Repository exploration is a distinct and costly stage of coding-agent pipelines: before generating a patch, an agent must identify which repository files are likely to matter. We study whether this stage can be delegated to lower-cost models while retaining useful localization quality. Using our IssueLoc-Bench, we evaluate five explorer models under the same read-only interactive interface on 499 SWE-bench Verified-derived tasks and 500 tasks from 153 additional repositories. We measure early candidate discovery, top-three gold-file coverage, strict file-set recovery, agent time, and token usage, with paired instance-level uncertainty and repository-clustered sensitivity analysis. The highest-quality explorer leads across localization metrics, but substantially cheaper operating points emerge: depending on the model and evaluation arm, lower-cost explorers retain approximately 78-94% of the reference Hit@3 and 73-92% of its F1 while reducing mean agent time by 41-88% and token usage by 84-95%. The preferred operating point depends on how localization is consumed downstream: ranking and coverage metrics characterize recoverable candidate handoffs, whereas F1 and exact match characterize restrictive file gates. These results support treating repository exploration as an independently measurable and budgetable stage of modular coding agents, with explorer selection guided by the downstream handoff contract.
Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requires adaptive retrieval and continuous revision of intermediate contexts. Recent reinforcement learning (RL)-based agentic RAG methods partially alleviate this issue, but typically rely on coarse-grained action spaces and trajectory-level rewards, resulting in weak reward assignment and a bias toward short-horizon, stereotyped reasoning template. To address, we propose AgenticRag-R1, a RL framework that deeply integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space, supported by hierarchical action-aware rewards and an information-aware trajectory rejection strategy to enable effective long-horizon learning. Experiments across a diverse set of multi-hop, open-domain, and agentic reasoning benchmarks, spanning multiple backbone model sizes, demonstrate that AgenticRag-R1 consistently outperforms strong baselines. Moreover, AgenticRag-R1 learns more robust, interpretable, and memory-aware reasoning behaviors, highlighting the effect of fine-grained action modeling and information-aware optimization for long-horizon reasoning. Our code is anonymous available at https://github.com/jiangxinke/Harness-RL/tree/AgenticRAG-R1-Whitebox.
Xinke Jiang, Yue Fang, Zhibang Yang et al.· 0 citations
Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt construction, rendering, and revision across interdependent scenes. Existing adaptive video systems primarily refine requests or reusable skills, leaving recurring production failures disconnected from persistent, stage-targeted improvements across stories. We introduce CineForge, a self-evolving video-production agent framework that couples CineForge-Produce for video generation with CineForge-Evolve for cross-story policy evolution. CineForge-Produce organizes each source story into typed narrative, character, spatial, and cinematic states, uses them to coordinate asset and clip generation, and records the process as a canonical production trajectory. CineForge-Evolve applies Case-to-Pattern-to-Policy Evolution (CPPE) to review trajectory evidence, consolidate recurrent findings into bounded stage-local patches, and deploy validated updates through structural replay and confidence-controlled paired evaluation. To measure complete story realization, we introduce CineScope, which combines a 100-script CineScope-Data suite with a human-aligned, multiscale CineScope-Metric spanning causal state, directorial orchestration, pacing and resource allocation, and character arc. Across CineScope-Data and two public benchmarks, the evolved CineForge policy improves CineScope-Metric from 4.024 to 4.380, outperforms three long-video baselines with consistent gains under ScriptAgent, and reduces review LLM calls by 37.0% on new stories. These results establish production trajectories as actionable experience for video agents that improve cumulatively across long-form storytelling tasks.
Junxiang Liu, Lin Wang, Haiyu Shi et al.· 0 citations
Text-to-spatial audio generation, such as text-to-First-Order Ambisonics (FOA), provides a convenient way to create spatial audio for billion-dollar gaming and film industries. However, existing text-to-FOA methods are largely data-driven and may produce audio that violates acoustic relations between source direction and distance. They also separate descriptive and parametric control, forcing users to trade usability for precision. In this paper, we present PhysWave, a physics-guided latent diffusion model for controllable text-to-FOA generation. PhysWave unifies natural-language and trajectory control through a shared waypoint-caption representation, and augments diffusion training with two differentiable acoustic priors: spherical-harmonic direction consistency and inverse-square distance consistency. To support dynamic spatial generation, we further construct a 300K-clip FOA dataset with diverse sound categories and source trajectories. Extensive results show that the proposed priors help PhysWave generate spatially consistent FOA audio while maintaining competitive audio quality. Further analyses show that these physics priors improve spatial consistency during training and can also be used as inference-time guidance for training-free spatial refinement.
