The rise of Large Language Models (LLMs) is reshaping multimodel models, with speech synthesis being a prominent application. However, existing approaches often underutilize the linguistic intelligence of these models, typically failing to leverage their powerful instruction-following capabilities. This limitation hinders the model's ability to follow text instructions for controllable Text-to-Speech~(TTS). To address this, we propose a new paradigm inspired by ``operationalism'' that decouples instruction understanding from speech generation. We introduce BatonVoice, a framework where an LLM acts as a ``conductor'', understanding user instructions and generating a textual ``plan'' -- explicit vocal features (e.g., pitch, energy). A separate TTS model, the ``orchestra'', then generates the speech from these features. To realize this component, we develop BatonTTS, a TTS model trained specifically for this task. Our experiments demonstrate that BatonVoice achieves strong performance in controllable and emotional speech synthesis, outperforming strong open- and closed-source baselines. Notably, our approach enables remarkable zero-shot cross-lingual generalization, accurately applying feature control abilities to languages unseen during post-training. This demonstrates that objectifying speech into textual vocal features can more effectively unlock the linguistic intelligence of LLMs.
Controllable summarization moves beyond generic outputs toward human-aligned summaries guided by specified attributes. In practice, the interdependence among attributes makes it challenging for language models to satisfy correlated constraints consistently. Moreover, previous approaches often require per-attribute fine-tuning, limiting flexibility across diverse summary attributes. In this paper, we propose adaptive planning for multi-attribute controllable summarization (PACO), a training-free framework that reframes the task as planning the order of sequential attribute control with a customized Monte Carlo Tree Search (MCTS). In PACO, nodes represent summaries, and actions correspond to single-attribute adjustments, enabling progressive refinement of only the attributes requiring further control. This strategy adaptively discovers optimal control orders, ultimately producing summaries that effectively meet all constraints. Extensive experiments across diverse domains and models demonstrate that PACO achieves robust multi-attribute controllability, surpassing both LLM-based self-planning models and fine-tuned baselines. Remarkably, PACO with Llama-3.2-1B rivals the controllability of the much larger Llama-3.3-70B baselines. With larger models, PACO achieves superior control performance, outperforming all competitors.
Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucinations and expose reasoning traces. However, many KG-RAG systems compose multiple LLM modules (e.g planning, reasoning, and responding), inflating inference cost and binding behavior to a specific target KG. To address this, we introduce KG-R1, an agentic KG retrieval-augmented generation (KG-RAG) framework through reinforcement learning (RL). KG-R1 utilizes a single agent that interacts with KGs as its environment, learning to retrieve at each step and incorporating the retrieved information into its reasoning and generation. The process is optimized through end-to-end RL. In controlled experiments across Knowledge-Graph Question Answering (KGQA) benchmarks, our method demonstrates both efficiency and transferability: Using Qwen-2.5-3B, KG-R1 improves answer accuracy with fewer generation tokens than prior multi-module workflow methods that use larger foundation or fine-tuned models. Furthermore, KG-R1 enables plug and play: after training, it maintains strong accuracy on new KGs without modification. These properties make KG-R1 a promising KG-RAG framework for real-world deployment. Our code is publicly available at https://github.com/Jinyeop3110/KG-R1.
Embodied task planning requires agents to produce executable actions in a close-loop manner within the environment. With progressively improving capabilities of LLMs in task decomposition, planning, and generalization, current embodied task planning methods adopt LLM-based architecture.However, existing LLM-based planners remain limited in three aspects, i.e., fixed planning paradigms, lack of action sequence constraints, and error-agnostic. In this work, we propose SDA-PLANNER, enabling an adaptive planning paradigm, state-dependency aware and error-aware mechanisms for comprehensive embodied task planning. Specifically, SDA-PLANNER introduces a State-Dependency Graph to explicitly model action preconditions and effects, guiding the dynamic revision. To handle execution error, it employs an error-adaptive replanning strategy consisting of Error Backtrack and Diagnosis and Adaptive Action SubTree Generation, which locally reconstructs the affected portion of the plan based on the current environment state. Experiments demonstrate that SDA-PLANNER consistently outperforms baselines in success rate and goal completion, particularly under diverse error conditions.
