Existing text-guided image editing methods primarily rely on end-to-end pixel-level inpainting paradigm. Despite its success in simple scenarios, this paradigm still significantly struggles with compositional editing tasks that require precise local control and complex multi-object spatial reasoning. This paradigm is severely limited by 1) the implicit coupling of planning and execution, 2) the lack of object-level control granularity, and 3) the reliance on unstructured, pixel-centric modeling. To address these limitations, we propose I2E, a novel "Decompose-then-Action” paradigm that revisits image editing as an actionable interaction process within a structured environment. I2E utilizes a Decomposer to transform unstructured images into discrete, manipulable object layers and then introduces a physics-aware Vision-Language-Action Agent to parse complex instructions into a series of atomic actions via Chain-of-Thought reasoning. Further, we also construct I2E-Bench, a benchmark designed for multi-instance spatial reasoning and high-precision editing. Experimental results on I2E-Bench and multiple public benchmarks demonstrate that I2E significantly outperforms state-of-the-art methods in handling complex compositional instructions, maintaining physical plausibility, and ensuring multi-turn editing stability.
论文检索
输入标题、作者或关键词，从 3,752 篇学术成果中精准定位
Mobile GUI agents powered by LMMs can perceive screens and follow instructions, yet existing benchmarks largely target short, linear workflows and step-level accuracy, offering limited insight into long-horizon planning and decision-making under branching structures. We present DAC-Bench, a decision-aware benchmark with compositional tasks comprising 830 episodes and 11,345 action steps across 35 applications on Android and iOS. Tasks are organized into Sequential, Conjunctive, Conditional, and Hierarchical structures, reflecting real-world multi-step and branching interaction patterns. To complement standard step-level evaluation, we introduce weighted longest common subsequence to capture length-sensitive progress and decision accuracy for branch correctness. Evaluations across 7 diverse agents show substantial performance degradation compared to prior benchmarks, with success rates dropping below 5% on 6–8 step tasks and branch accuracy averaging 38%, highlighting challenges in conditional decision-making. By exposing these failure modes, DAC-Bench provides a challenging and diagnostic benchmark for advancing decision-aware mobile GUI agents. Our code and dataset are available at: https://github.com/YuqingZhangMirror12/DAC-Bench.
Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic evaluations. However, most existing benchmarks evaluate agents in simplified, idealized settings. They typically rely on pre-packaged tool interfaces, overlook critical steps, and assume inputs are clean and fully specified. Consequently, they understate the difficulty of real deployments, where uncertainty and noise are ubiquitous and agents must proactively explore the environment to uncover new tools. To bridge this gap, we present AgentGym2, a new evaluation framework with task instances grounded in real-world end-to-end working demands. Beyond reasoning and planning, it measures agents’ ability to execute end-to-end procedures, discover tools via exploration, compose tools for unseen tasks, and remain robust to noisy and underspecified information. Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2, revealing a substantial gap between the capability of current agents and the demands of real-world applications.
Large language models (LLMs) are post-trained through reinforcement learning (RL) to evolve into Reasoning Language Models (RLMs), where the hallmark of this advanced reasoning is “aha” moments when they start to perform strategies, such as self-reflection and deep thinking, within chain of thoughts (CoTs). Motivated by this, this paper proposes a novel reinforced strategy injection mechanism (rSIM), that enables any LLM to become an RLM by employing a small planner to guide the LLM’s CoT through the adaptive injection of reasoning strategies. To achieve this, the planner (leader agent) is jointly trained with an LLM (follower agent) using multi-agent RL (MARL), based on a leader-follower framework and straightforward rule-based rewards. Experimental results show that rSIM enables Qwen2.5-0.5B to become an RLM and significantly outperform Qwen2.5-14B across mathematical, coding, and financial reasoning tasks. Moreover, the planner is generalizable: it only needs to be trained once and can be applied as a plug-in to substantially improve the reasoning capabilities of existing LLMs. In addition, the planner supports continual learning across various tasks, allowing its planning abilities to gradually improve and generalize to a wider range of problems. Our source code is available under the examples/rSIM of https://github.com/AgenticFinLab/eparl.
The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check
PDF ↗The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive backbones, promising to break the sequential latency bottleneck. **However, does such efficiency gains translate into effective agentic behavior?** In this work, we present a comprehensive evaluation of dLLMs (e.g., LLaDA, Dream) across two distinct agentic paradigms: Embodied Agents (requiring long-horizon planning) and Tool-Calling Agents (requiring precise formatting).Contrary to the efficiency hype, our results on Agentboard and BFCL reveal a "**bitter lesson**": current dLLMs fail to serve as reliable agentic backbones, frequently leading to systematically failure. **(1) In Embodied settings**, dLLMs suffer repeated attempts, failing to branch under temporal feedback. **(2) In Tool-Calling settings**, dLLMs fail to maintain symbolic precision (e.g. strict JSON schemas) under diffusion noise. To assess the potential of dLLMs in agentic workflows, we introduce **DiffuAgent**, a multi-agent evaluation framework that integrates dLLMs as plug-and-play cognitive cores. Our analysis shows that dLLMs are effective in non-causal roles (e.g., memory summarization and tool selection) but require the incorporation of causal, precise, and logically grounded reasoning mechanisms into the denoising process to be viable for agentic tasks.
