AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition

LLM agents are increasingly built not as single model calls, but as scaffolded systems that combine reasoning, memory, reflection, action execution, and learning. While such scaffolds often improve performance, they are often embedded in tightly coupled pipelines, making it difficult to isolate component contributions, compare alternative designs, or understand how module interactions shape agent behavior. We introduce AgentSpec, a modular specification framework that represents embodied agents as typed compositions of reusable policy components with standardized interfaces. AgentSpec standardizes the interfaces among perception, memory, reasoning, reflection, action, and optional learning, enabling components to be swapped and recombined under controlled conditions. We instantiate this framework across DeliveryBench, ALFRED, MiniGrid, and RoboTHOR, and analyze reasoning, memory, reflection, and reinforcement-learning modules across model backbones. Our results show that agent performance is governed by scaffold compatibility and interaction effects rather than isolated module strength. In particular, structured multi-granularity memory improves long-horizon state tracking, reasoning and memory interact non-uniformly across environments, reflection trades off correction and cost, and RL-trained policies compose best when optimized with deployment-time scaffold structure. AgentSpec provides a controlled foundation for studying, comparing, and designing composable LLM agents. Our code, baselines and interactive playground are publicly available at https://agentspec-embodied.github.io.

SIGA: Self-Evolving Coding-Agent Adapters for Scientific Simulation

Advanced scientific simulators expose specialized input languages that turn simulation goals into executable configurations, but learning them can cost domain scientists hours to days. We study simulator setup as a problem of agent-tool interface grounding: what minimal simulator-specific adaptations are needed for an off-the-shelf coding agent to operate real scientific software? Our intuition is that coding agents already know how to navigate files, edit code, run commands, and repair outputs, but they lack the simulator's executable contract: its vocabulary, structural constraints, validation rules, and termination conditions. We introduce SIGA, a Simulator-Interface Grounding Adapter that supplies this contract through retrieval, procedural memory, in-trajectory validation, and validation-enforced termination. We primarily evaluate SIGA on GEOS, an open-source multiphysics simulator used in subsurface science. SIGA produces a complete GEOS deck in about five minutes with TreeSim above 0.90, matching an extended-budget human expert who took about three hours, a roughly 36x wall-clock speedup. On a harder held-out set, grounding raises TreeSim from 0.720 to 0.789, a roughly 10% relative gain over the bare agent, and can reduce the across-seed standard deviation by 16x. Self-evolution further improves SIGA by rewriting adapter contents from prior trajectories, yielding the highest held-out GEOS mean and matching or outperforming the strongest hand-designed configuration. Transfers to OpenFOAM and LAMMPS show that the dominant mechanism shifts by interface: validation matters most when structural completeness is the bottleneck, while memory and retrieval matter most when domain correctness is the bottleneck. These results suggest that lightweight, self-improvable grounding layers can turn general coding agents into practical operators of scientific software.

Latent Reasoning with Normalizing Flows

Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation. However, textual CoT forces this computation through a discrete, serial, and communication-oriented token stream: each reasoning step must be verbalized before the model can proceed, even when the underlying update is semantic, uncertain, or only partially formed. Latent reasoning offers a higher-bandwidth alternative by performing intermediate computation in compact continuous states before committing to text. Yet existing latent-reasoning methods often sacrifice key advantages that make CoT effective in autoregressive language models, including native left-to-right generation, probabilistic sampling, compatibility with KV-cache decoding, and tractable likelihood estimation. We propose NF-CoT, a latent reasoning framework that preserves these advantages by modeling continuous thoughts with normalizing flows. NF-CoT instantiates a TARFlow-style normalizing flow inside the LLM backbone, defining a tractable probability model over compact continuous thoughts distilled from explicit CoT. Continuous-thought positions are generated by an NF head, while text positions are generated by the standard LM head within the same causal stream. This design provides exact likelihoods for latent thoughts, enables probabilistic left-to-right decoding with the original KV cache, and supports direct policy-gradient optimization in the latent reasoning space. On code-generation benchmarks, NF-CoT improves pass rates over explicit-CoT and prior latent-reasoning baselines while substantially reducing intermediate-reasoning cost.

SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning

LLM/VLM-based digital agents have advanced rapidly thanks to scalable sandboxes for coding, web navigation, and computer use, which provide rich interactive training grounds. In contrast, embodied agents still lack abundant, diverse, and automatically generated 3D environments for interactive learning. Existing embodied simulators rely on manually crafted scenes or procedural templates, while recent LLM-based 3D generation systems mainly produce static scenes rather than deployable environments with verifiable tasks and standard learning interfaces. We introduce SimWorld Studio, an open-source platform built on Unreal Engine 5 for generating evolving embodied learning environments. At its core is SimCoder, a tool/skill-augmented coding agent that writes and executes engine-level code to construct physically grounded 3D worlds from language/image instructions. SimCoder self-evolves by using verifier feedback (e.g., compilation errors, physics checks, VLM critiques) to revise environments and autonomously add reusable tools and skills to its library. Generated worlds are exported as Gym-style environments for embodied agent learning. SimWorld Studio further enables co-evolution between environment generation and embodied learning: agent performance feedback guides SimCoder to generate adaptive curricula near the learner's capability frontier, so that environments become increasingly challenging as the embodied agent improves. Three case studies on embodied navigation show that self-evolution improves generation reliability, generated environments substantially improve embodied agent performance that generalizes to unseen benchmarks, and co-evolution yields an 18-point success-rate gain over fixed-environment learning and a 40-point gain over an untrained agent.

CocoaBench: Evaluating Unified Digital Agents in the Wild

LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly integrating these capabilities into unified systems. Yet, most evaluations still test these capabilities in isolation, which leaves a gap for more diverse use cases that require agents to combine different capabilities. We introduce CocoaBench, a benchmark for unified digital agents built from human-designed, long-horizon tasks that require flexible composition of vision, search, and coding. Tasks are specified only by an instruction and an automatic evaluation function over the final output, enabling reliable and scalable evaluation across diverse agent infrastructures. We also present CocoaAgent, a lightweight shared scaffold for controlled comparison across model backbones. Experiments show that current agents remain far from reliable on CocoaBench, with the best evaluated system achieving only 45.1% success rate. Our analysis further points to substantial room for improvement in reasoning and planning, tool use and execution, and visual grounding.

Beyond Mode Elicitation: Diversity-Preserving Reinforcement Learning via Latent Diffusion Reasoner

Recent reinforcement learning (RL) methods improve LLM reasoning by optimizing discrete Chain-of-Thought (CoT) generation; however, exploration in token space often suffers from diversity collapse as policy entropy decreases due to mode elicitation behavior in discrete RL. To mitigate this issue, we propose Latent Diffusion Reasoning with Reinforcement Learning (LaDi-RL), a framework that conducts exploration directly in a continuous latent space, where latent variables encode semantic-level reasoning trajectories. By modeling exploration via guided diffusion, multi-step denoising distributes stochasticity and preserves multiple coexisting solution modes without mutual suppression. Furthermore, by decoupling latent-space exploration from text-space generation, we show that latent diffusion-based optimization is more effective than text-space policy optimization alone, while a complementary text policy provides additional gains when combined with latent exploration. Experiments on code generation and mathematical reasoning benchmarks demonstrate consistent improvements in both pass@1 and pass@k over discrete RL baselines, with absolute pass@1 gains of +9.4% on code generation and +5.7% on mathematical reasoning, highlighting diffusion-based latent RL as a principled alternative to discrete token-level RL for reasoning.