The growing demand for real-time, safety-critical systems has significantly increased both the adoption and complexity of Time Sensitive Networking (TSN). Configuring an optimized TSN network is highly challenging, requiring careful planning, design, verification, validation, and deployment. Large Language Models (LLMs) have recently demonstrated strong capabilities in solving complex tasks, positioning them as promising candidates for automating end-to-end TSN deployment, referred to as TSN orchestration. This paper outlines the steps involved in TSN orchestration and the associated challenges. To assess the capabilities of existing LLM models, we conduct an initial proof-of-concept case study focused on TSN configuration across multiple models. Building on these insights, we propose an LLM-assisted orchestration framework. Unlike prior research on LLMs in computer networks, which has concentrated on general configuration and management, TSN-specific orchestration has not yet been investigated. We present the building blocks for automating TSN using LLMs, describe the proposed pipeline, and analyze opportunities and limitations for real-world deployment. Finally, we highlight key challenges and research directions, including the development of TSN-focused datasets, standardized benchmark suites, and the integration of external tools such as Network Calculus (NC) engines and simulators. This work provides the first roadmap toward assessing the feasibility of LLM-assisted TSN orchestration.
Long-horizon embodied planning is challenging because the world does not only change through an agent's actions: exogenous processes (e.g., water heating, dominoes cascading) unfold concurrently with the agent's actions. We propose a framework for abstract world models that jointly learns (i) symbolic state representations and (ii) causal processes for both endogenous actions and exogenous mechanisms. Each causal process models the time course of a stochastic cause-effect relation. We learn these world models from limited data via variational Bayesian inference combined with LLM proposals. Across five simulated tabletop robotics environments, the learned models enable fast planning that generalizes to held-out tasks with more objects and more complex goals, outperforming a range of baselines.
This paper introduces a novel framework for proactive cross-domain resource orchestration in 6G RAN-Edge networks, featuring large language model (LLM)-augmented agents. The system comprises specialized RAN (energy efficiency) and Edge (latency assurance) agents that engage in iterative negotiation, supported by advanced reasoning and planning capabilities. Agents dynamically interact with a digital twin (DT) to test their proposals and leverage a long-term collective memory where their joint successful and failed agreements along with the related network contexts are distilled into strategies to either follow or avoid and subsequently stored. Given that agents are subject to a plethora of cognitive distortions when retrieving those past experiences -- such as primacy, recency, confirmation and availability biases -- we propose in this work a novel unbiased memory design (A reusable mockup version of the unbiased memory source code is available for non-commercial use at https://github.com/HatimChergui/unbiased-collective-memory). featuring (i) semantic retrieval of past strategies via Jaccard similarity; (ii) learning from failures through amplified weighting of SLA violations and mandatory inclusion of failed negotiation cases to mitigate confirmation bias; (iii) diversity enforcement to minimize availability bias and (iv) recency and primacy weighting with slow decay to counteract temporal biases. Evaluation results showcase the impact of existing biases and how the unbiased memory allows to tackle them by learning from both successful and failed strategies, either present or old, resulting in $\times 4.5$ and $\times 3.5$ reductions of unresolved negotiations compared to non-memory and vanilla memory baselines, respectively, while totally mitigating SLA violations as well as improving latency and energy saving distributions.
Deploying a large language model (LLM) inference service remains costly because centralized serving depends on specialized GPU clusters and high-bandwidth interconnects in datacenters. An appealing alternative is to leverage collaborative decentralized GPU pools. However, heterogeneity in GPU and limited interconnected network bandwidth, along with potentially dynamic availability, make efficient scheduling the central challenge in this scenario. In this paper, we present Parallax, a decentralized LLM serving system that turns a pool of heterogeneous GPUs into an efficient inference platform via a two-phase scheduler. Parallax decomposes planning into (i) model allocation, which places layers of each replica across diverse GPUs to jointly optimize latency and throughput under memory and link-bandwidth constraints, and (ii) request-time GPU pipeline selection, which stitches layers from different replicas into end-to-end execution chains that balance load and adapt to current conditions. We implement Parallax and evaluate it on open-source LLMs deployed over real volunteer nodes. Parallax consistently reduces latency and increases throughput relative to decentralized baselines, demonstrating that principled scheduling can make volunteer compute a practical, affordable substrate for LLM inference. Github Repo at: https://github.com/GradientHQ/parallax.