Large language models struggle with reasoning over long contexts where relevant information is sparsely distributed. Although plan-and-execute frameworks mitigate this by decomposing tasks into planning and execution, their effectiveness is often limited by unreliable plan generation due to dependence on surface-level cues. Consequently, plans may be based on incorrect assumptions, and once a plan is formed, identifying errors and revising it reliably becomes difficult, limiting the effectiveness of reactive refinement. To address this limitation, we propose PPA-Plan, a proactive planning strategy for long-context reasoning that focuses on preventing such failures before plan generation. PPA-Plan identifies potential logical pitfalls and false assumptions, formulates them as negative constraints, and conditions plan generation on explicitly avoiding these constraints. Experiments on long-context QA benchmarks show that executing plans generated by PPA-Plan consistently outperforms existing plan-and-execute methods and direct prompting.
Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constraints. Existing large language model (LLM) approaches face fundamental limitations in this domain. Pure reasoning paradigms, which rely on long natural language chains, are prone to inconsistency, error accumulation, and prohibitive cost as constraints compound. Conversely, LLMs combined with coding- or solver-based strategies lack flexibility: they often generate problem-specific code from scratch or depend on fixed solvers, failing to capture generalizable logic across diverse problems.To alleviate these issues, we introduce the Scalable Code Planning Engine (SCOPE), a systematic framework that disentangles query-specific problem reasoning from generic code execution. SCOPE first transforms input queries into optimized structured representations, capturing the interdependent constraints, and then autonomously generates reusable solver functions (Combination, Filter, and Deliver) that provide consistent and reliable execution across diverse problems. SCOPE achieves state-of-the-art performance while lowering cost and latency. For example, with GPT-4o, it reaches 93.1% success on TravelPlanner, a 61.6% gain over the best baseline (CoT) while cutting inference cost by 1.4 times and time by approximately 4.67 times. Code is available at https://github.com/DerrickGXD/SCOPE.
Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address complex issues through planning and research cycles, existing frameworks are deficient in sufficient evaluation procedures and stage-specific protections. They typically treat evaluation as exact match accuracy of question-answering, but overlook crucial aspects of report quality such as credibility, coherence, breadth, depth, and safety. This oversight may result in hazardous or malicious sources being integrated into the final report. To address this, we introduce DeepResearchGuard, a framework featuring four-stage safeguards with open-domain evaluation, and DRSafeBench, a novel stage-wise safety benchmark. Evaluating across GPT-4o, o4-mini, Gemini-2.5-flash, DeepSeek-v3, and GPT-5, DeepResearchGuard improves defense success rates by an absolute 16.53% while reducing over-refusal rates to approximately 6%. Through extensive experiments, we show that DeepResearchGuard enables comprehensive open-domain evaluation and stage-aware defenses that effectively block harmful content propagation, while systematically improving report quality without excessive over-refusal rates.
To close the gap between LLM-based agents and humans in planning and reasoning, agents need large-scale, diverse environments for continuous learning—yet building such environments is itself prohibitively expensive. We present C-World, an environment creation system that enables users to build agent environments on demand. We define a complete agent environment through four components: an Action Space of 5,571 format-unified tools across 204 common applications, a Task Distribution engine that synthesizes long-horizon workflows with wild constraints, a Transition Function implemented as a state controller that injects realistic failures and perturbations, and a Reward Signal combining verifiable metrics with LLM-based judgment. C-World operates in two modes: a realistic mode grounded in live API execution, and a synthesized mode powered by the World Engine, which approximates tool behavior without live service access, enabling scalable environment creation—including environments for domains and tools that do not yet exist in the real world. Evaluation of nine state-of-the-art LLMs reveals that planning ability is uniformly strong but execution remains the bottleneck, and that constraint following—not tool invocation—is the dominant failure mode. The World Engine achieves Spearman \rho = 0.883 ranking correlation with real execution, and fine-tuning on just 1,170 C-World trajectories outperforms baselines trained on 119k samples, demonstrating C-World’s dual value as a rigorous evaluation environment and a scalable data engine. Our code and data are available at https://ziqiao-git.github.io/C-World/.