Lingfeng Yao, Chenpei Huang, Xingke Yang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Frozen vision-language-action (VLA) policies offer broad manipulation skills but execute open-loop action chunks without tracking task progress, so the agent cannot reliably decide whether to continue, retry, or terminate. External memory is a natural remedy, yet it can be harmful when attempted actions are treated as completed progress, turning local execution errors into persistent task-state errors. We propose Achievement-Grounded Memory (AGM), a lightweight closed-loop framework for frozen VLA policies that represents a task as a subgoal sequence with a progress pointer and advances this memory only after the current subgoal is verified by physical evidence. Proprioceptive interaction cues decide when to verify, while coherent point tracking and language-conditioned cross-view comparison, sourced from frozen foundation models through a single 2.43M-parameter verification head, decide what was achieved. AGM thereby converts open-loop execution into a closed loop of execution, verification, and progress, keeping the policy frozen without test-time large-model inference. On the RoboMME Counting benchmark, AGM reaches on PickXTimes and on BinFill, surpassing the strongest memory-augmented baseline by points on average, and the framework yields equally decisive gains on a physical robot. Reliable embodied memory thus depends more on disciplined state updates than on memory capacity.
Infectious disease transmission is shaped by patterns of human interaction, which adapt as epidemic conditions change. Capturing these context-dependent behaviors remains a fundamental challenge for epidemic models. Here, we recast this challenge by using large language models (LLMs) to represent adaptive human behavior within mechanistic epidemic models. We operationalize this idea through Generative Adaptive Behavioral Layer for Epidemics (GABLE), which adapts LLMs to infer behavioral responses to epidemic and policy conditions and translates them into age-structured contact matrices coupled to a mechanistic epidemic model. Applied to COVID-19 in France, GABLE reproduced responses in population mixing and age-specific contact structures that remained epidemiologically informative. In short-term forecasting, LLM-generated contact matrices outperformed mobility-driven matrices derived from real-world mobility data, with the largest gains at longer horizons. GABLE also extends beyond forecasting to prospective policy evaluation by projecting behavioral and epidemic responses to candidate interventions before implementation. When supplied with subsequently implemented policies, GABLE reproduced epidemic trajectories and generated distinct responses to alternative policy timing and composition. By leveraging LLMs as a flexible behavioral layer, GABLE provides a framework for coupling context-sensitive behavioral generation with epidemic dynamics.
Yicheng Mao, Haoyang Li, Rob Deardon et al.· 0 citations
Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collisions. Signal Temporal Logic (STL) elegantly encodes such objectives, but current STL planning methods face critical limitations. State-of-the-art optimization-based approaches can handle arbitrary STL specifications but struggle with scalability, becoming computationally impractical as the number of agents grows. Learning-based methods efficiently handle a large number of agents with rapid planning times but fare poorly when deployment-time objectives differ from those used during training, and do not support planning tasks that require different specifications to be ascribed to different agents (i.e., heterogeneity) or team-level specifications requiring coordination of multiple agents. This fundamental trade-off between generalizability and scalability presents a challenge for realizing multi-agent STL planning algorithms in practice. To overcome this challenge, we introduce a new diffusion method for multi-agent planning with STL specifications. Using a differentiable approximation of STL, we integrate the STL gradient in the denoising process, making our approach generalizable to novel formulas whose predicates are placed anywhere within the goal region covered during training, while achieving the same scalability as existing learning-based methods. Our method supports heterogeneous specifications, and by using diffusion models, naturally enhances plan diversity, thereby significantly reducing safety-related violations (e.g., collisions) among agents. A detailed evaluation study justifies the utility of STL-guided diffusion-based multi-agent planners for constructing generalizable, scalable, and diverse plans. Videos and code are available at https://www.jeappen.com/diff-ma-stl/ and https://github.com/jeappen/diff-ma-stl .