Conversational Recommender Systems (CRSs) aim to provide personalized recommendations through multi-turn natural language interactions with users. Given the strong interaction and reasoning skills of Large Language Models (LLMs), leveraging LLMs for CRSs has recently emerged as a promising direction. However, existing LLM-based methods often lack explicit optimization of interaction strategies, instead relying on unified prompts and the LLM's internal knowledge to decide how to interact, which can lead to suboptimal outcomes. In this paper, we propose a novel Reinforced Strategy Optimization (RSO) method for CRS, which decomposes the process of generating strategy-driven response decisions into the macro-level strategy planning and micro-level strategy adaptation through a network-of-experts architecture. At the macro level, a Planner expert selects macro-level interaction strategies (e.g., recommend, explain, encourage). At the micro level, an Actor expert generates detailed responses conditioned on the selected macro-level strategy, guided by auxiliary experts that provide complementary information such as user preferences and factual grounding. This hierarchical decomposition disentangles the optimization of different sub-tasks involved in CRS response generation, enabling more tractable learning at each level. To address the scarcity of high-quality multi-turn training data, we formulate strategy learning as a reinforcement learning problem, guided by an LLM-based reward model to achieve automatic strategy exploration. Extensive experiments show that RSO significantly improves interaction performance compared to state-of-the-art baselines, demonstrating the effectiveness of explicit hierarchical strategy optimization for CRS.
Agent systems based on large language models (LLMs) have shown great potential in complex reasoning tasks, but building efficient and generalizable workflows remains a major challenge. Most existing approaches rely on manually designed processes, which limits their adaptability across different tasks. While a few methods attempt automated workflow generation, they are often tied to specific datasets or query types and make limited use of intermediate feedback, reducing system robustness and reasoning depth. Moreover, their operations are typically predefined and inflexible. To address these limitations, we propose DyFlow, a dynamic workflow generation framework that adaptively constructs and adjusts reasoning procedures based on task requirements and real-time intermediate feedback, thereby enhancing cross-task generalization. DyFlow consists of two core components: a designer and an executor. The designer decomposes complex problems into a sequence of sub-goals defined by high-level objectives and dynamically plans the next steps based on intermediate outputs and feedback. These plans are then carried out by the executor, which executes each operation using dynamic operators with context-aware parameterization, enabling flexible and semantically grounded reasoning. We systematically evaluate DyFlow across diverse domains, including social reasoning, biomedical tasks, mathematical problem solving, and code generation. Results demonstrate that DyFlow significantly outperforms existing baselines, achieving substantial Pass@k improvements and exhibiting robust generalization across diverse domains. The code is publicly available at https://github.com/wyf23187/DyFlow.
Large language models (LLMs) excel at knowledge-intensive question answering and reasoning, yet their real-world deployment remains constrained by knowledge cutoff, hallucination, and limited interaction modalities. Augmenting LLMs with external search tools helps alleviate these issues, but it also exposes agents to a complex search environment in which small, plausible variations in query formulation can steer reasoning into unproductive trajectories and amplify errors. We present a systematic analysis that quantifies how environmental complexity induces fragile search behaviors and, in turn, degrades overall performance. To address this challenge, we propose a simple yet effective approach to instantiate a search agent, RE-Searcher. During search, RE-Searcher explicitly articulates a concrete search goal and subsequently reflects on whether the retrieved evidence satisfies that goal. This combination of goal-oriented planning and self-reflection enables RE-Searcher to resist spurious cues in complex search environments and perform robust search. Extensive experiments show that our method improves search accuracy and achieves state-of-the-art results. Perturbation studies further demonstrate substantial resilience to noisy or misleading external signals, mitigating the fragility of the search process. We believe these findings offer practical guidance for integrating LLM-powered agents into more complex interactive environments and enabling more autonomous decision-making.
Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning stages where hazards may arise: Task Understanding, Environment Perception, High-Level Plan Generation, and Low-Level Action Generation. We further formalize three orthogonal safety constraint types (Factual, Causal, and Temporal) to systematically characterize potential safety violations. Building on this risk model, we present SafeMindBench, a multimodal benchmark with 5,558 samples spanning four task categories (Instr-Risk, Env-Risk, Order-Fix, Req-Align) across high-risk scenarios such as sabotage, harm, privacy, and illegal behavior. Extensive experiments on SafeMindBench reveal that leading LLMs (e.g., GPT-4o) and widely used embodied agents remain susceptible to safety-critical failures. To address this challenge, we introduce SafeMindAgent, a modular Planner-Executor architecture integrated with three cascaded safety modules, which incorporate safety constraints into the reasoning process. Results show that SafeMindAgent significantly improves safety rate over strong baselines while maintaining comparable task completion. Together, SafeMindBench and SafeMindAgent provide both a rigorous evaluation suite and a practical solution that advance the systematic study and mitigation of safety risks in embodied LLM agents.
The success of large language models (LLMs) depends heavily on large-scale, high-quality instruction-following and reinforcement datasets. However, generating such data through human annotation is prohibitively time-consuming particularly for domain-specific tasks like telecom network troubleshooting, where accurate responses require deep technical expertise and contextual understanding. In this paper, we present a fully automated, retrieval-augmented pipeline for generating synthetic question-answer (QA) pairs grounded in structured domain knowledge. Our multi-stage framework integrates a retriever, base generator, and refinement model to synthesize and enhance QA pairs using documents retrieved from a domain-specific knowledge graph. To ensure data quality, we employ customized RAGAS-based scoring to filter low-quality samples, producing a high-quality dataset suitable for reinforcement fine-tuning (RFT). We demonstrate our approach in a real-world telecom scenario focused on radio access network (RAN) troubleshooting. The resulting pipeline generates complex, context-rich troubleshooting solution plans without human intervention. This work offers a scalable solution for building instruction and reinforcement datasets in specialized domains, significantly reducing dependence on manual labeling while maintaining high technical fidelity.
Automated textual description of remote sensing images is crucial for unlocking their full potential in diverse applications, from environmental monitoring to urban planning and disaster management. However, existing studies in remote sensing image captioning primarily focus on the image level, lacking object-level fine-grained interpretation, which prevents the full utilization and transformation of the rich semantic and structural information contained in remote sensing images. To address this limitation, we propose Geo-DLC, a novel task of object-level fine-grained image captioning for remote sensing. To support this task, we construct DE-Dataset, a large-scale dataset contains 25 categories and 261,806 annotated instances with detailed descriptions of object attributes, relationships, and contexts. Furthermore, we introduce DE-Benchmark, a LLM-assisted question-answering based evaluation suite designed to systematically measure model capabilities on the Geo-DLC task. We also present DescribeEarth, a Multi-modal Large Language Model (MLLM) architecture explicitly designed for Geo-DLC, which integrates a scale-adaptive focal strategy and a domain-guided fusion module leveraging remote sensing vision-language model features to encode high-resolution details and remote sensing category priors while maintaining global context. Our DescribeEarth model consistently outperforms state-of-the-art general MLLMs on DE-Benchmark, demonstrating superior factual accuracy, descriptive richness, and grammatical soundness, particularly in capturing intrinsic object features and surrounding environmental attributes across simple, complex, and even out-of-distribution remote sensing scenarios. All data, code and weights are released at https://github.com/earth-insights/DescribeEarth.
Environments built for people are increasingly operated by a new class of economic actors: LLM-powered software agents making decisions on our behalf. These decisions range from our purchases to travel plans to medical treatment selection. Current evaluations of these agents largely focus on task competence, but we argue for a deeper assessment: how these agents choose when faced with realistic decisions. We introduce ABxLab, a framework for systematically probing agentic choice through controlled manipulations of option attributes and persuasive cues. We apply this to a realistic web-based shopping environment, where we vary prices, ratings, and psychological nudges, all of which are factors long known to shape human choice. We find that agent decisions shift predictably and substantially in response, revealing that agents are strongly biased choosers even without being subject to the cognitive constraints that shape human biases. This susceptibility reveals both risk and opportunity: risk, because agentic consumers may inherit and amplify human biases; opportunity, because consumer choice provides a powerful testbed for a behavioral science of AI agents, just as it has for the study of human behavior. We release our framework as an open benchmark for rigorous, scalable evaluation of agent decision-making.
