLM agents with interactive, 3D chain-of-thought reasoning capabilities. By integrating a suite of 3D manipulation tools, Think3D transforms perception into active spatial exploration, mirroring human geometric reasoning. Think3D consistently improves proprietary models, including GPT-4.1 and Gemini 2.5 Pro, across BLINK Multi-view, MindCube-1K, and VSI-Bench-Tiny. We further propose Think3D-RL to teach smaller open-weight models how to manipulate 3D space effectively. Using only final-answer rewards, without process supervision or handcrafted exploration trajectories, Think3D-RL enables Qwen3-VL-4B to autonomously learn effective 3D exploration strategies. After training, the model exhibits tool-use patterns similar to those of stronger proprietary models, while shifting the effect of 3D tool use on MindCube-1K from a performance drop to a substantial improvement. These results show that active exploration in 3D space provides an effective and general paradigm for improving spatial reasoning in multimodal agents. Code, models, and data are available at https://github.com/zhangzaibin/spagent.

cs.CV↗
arXiv2026

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a domain-general framework built on JEPA-Anything that uses predictive world models to guide action and learning-data selection. Observed feedback drives policy or workflow improvement and conditional world-model adaptation, while component and compatibility checks govern the retention of updated policy-model pairs. Across diverse computational and scientific domains, RSI-Anything demonstrates substantial gains. In code repair, with the coder fixed, success increases from 26.3% with a static verifier to 29.2% through predictive selection and 31.2% after world-model adaptation, at comparable test usage. Graphical user interface (GUI) evaluations showed higher task completion, while average actions decrease by 39.4%. Across five successive policy versions, laboratory-planning scores more than double from 21.80% to 46.01%. In reaction optimization, RSI-Anything achieves 96.15% mean best observed yield versus 82.16% for Bayesian optimization under the same 40-experiment budget. An end-to-end immune-science application further connects workflow evolution and predictive modeling with therapeutic hypothesis generation. These results demonstrate how predictive world models and retained system updates enable recursive improvement across diverse environments.

cs.CL↗
arXiv2026

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

Agent skills have become an important mechanism for equipping language-model agents with reusable procedural knowledge. However, providing skills alone does not guarantee that current models can effectively identify, apply, and coordinate them. To improve skill-use capabilities, we introduce SKT, a verified data synthesis pipeline that constructs skill-grounded tasks and executable trajectories from large collections of agent skills. SKT selects suitable single-skill and multi-skill configurations, synthesizes tasks through rule-based and agent-based verification with feedback-guided repair, and retains only successful trajectories that substantially use every required skill. Using 2,000 public skills, SKT produces 4,000 task packages and 27,164 verified trajectories. Based on the same pipeline and a disjoint test pool, we further construct SkillEval, a held-out executable benchmark for evaluating skill use. Experiments across diverse models, benchmarks, and agent harnesses show that supervised fine-tuning on SKT-generated trajectories consistently improves skill-use performance. Verification ablations, cross-harness evaluation, and scaling experiments further demonstrate that these gains depend on high-quality supervision, extend beyond a single agent interface, and increase with broader skill coverage. Together, these results establish verified data synthesis as an effective and scalable approach for skill-use training.

cs.AI↗
arXiv2026

Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models

Generalization in multi-arm collaboration can be studied as composing familiar atomic skills in new ways across arms. However, existing evaluations offer limited insight into which training and architectural choices support this ability under different coordination requirements. We introduce \textbf{ACG-Bench}, a benchmark for \emph{Arm-wise Compositional Generalization} that provides a common testbed for studying skill recomposition in dual-arm policies. It contains 23 task--condition pairs across 8 task families, with 6 in-domain conditions and 17 unseen compositions covering reordering, synchronization, their combination, and cross-task composition. All methods receive the same per-arm atomic prompts, and success requires achieving the task goal while satisfying physical milestones and specified order or timing constraints. Using $π_{0.5}$ as a common vision-language-action backbone, we compare representative data-augmentation and architectural strategies with shared source data and a common evaluation protocol. Our architectural study examines arm-token grouping, skill-specific LoRA adapters (SkillLoRA), and arm-wise attention (AWA), highlighting the complementarity of skill-conditioned parameters and attention structure. Combining these choices yields \textbf{AE-VLA}, which achieves 21.53\% generalization success in simulation, compared with 2.94\% for Single $π_{0.5}$, 3.06\% for MA-VLA, and 5.53\% for two independently controlled $π_{0.5}$ policies. On physical SO101 robots, AE-VLA reaches 39.00\% mean success across five unseen conditions, compared with 10.00\% for the strongest baseline. These findings provide empirical guidance for designing dual-arm policies that generalize beyond fixed training routines.