How do Role Models Shape Collective Morality? Exemplar-Driven Moral Learning in Multi-Agent Simulation
PDF ↗We investigate how role models shape collective morality. To explore this, we build a multi-agent simulation powered by a Large Language Models (LLMs), where agents with diverse intrinsic drives, ranging from cooperative to competitive, interact and adapt through a four-stage cognitive loop (plan-act-observe-reflect). We design four experimental games (Alignment, Collapse, Conflict, and Construction) and conduct motivational ablation studies to identify the key drivers of imitation. The results indicate that identity-driven conformity can substantially reshape the initial dispositions. Agents tend to adapt their values to align with a perceived successful exemplar, leading to rapid value convergence.
Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. In these irreversible environments, probabilistic hallucinations are not merely incorrect; they can cause equipment damage or experimental failure. To address this, we propose BioProAgent, a neuro-symbolic framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM). We introduce a State-Augmented Planning mechanism that enforces a rigorous Design-Verify-Rectify workflow, ensuring hardware compliance before execution. Furthermore, we address the context bottleneck inherent in complex device schemas by Semantic Symbol Grounding, reducing token consumption by \sim6\times through symbolic abstraction. In the extended BioProBench benchmark, BioProAgent achieves 95.6% physical compliance (compared to 21.0% for ReAct), demonstrating that neuro-symbolic constraints are essential for reliable autonomy in irreversible physical environments. Code at https://github.com/YuyangSunshine/bioproagent and Website at https://yuyangsunshine.github.io/BioPro-Project/ .
GCA Framework: A GCC Countries–Grounded Dataset and Agentic Pipeline for Climate Decision Support
PDF ↗Climate decision-making in the GCC states increasingly demands systems that can translate heterogeneous scientific and policy evidence into actionable guidance, yet general-purpose large language models (LLMs) remain weak both in region-specific climate knowledge and grounded interaction with geospatial and forecasting tools. We present the GCA framework, which unifies (i) GCA-DS, a curated multimodal dataset grounded in the GCC states, and (ii) Gulf Climate Agent (GCA), a tool-augmented agent for climate analysis. GCA-DS comprises nearly 200k question-answer pairs spanning governmental policies and adaptation plans, NGO and international frameworks, academic literature, and event-driven reporting on heatwaves, dust storms, and floods, complemented with remote-sensing inputs that couple imagery with textual evidence. Building on this foundation, the GCA agent orchestrates a modular tool pipeline grounded in real-time and historical signals and geospatial processing that produces derived indices and interpretable visualizations. Finally, we benchmark open and proprietary LLMs on climate tasks in the GCC states and show that domain fine-tuning and tool integration substantially improve reliability over general-purpose baselines.
Can generative agents be trusted in multimodal environments? Despite recent advances, agents remain limited in their ability to reason about safety, coherence, and trust across modalities. We introduce a reproducible simulation framework to evaluate generative agents in three aspects: (1) safety improvement over time via iterative plan revision in multimodal scenarios; (2) detection of unsafe activities across social contexts; and (3) social dynamics, measured through interaction and acceptance rates. These multimodal agents are evaluated using metrics that quantify plan revisions and unsafe-to-safe conversions. Experiments show that while agents detect direct multimodal contradictions, they often fail to align local revisions with global safety, achieving only a 55% success rate in correcting unsafe plans. We release a dataset of 1,000 multimodal plans, yielding more than 600,000 simulation steps. Notably, 45% of unsafe actions are accepted when paired with misleading visual cues, revealing a strong tendency to overtrust visual content. Code is available at https://github.com/AdonaiVera/X-CASE
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
PDF ↗Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains, where the agent must continuously interact with environments and process observation-action interleaved trajectories, remains largely unexplored. We present Embodied-Reasoner, a reasoning model for interactive embodied tasks. Unlike mathematical reasoning that relies primarily on logical deduction, embodied scenarios demand spatial understanding, temporal reasoning, and ongoing self-reflection based on interaction history. To address these challenges, we synthesize 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes (analysis, spatial reasoning, reflection, planning, and verification). We develop a three-stage training recipe that progressively enhances the model’s capabilities through imitation learning, rejection sampling tuning on self-exploration trajectories, and reflection tuning. The evaluation shows that our model significantly outperforms advanced visual reasoning models, e.g., exceeds OpenAI o1, o3-mini, and Claude-3.7 by +9%, 24%, and +13%. Analysis reveals that our model exhibits fewer repeated searches and logical inconsistencies, with particular advantages in complex long-horizon tasks. Real-world testing further validates the effectiveness of our approach.