While Large Language Models (LLMs) have shown remarkable advancements in reasoning and tool use, they often fail to generate optimal, grounded solutions under complex constraints. Real-world travel planning exemplifies these challenges, evaluating agents' abilities to handle constraints that are explicit, implicit, and even evolving based on interactions with dynamic environments and user needs. In this paper, we present ATLAS, a general multi-agent framework designed to effectively handle such complex nature of constraints awareness in real-world travel planning tasks. ATLAS introduces a principled approach to address the fundamental challenges of constraint-aware planning through dedicated mechanisms for dynamic constraint management, iterative plan critique, and adaptive interleaved search. ATLAS demonstrates state-of-the-art performance on the TravelPlanner benchmark, improving the final pass rate from 23.3% to 44.4% over its best alternative. More importantly, our work is the first to demonstrate quantitative effectiveness on real-world travel planning tasks with live information search and multi-turn feedback. In this realistic setting, ATLAS showcases its superior overall planning performance, achieving an 84% final pass rate which significantly outperforms baselines including ReAct (59%) and a monolithic agent (27%).
Manual labeling limits the scale, accuracy, and timeliness of patient outcomes research in radiation oncology. We present RadOnc-GPT, an autonomous large language model (LLM)-based agent capable of independently retrieving patient-specific information, iteratively assessing evidence, and returning structured outcomes. Our evaluation explicitly validates RadOnc-GPT across two clearly defined tiers of increasing complexity: (1) a structured quality assurance (QA) tier, assessing the accurate retrieval of demographic and radiotherapy treatment plan details, followed by (2) a complex clinical outcomes labeling tier involving determination of mandibular osteoradionecrosis (ORN) in head-and-neck cancer patients and detection of cancer recurrence in independent prostate and head-and-neck cancer cohorts requiring combined interpretation of structured and unstructured patient data. The QA tier establishes foundational trust in structured-data retrieval, a critical prerequisite for successful complex clinical outcome labeling.
Investigative journalists routinely confront large document collections. Large language models (LLMs) with retrieval-augmented generation (RAG) capabilities promise to accelerate the process of document discovery, but newsroom adoption remains limited due to hallucination risks, verification burden, and data privacy concerns. We present a journalist-centered approach to LLM-powered document search that prioritizes transparency and editorial control through a five-stage pipeline -- corpus summarization, search planning, parallel thread execution, quality evaluation, and synthesis -- using small, locally-deployable language models that preserve data security and maintain complete auditability through explicit citation chains. Evaluating three quantized models (Gemma 3 12B, Qwen 3 14B, and GPT-OSS 20B) on two corpora, we find substantial variation in reliability. All models achieved high citation validity and ran effectively on standard desktop hardware (e.g., 24 GB of memory), demonstrating feasibility for resource-constrained newsrooms. However, systematic challenges emerged, including error propagation through multi-stage synthesis and dramatic performance variation based on training data overlap with corpus content. These findings suggest that effective newsroom AI deployment requires careful model selection and system design, alongside human oversight for maintaining standards of accuracy and accountability.
Large Language Models (LLMs) have achieved significant advances in reasoning tasks. A key approach is tree-based search with verifiers, which expand candidate reasoning paths and use reward models to guide pruning and selection. Although effective in improving accuracy, these methods are not optimal in terms of efficiency: they perform simple decomposition on the reasoning process, but ignore the planning-execution nature of tasks such as math reasoning or code generation. This results in inefficient exploration of reasoning process. To address this, we propose a dual-phase test-time scaling framework that explicitly separates reasoning into planning and execution, and performs search over the two phases individually. Specifically, we decompose reasoning trajectories and develop reward models for each phase, enabling the search to explore and prune plans and executions separately. We further introduce a dynamic budget allocation mechanism that adaptively redistributes sampling effort based on reward feedback, allowing early stopping on confident steps and reallocation of computation to more challenging parts of the reasoning process. Experiments on both mathematical reasoning and code generation benchmarks demonstrate that our approach consistently improves accuracy while reducing redundant computation.
Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading failures, where a single root-cause error propagates through subsequent decisions, leading to task failure. Current systems lack a framework that can comprehensively understand agent error in a modular and systemic way, and therefore fail to detect these errors accordingly. We address this gap with three contributions. First, we introduce the AgentErrorTaxonomy, a modular classification of failure modes spanning memory, reflection, planning, action, and system-level operations. Second, we construct AgentErrorBench, the first dataset of systematically annotated failure trajectories from ALFWorld, GAIA, and WebShop, grounding error analysis in real-world agent rollouts. Third, we propose AgentDebug, a debugging framework that isolates root-cause failures and provides corrective feedback, enabling agents to recover and iteratively improve. Experiments on AgentErrorBench show that AgentDebug achieves 24% higher all-correct accuracy and 17% higher step accuracy compared to the strongest baseline. Beyond detection, the targeted feedback generated by AgentDebug enables LLM agents to iteratively recover from failures, yielding up to 26% relative improvements in task success across ALFWorld, GAIA, and WebShop. These results establish principled debugging as a pathway to more reliable and adaptive LLM agents. The code and data will be available at https://github.com/ulab-uiuc/AgentDebug
The pursuit of artificial agents that can learn to master complex environments has led to remarkable successes, yet prevailing deep reinforcement learning methods often rely on immense experience, encoding their knowledge opaquely within neural network weights. We propose a different paradigm, one in which an agent learns to play by reasoning and planning. We introduce Cogito, ergo ludo (CEL), a novel agent architecture that leverages a Large Language Model (LLM) to build an explicit, language-based understanding of its environment's mechanics and its own strategy. Starting from a tabula rasa state with no prior knowledge (except action set), CEL operates on a cycle of interaction and reflection. After each episode, the agent analyzes its complete trajectory to perform two concurrent learning processes: Rule Induction, where it refines its explicit model of the environment's dynamics, and Strategy and Playbook Summarization, where it distills experiences into an actionable strategic playbook. We evaluate CEL on diverse grid-world tasks (i.e., Minesweeper, Frozen Lake, and Sokoban), and show that the CEL agent successfully learns to master these games by autonomously discovering their rules and developing effective policies from sparse rewards. Ablation studies confirm that the iterative process is critical for sustained learning. Our work demonstrates a path toward more general and interpretable agents that not only act effectively but also build a transparent and improving model of their world through explicit reasoning on raw experience.
Large language models (LLMs) are being increasingly used for planning in orchestrated multi-agent systems. However, existing LLM-based approaches often fall short of human expectations and, critically, lack effective mechanisms for users to inspect, understand, and control their behaviors. These limitations call for enhanced transparency, controllability, and human oversight. To address this, we introduce AIPOM, a system supporting human-in-the-loop planning through conversational and graph-based interfaces. AIPOM enables users to transparently inspect, refine, and collaboratively guide LLM-generated plans, significantly enhancing user control and trust in multi-agent workflows. Our code and demo video are available at https://github.com/megagonlabs/aipom.
Agent memory shapes how Large Language Model (LLM)-powered agents, akin to the human brain, progressively refine themselves through environment interactions. Existing paradigms remain constrained: parametric memory forcibly adjusts model parameters, and retrieval-based memory externalizes experience into structured databases, yet neither captures the fluid interweaving of reasoning and memory that underlies human cognition. To address this gap, we propose MemGen, a dynamic generative memory framework that equips agents with a human-esque cognitive faculty. It consists of a \textit{memory trigger}, which monitors the agent's reasoning state to decide explicit memory invocation, and a \textit{memory weaver}, which takes the agent's current state as stimulus to construct a latent token sequence as machine-native memory to enrich its reasoning. In this way, MemGen enables agents to recall and augment latent memory throughout reasoning, producing a tightly interwoven cycle of memory and cognition. Extensive experiments across eight benchmarks show that MemGen surpasses leading external memory systems such as ExpeL and AWM by up to $38.22\%$, exceeds GRPO by up to $13.44\%$, and exhibits strong cross-domain generalization ability. More importantly, we find that without explicit supervision, MemGen spontaneously evolves distinct human-like memory faculties, including planning memory, procedural memory, and working memory, suggesting an emergent trajectory toward more naturalistic forms of machine cognition.