COLT: Lightweight Multi-LLM Collaboration through Shared MCTS Reasoning for Model Compilation

Model serving costs dominate AI systems, making compiler optimization essential for scalable deployment. Recent works show that a large language model (LLM) can guide compiler search by reasoning over program structure and optimization history. However, using a single large model throughout the search is expensive, while smaller models are less reliable when used alone. Thus, this paper seeks to answer whether multi-LLM collaborative reasoning relying primarily on small LLMs can match or exceed the performance of a single large model. As such, we propose a lightweight collaborative multi-LLM framework, dubbed COLT, for compiler optimization that enables coordinated reasoning across multiple models within a single Monte Carlo tree search (MCTS) process. A key contribution is the use of a single shared MCTS tree as the collaboration substrate across LLMs, enabling the reuse of transformation prefixes and cross-model value propagation. Hence, we circumvent both heavy internal reasoning mechanisms and conventional agentic machinery that relies on external planners, multiple concurrent LLMs, databases, external memory/versioning of intermediate results, and controllers by simply endogenizing model selection within the lightweight MCTS optimization loop. Every iteration, the acting LLM proposes a joint action: (compiler transformation, model to be queried next). We also introduce a model-aware tree policy that biases search toward smaller models while preserving exploration, and a course-alteration mechanism that escalates to the largest model when the search exhibits persistent regressions attributable to smaller models.

TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models

Time series data is ubiquitous in real-world scenarios and crucial for critical applications ranging from energy management to traffic control. Consequently, the ability to reason over time series is a fundamental skill for generalist models to solve practical problems. However, this dimension is notably absent from existing benchmarks of generalist models. To bridge this gap, we introduce TSRBench, a comprehensive multi-modal benchmark designed to stress-test the full spectrum of time series reasoning capabilities. TSRBench features: i) a diverse set of 4125 problems from 14 domains, and is categorized into 4 major dimensions: Perception, Reasoning, Prediction, and Decision-Making. ii) 15 tasks from the 4 dimensions evaluating essential reasoning capabilities (e.g., numerical reasoning). Through extensive experiments, we evaluated over 30 leading proprietary and open-source LLMs, VLMs, and TSLLMs within TSRBench. Our findings reveal that: i) scaling laws hold for perception and reasoning but break down for prediction; ii) strong reasoning does not guarantee accurate context-aware forecasting, indicating a decoupling between semantic understanding and numerical prediction; and iii) despite the complementary nature of textual and visual represenations of time series as inputs, current multimodal models fail to effectively fuse them for reciprocal performance gains. TSRBench provides a standardized evaluation platform that not only highlights existing challenges but also offers valuable insights to advance generalist models. Our code and dataset are available at https://tsrbench.github.io/.

PrivacyReasoner: Can LLM Emulate a Human-like Privacy Mind?

This paper introduces PRA, an AI-agent design for simulating how individual users form privacy concerns in response to real-world news. Moving beyond population-level sentiment analysis, PRA integrates privacy and cognitive theories to simulate user-specific privacy reasoning grounded in personal comment histories and contextual cues. The agent reconstructs each user's "privacy mind", dynamically activates relevant privacy memory through a contextual filter that emulates bounded rationality, and generates synthetic comments reflecting how that user would likely respond to new privacy scenarios. A complementary LLM-as-a-Judge evaluator, calibrated against an established privacy concern taxonomy, quantifies the faithfulness of generated reasoning. Experiments on real-world Hacker News discussions show that \PRA outperforms baseline agents in privacy concern prediction and captures transferable reasoning patterns across domains including AI, e-commerce, and healthcare.

ToolGym: an Open-world Tool-using Environment for Scalable Agent Testing and Data Curation

Tool-using LLM agents still struggle in open-world settings with large tool pools, long-horizon objectives, wild constraints, and unreliable tool states. For scalable and realistic training and testing, we introduce an open-world tool-using environment, built on 5,571 format unified tools across 204 commonly used apps. It includes a task creation engine that synthesizes long-horizon, multi-tool workflows with wild constraints, and a state controller that injects interruptions and failures to stress-test robustness. On top of this environment, we develop a tool select-then-execute agent framework with a planner-actor decomposition to separate deliberate reasoning and self-correction from step-wise execution. Comprehensive evaluation of state-of-the-art LLMs reveals the misalignment between tool planning and execution abilities, the constraint following weakness of existing LLMs, and DeepSeek-v3.2's strongest robustness. Finally, we collect 1,170 trajectories from our environment to fine-tune LLMs, achieving superior performance to baselines using 119k samples, indicating the environment's value as both a realistic benchmark and a data engine for tool-using agents. Our code and data will be publicly released.