cs.RO↗
arXiv2026

Oneira: From Open-Ended Generation to Open-World Interaction in Video World Models

Generative video world models can now synthesize open-ended environments that agents can navigate and interact with in simple ways. Yet open-ended generation does not imply full interaction: as a generated world expands, newly created content through navigation should expand what the agent can act upon, and as the agent changes the world, those changes should become persistent parts of the environment rather than transient visual effects. We characterize these two requirements as Open-World Interactivity, where newly generated or encountered entities are incorporated into the actionable world, and Persistent State, where interaction outcomes are committed to the world state and continue to influence subsequent observations and interactions. We present Oneira, an interactive video world model that closes the loop between generation and interaction through an explicit, extensible world state managed by a coding agent. Given the current observation and an action or high-level goal, the agent reads the world state, grounds the relevant entities, plans the interaction, and writes its outcome back into a world state table. When exploration reveals new objects, the agent incorporates them from generated observations, allowing the interaction space to expand with the generated world. Meanwhile, previously induced state changes are carried across video segments, making the consequences of interaction persistent parts of subsequent world evolution. The updated world state is rendered along the camera action trajectory into a coarse conditioning video, from which a video generator fills in the appearance, motion, and interaction details not represented in the state. Experiments show that Oneira enables direct and consistent interaction with newly generated objects, while preserving the effects of prior interactions over long horizons. Project page: https://madaoer.github.io/projects/oneira

cs.CV↗
arXiv2026

StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit assignment over extended trajectories. In this work, we present Strategic Trajectory Abstraction (StraTA), a simple framework that introduces an explicit trajectory-level strategy into agentic reinforcement learning (RL). StraTA samples a compact strategy from the initial task state, conditions subsequent actions on that strategy, and trains strategy generation and action execution jointly with a hierarchical GRPO-style rollout design, further enhanced by diverse strategy rollout and critical self-judgment. Experiments on ALFWorld, WebShop, and SciWorld show that StraTA consistently improves both sample efficiency and final performance over strong baselines. StraTA reaches success rates of 93.1% on ALFWorld and 84.2% on WebShop. On SciWorld, StraTA attains a 63.5% overall score, outperforming frontier closed-source models.

cs.CL↗
arXiv2026

SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm

Social simulation offers the social sciences an experimental instrument that the real world cannot supply, and generative agents have transformed it by acting as silicon samples that unite agent-based modeling with real behavioral data. Existing platforms verify collective behavior, align simulated populations with real societies in cross-sections, and employ autonomous agents for the research process. However, two social science requirements remain without systematic support: intervention in the content of a simulation and the researcher's control over the process that produces it. We present SocioVerse2, which extends SocioVerse 1.0 into a human-AI co-evolutionary paradigm built from two loops and one infrastructure. The longitudinal simulation loop simulates the target population with evolving environments and forks counterfactual branches via interventions. The controllable research loop takes the study itself as an editable state and updates state versions via controllable editing. The social science agentic infrastructure carries both loops through composable skills with researcher checkpoints, a population service over five persona pools, and an environment service over 21 real-world signal sources with point-in-time guarantees. We validate SocioVerse2 across three case families and seven case studies, from reproducing canonical agent-based models to modeling policy processes on real records and nowcasting macro-economic indices beyond the response model's knowledge cutoff. With the human-AI co-evolutionary paradigm, these cases go beyond system demonstrations to become substantive studies that investigate frontier questions in their respective disciplines. Code, data services, and a workbench are released as open-source resources.