The paradigm of Next Token Prediction (NTP) has driven the unprecedented success of Large Language Models (LLMs), but is also the source of their most persistent weaknesses such as poor long-term planning, error accumulation, and computational inefficiency. Acknowledging the growing interest in exploring alternatives to NTP, the survey describes the emerging ecosystem of alternatives to NTP. We categorise these approaches into five main families: (1) Multi-Token Prediction, which targets a block of future tokens instead of a single one; (2) Plan-then-Generate, where a global, high-level plan is created upfront to guide token-level decoding; (3) Latent Reasoning, which shifts the autoregressive process itself into a continuous latent space; (4) Continuous Generation Approaches, which replace sequential generation with iterative, parallel refinement through diffusion, flow matching, or energy-based methods; and (5) Non-Transformer Architectures, which sidestep NTP through their inherent model structure. By synthesizing insights across these methods, this survey offers a taxonomy to guide research into models that address the known limitations of token-level generation to develop new transformative models for natural language processing.
Autonomous driving systems increasingly rely on multi-agent architectures powered by large language models (LLMs), where specialized agents collaborate to perceive, reason, and plan. A key component of these systems is the shared function library, a collection of software tools that agents use to process sensor data and navigate complex driving environments. Despite its critical role in agent decision-making, the function library remains an under-explored vulnerability. In this paper, we introduce FuncPoison, a novel poisoning-based attack targeting the function library to manipulate the behavior of LLM-driven multi-agent autonomous systems. FuncPoison exploits two key weaknesses in how agents access the function library: (1) agents rely on text-based instructions to select tools; and (2) these tools are activated using standardized command formats that attackers can replicate. By injecting malicious tools with deceptive instructions, FuncPoison manipulates one agent s decisions--such as misinterpreting road conditions--triggering cascading errors that mislead other agents in the system. We experimentally evaluate FuncPoison on two representative multi-agent autonomous driving systems, demonstrating its ability to significantly degrade trajectory accuracy, flexibly target specific agents to induce coordinated misbehavior, and evade diverse defense mechanisms. Our results reveal that the function library, often considered a simple toolset, can serve as a critical attack surface in LLM-based autonomous driving systems, raising elevated concerns on their reliability.
Existing methods usually leverage a fixed strategy, such as natural language reasoning, code-augmented reasoning, tool-integrated reasoning, or ensemble-based reasoning, to guide Large Language Models (LLMs) to perform mathematical reasoning. Our analysis reveals that the single strategy cannot adapt to problem-specific requirements and thus overlooks the trade-off between effectiveness and efficiency. To address these issues, we propose Planning and Routing through Instance-Specific Modeling (PRISM), a novel framework that decouples mathematical reasoning into two stages: strategy planning and targeted execution. Specifically, we first curate a multi-strategy preference dataset, which we call MathStrat, capturing correctness, process quality, and computational efficiency for each problem--strategy pair. Then, we train a lightweight Strategy Adapter based on the dataset to obtain confidence distributions over the mentioned four reasoning strategies. At inference time, an adaptive routing policy dynamically tailors the reasoning approach based on predictor confidence. It directs the model to use single-strategy execution for high-confidence predictions, dual-strategy verification for competitive scenarios, or comprehensive multi-strategy exploration for uncertain cases. Extensive experiments across five mathematical reasoning benchmarks demonstrate that PRISM consistently outperforms individual strategies and ensemble baselines, achieving improvements ranging from 0.9% to 7.6% across different base models. The adaptive routing approach shows particularly strong benefits for mathematical reasoning tasks across diverse model architectures. Our code is released at https://github.com/reml-group/PRISM.