Recent agentic search frameworks enable deep research via iterative planning and retrieval, reducing hallucinations and enhancing factual grounding. However, they remain text-centric, overlooking the multimodal evidence that characterizes real-world expert reports. We introduce a pressing task: multimodal long-form generation. Accordingly, we propose Deep-Reporter, a unified agentic framework for grounded multimodal long-form generation. It orchestrates: (i) Agentic Multimodal Search and Filtering to retrieve and filter textual passages and information-dense visuals; (ii) Checklist-Guided Incremental Synthesis to ensure coherent image-text integration and optimal citation placement; and (iii) Recurrent Context Management to balance long-range coherence with local fluency. We develop a rigorous curation pipeline producing 8K high-quality agentic traces for model optimization. We further introduce M^2LongBench, a comprehensive testbed comprising 247 research tasks across 9 domains and a stable multimodal sandbox. It enables unified multimodal assessment, fair comparison, and accessible evaluation without commercial APIs. Extensive experiments demonstrate that long-form multimodal generation is a challenging task, especially in multimodal selection and integration, and effective post-training can bridge the gap. Our code is available at https://github.com/fangda-ye/Deep-Report.
Proactive dialogue has emerged as a critical and challenging research problem in advancing large language models (LLMs). Existing works predominantly focus on domain-specific or task-oriented scenarios, which leads to fragmented evaluations and limits the comprehensive exploration of models’ proactive dialogue abilities. In this work, we propose ProactiveEval, a unified framework for evaluating proactive dialogue capabilities of LLMs. This framework decomposes proactive dialogue into target planning and dialogue guidance, establishing evaluation metrics across various domains. Moreover, it also enables the automatic generation of diverse and challenging evaluation data. Based on the proposed framework, we develop 328 evaluation environments spanning 6 distinct domains. Through experiments with 22 different types of LLMs, we show that DeepSeek-R1 and Claude-3.7-Sonnet exhibit exceptional performance on target planning and dialogue guidance tasks, respectively. Finally, we investigate how reasoning capabilities influence proactive behaviors and discuss their implications for future model development. Our code and data are available at the https://github.com/liutj9/ProactiveEval.
Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed *LongTVQA* and *LongTVQA+* which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent.
The evaluation of navigation instructions remains a persistent challenge in Vision-and-Language Navigation (VLN) research. Traditional reference-based metrics such as BLEU and ROUGE fail to capture the functional utility of spatial directives, specifically whether an instruction successfully guides a navigator to the intended destination. Although existing VLN agents could serve as evaluators, their reliance on high-fidelity visual simulators introduces licensing constraints and computational costs, and perception errors further confound linguistic quality assessment. This paper introduces GROKE (Graph-based Reasoning over OSM Knowledge for instruction Evaluation), a vision-free training-free hierarchical LLM-based framework for evaluating navigation instructions using OpenStreetMap data. Through systematic ablation studies, we demonstrate that structured JSON and textual formats for spatial information substantially outperform grid-based and visual graph representations. Our hierarchical architecture combines sub-instruction planning with topological graph navigation, reducing navigation error by 68.5% compared to heuristic and sampling baselines on the Map2Seq dataset. The agent’s execution success, trajectory fidelity, and decision patterns serve as proxy metrics for functional navigability given OSM-visible landmarks and topology, establishing a scalable and interpretable evaluation paradigm without visual dependencies.
Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and verbal goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle in interactive environments. Reinforcement learning (RL) offers a natural way to address this limitation, yet online RL approaches suffer from costly interaction and sparse rewards in embodied settings. This paper introduces ORBIT, an On-policy Reinforcement fine-tuning (RFT) framework with offline rewards for EmBodIed Task Planning, that preserves the generalization benefits of RFT while addressing the challenges of costly interaction and sparse rewards, supported by solid theoretical guarantees. Our approach is evaluated on EmbodiedBench, a recent benchmark for interactive embodied tasks, covering both in-domain and out-of-domain scenarios. Experimental results show that ORBIT achieves SOTA performance on EB-ALFRED, outperforming all closed-source and online-RL-based methods, while being substantially more efficient in training speed and computational cost, remaining robust to sub-optimal expert trajectories, and exhibiting strong generalization to unseen environments. We released all code and data at https://github.com/mail-taii/Reinforced-Reasoning-for-Embodied-Planning.
Psychiatric interviewing is a strategic, goal-oriented interaction that requires proactively steering the conversation to elicit latent information. However, existing methods often degenerate into rigid interrogation or aimless chitchat due to a lack of strategic planning. In this work, we introduce S4, a comprehensive framework grounded in Speech Act Theory, modeling the interview as a unified process of internal strategy (Illocution and Perlocution) and external realization (Locution). We synthesize a large-scale dataset with fine-grained psychiatric speech act annotations. Trained on this data, S4Dial employs reinforcement learning driven by long-term therapeutic effects to optimize the strategic chaining of atomic acts, aiming to maximally elicit information and maintain patient engagement. Experiments demonstrate that S4 significantly outperforms baselines, validating the effectiveness of our effect-driven strategic modeling.