cs.CL↗
arXiv2026

JEPA-Anything: Learning Predictive Models across Different Worlds

World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling across radically different systems? We introduce JEPA-Anything, a domain-agnostic framework based on orthogonal predictive factorization (OPF). Extending joint-embedding predictive architectures, OPF decomposes latent targets into complementary factors, learns them through dedicated pathways, and recombines them within a shared predictive design. We evaluate JEPA-Anything across seven domains: vision, biology, clinical trajectories, control, molecular dynamics, physical fields, and weather. Experiments span representation learning, intervention prediction, out-of-distribution generalization, and long-horizon dynamics, including 10 matched dynamics tasks, forecasting of over 1,000 clinical events, and 100-step molecular rollouts across four systems. Against matched JEPA baselines, JEPA-Anything improves reported metrics on all 10 dynamics tasks and reduces single-intervention prediction error on Interventional Pong by 34.8%. It achieves the lowest one-step and 100-step molecular errors among compared methods in all four systems. Beyond prediction, a factor-nominated biological intervention receives experimental support in cell co-cultures, patient-derived organoids, tumor fragments, and mice; latent orbital modes recover the Keplerian scaling exponent with a fitted slope of -1.4991. These results support a common factorized predictive principle across heterogeneous worlds, connecting world modeling with intervention and experimentally grounded scientific discovery. Code: https://github.com/Gen-Verse/JEPA-Anything

cs.CL↗
arXiv2026

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE

cs.CL↗
arXiv2026

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying out scientific tasks while transforming their requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. At its core is recursive-in-recursive self-improvement, a paradigm that couples harness evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, while the outer recursion trains the model under the improved harness. Harness evolution shapes training experience, and model learning creates new opportunities for harness adaptation. We present case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scientific task families. By releasing ScienceBuddy as a research product, we make this paradigm available to the scientific community and take a step toward discovery intelligence: scientific AI that advances through sustained collaboration with researchers and evolves alongside the research it supports. Website: http://science-buddy.io

cs.AI↗
arXiv2026

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through action, tool use, and outcome feedback. We argue that the next frontier is a further transition: from solving and acting within problems specified by humans to participating in the process by which new problems, representations, explanations, and knowledge are created. We refer to this capability as Discovery Intelligence. We formulate Discovery Foundation Models (DFMs) as general-purpose model systems for open-ended discovery. A DFM operates over a revisable research state and supports seven coupled capabilities spanning problem discovery, formulation, representation construction, hypothesis formation, intervention, evidence-grounded revision, and continual discovery improvement. We instantiate this framework with Zetema, which couples explicit research-state dynamics, verification and experimental gating, external grounding, and cross-task Discovery Skill evolution. We further ground the framework with GALILEO, a real therapeutic-discovery system in which Dry-Lab reasoning, robotic and hands-on Wet-Lab experimentation, external biological evidence, and iterative hypothesis and design revision form a closed physical discovery loop. We then formulate a unified approach to capability formation and process-centered evaluation, enabling discovery behavior to be trained, improved, and measured beyond final-answer performance. Together, these components establish discovery as a learnable, executable, and evaluable capability of foundation-model systems. We view this shift as a broader progression in intelligence scaling: from learning over existing knowledge, to learning from action outcomes, and ultimately to participating in the construction, testing, and revision of the structures through which new knowledge is discovered. Code: https://github.com/Gen-Verse/DFM-Plans

cs.CL↗
arXiv2026

An immune world model for multiscale forecasting and therapeutic hypothesis generation

Immune therapies act across cell-intrinsic programs, tissue ecosystems, and patient-specific immune states, yet most predictors address these scales separately. We used a governed evolutionary AI Scientist to construct the Immune World Model, an action-conditioned model that learns how interventions move immune states across cellular, tissue, and individual levels. The Immune World Model--building Scientist searched candidate architectures and workflows, and the resulting world model was frozen before independent confirmation. The frozen model generalized to unseen interventions and biological contexts, recovered intervention-specific cellular programs, integrated cell and tissue information to improve ecosystem and patient-response prediction, and forecast unseen perturbation combinations. Immune World Model--guided analysis then combined measured perturbations with cross-axis inference to nominate IL-36$γ$ plus SIRP$α$ inhibition as a complementary-axis therapeutic hypothesis, whereas a governed self-correction audit rejected every screened cytokine pair. The Immune World Model provides a framework for multiscale immune simulation that connects AI Scientist-driven model construction, intervention forecasting, and the generation of prospectively testable therapeutic hypotheses.

cs.LG↗