The exponential technological breakthrough of the FinTech industry has significantly enhanced user engagement through sophisticated advisory chatbots. However, large-scale fine-tuning of LLMs can occasionally yield unprofessional or flippant remarks, such as ``With that money, you're going to change the world,'' which, though factually correct, can be contextually inappropriate and erode user trust. The scarcity of domain-specific datasets has led previous studies to focus on isolated components, such as reasoning-aware frameworks or the enhancement of human-like response generation. To address this research gap, we present Fin-Solution 2.O, an advanced solution that 1) introduces the multi-turn financial conversational dataset, Fin-Vault, and 2) incorporates a unified model, Fin-Ally, which integrates commonsense reasoning, politeness, and human-like conversational dynamics. Fin-Ally is powered by COMET-BART-embedded commonsense context and optimized with a Direct Preference Optimization (DPO) mechanism to generate human-aligned responses. The novel Fin-Vault dataset, consisting of 1,417 annotated multi-turn dialogues, enables Fin-Ally to extend beyond basic account management to provide personalized budgeting, real-time expense tracking, and automated financial planning. Our comprehensive results demonstrate that incorporating commonsense context enables language models to generate more refined, textually precise, and professionally grounded financial guidance, positioning this approach as a next-generation AI solution for the FinTech sector. Dataset and codes are available at: https://github.com/sarmistha-D/Fin-Ally
Recent large language models (LLMs) have shown strong reasoning capabilities. However, a critical question remains: do these models possess genuine reasoning skills particularly complex strategic reasoning or are they primarily excelling at sophisticated pattern recognition within their training data? To address this question, this paper presents a chess testbed, ChessArena, to evaluate the strategic reasoning capabilities of LLMs. Chess requires complex strategic reasoning capabilities including long-term planning, strict rule comprehension, and multi-turn conversation memorization. Specifically, ChessArena is a competitive framework where LLMs play against each other, under four different play modes. The testbed is equipped with a ranking algorithm and a leaderboard. The testbed can also evaluate fine-grained capabilities including basic understanding, move selection, and puzzle solving. Over 13 LLMs with different modes are evaluated in ChessArena, playing over 800 games. The results reveal significant shortcomings in current LLMs: no model can beat Maia-1100 (a chess engine at human amateur level), while some even failed to defeat a random player that selects moves arbitrarily. We also present a strong baseline to the testbed: our fine-tuned Qwen3-8B substantially improved performance, approaching much larger state-of-the-art reasoning models.
Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: declarative methods lack adaptability in dynamic environments, while iterative methods incur prohibitive computational costs that scale poorly with team size and task complexity. In this paper, we propose ELHPlan, a novel framework that introduces Action Chains--sequences of actions explicitly bound to sub-goal intentions--as the fundamental planning primitive. ELHPlan operates via a cyclical process: 1) constructing intention-bound action sequences, 2) proactively validating for conflicts and feasibility, 3) refining issues through targeted mechanisms, and 4) executing validated actions. This design balances adaptability and efficiency by providing sufficient planning horizons while avoiding expensive full re-planning. We further propose comprehensive efficiency metrics, including token consumption and planning time, to more holistically evaluate multi-agent collaboration. Our experiments on benchmark TDW-MAT and C-WAH demonstrate that ELHPlan achieves comparable task success rates while consuming only 24% of the tokens required by state-of-the-art methods. Our research establishes a new efficiency-effectiveness frontier for LLM-based multi-agent planning systems.
Robots trained via Reinforcement Learning (RL) or Imitation Learning (IL) often adapt slowly to new tasks, whereas recent Large Language Models (LLMs) and Vision-Language Models (VLMs) promise knowledge-rich planning from minimal data. Deploying LLMs/VLMs for motion planning, however, faces two key obstacles: (i) symbolic plans are rarely grounded in scene geometry and object physics, and (ii) model outputs can vary for identical prompts, undermining execution reliability. We propose ViReSkill, a framework that pairs vision-grounded replanning with a skill memory for accumulation and reuse. When a failure occurs, the replanner generates a new action sequence conditioned on the current scene, tailored to the observed state. On success, the executed plan is stored as a reusable skill and replayed in future encounters without additional calls to LLMs/VLMs. This feedback loop enables autonomous continual learning: each attempt immediately expands the skill set and stabilizes subsequent executions. We evaluate ViReSkill on simulators such as LIBERO and RLBench as well as on a physical robot. Across all settings, it consistently outperforms conventional baselines in task success rate, demonstrating robust sim-to-real generalization.