Joe Eappen, Zikang Xiong, Shreyash S. Iyengar et al.· 0 citations
Scholarly work which aims to describe potential societal impacts (e.g., risks) of proliferating technology (especially related to artificial intelligence or other algorithmic systems) is likely to have an impact beyond the scientific communities it was written for, given that general society itself is a primary object of study. However, it is an open question whether the current practices of AI evaluation scholarship follow the principles and best practices established by risk science, which aims to systematically generate knowledge related to understanding, assessing, communicating, managing, and governing risk. In this work, we examine this in depth by conducting a literature review of scholarly works purporting to evaluate the bias or fairness of technological systems used for tasks related to hiring and employment. Through analysis of 22 common fairness evaluation metrics and studies using them, we find that most characterize the severity of bias- or fairness-related consequences but do not follow best practices to characterize the uncertainty around either the occurrence of these consequences or severity estimates. Next, we conduct a case study of fairness evaluation for an AI-mediated resume screening task and demonstrate how principles of risk science can be incorporated into such an evaluation. Finally, we propose the AI Risk Report Card, which facilitates the reporting and communication of risk assessment results to stakeholders in positions to act based on the predicted risks. The outcomes of these activities suggest that further research at the convergence of risk science and AI evaluation can lead to advancements in AI assessments of societal impact by enabling shared frameworks to evaluate and discuss AI risks both within and outside of the scientific community.
Kyra Wilson, Sabrina Kang, Saloni Dash et al.· 0 citations
AI agents are moving toward persistent, stateful execution across various applications, accumulating execution state and external effects that are costly to reconstruct after failures. Checkpoint and rollback (C/R) are becoming essential for recovery, yet their security implications remain largely unexplored. Correct rollback does not imply secure recovery: a faithfully restored checkpoint may resume an execution whose states, assumptions, and external effects never coexisted in any valid history. In this paper, we present the first systematic security study of checkpoint and rollback in existing agent systems. By examining representative agent C/R systems, we characterize the design space of existing C/R mechanisms and develop a general execution model that captures their recovery boundaries and state dependencies. From this model, we identify five fundamental failure modes spanning incomplete or inconsistent internal state, stale external dependencies, nondeterministic replay, and unrecorded external effects. We further demonstrate their security impact through three end-to-end attacks on Hermes, Cline, and LangGraph, enabling malware-verification bypass, unauthorized mail forwarding, and double payment. To systematically study these failures in practice, we develop a multi-agent analysis pipeline that reconstructs execution semantics, identifies violations of the five failure conditions, and validates them through actual rollback. Across five representative frameworks, our evaluation shows that these failures recur across heterogeneous C/R designs and stem from a common gap between the state restored by a checkpoint and the dependencies required for secure continuation.
Guanlong Wu, Dahui Li, Ke Jiang et al.· 0 citations
This work introduces Semantically-Guided Exploration (SGE), a modular exploration framework for ground vehicles that integrates pixel-level semantic segmentation into sampling-based waypoint selection and receding-horizon route optimization. Unlike conventional geometric exploration methods, SGE evaluates candidate exploration goals directly in the image space using a semantic-aware utility function that accounts for terrain traversability, obstacle proximity, objects of interest, and depth-based exploration reward. Sampled waypoints are projected into 3D and ordered through a real-time Traveling Salesman Problem (TSP) formulation, enabling receding-horizon goal selection. To address real-world navigation uncertainty, the framework introduces mechanisms, including temporary taboo regions to handle navigation failures and a graph-based relocation strategy for efficient backtracking across explored areas. We evaluate SGE in standardized simulation benchmarks against state-of-the-art exploration planners and demonstrate competitive performance in volumetric coverage, while enabling semantic task biasing that cannot be achieved by purely geometric methods. The framework is further validated through real-world experiments using multiple robotic platforms in indoor campus buildings and in limestone and coal mines. Results show consistent performance and adaptability across platforms and domains.
This work provides an overview of the different strategies that can be used to evaluate the performance of AI models and agents based on large language models (LLMs) for materials synthesis. After providing a brief overview of the key technologies behind the current generation of AI agents based on LLMs, we summarize the different approaches to evaluating these models in the context of materials science and in particular on materials synthesis, with a specific emphasis on scenarios in which the models are directly integrated with experimental tools. We discuss evaluation strategies spanning knowledge and reasoning benchmarks, tool-use benchmarks, and closed loop benchmarks involving the interaction with experimental systems or realistic virtual tools. We use atomic layer deposition (ALD) as a case study, emphasizing how existing approaches in the literature both build from general approaches used beyond materials science and can be generalized to other materials synthesis techniques. Finally, we provide a practical evaluation framework to evaluate LLMs in the context of materials synthesis
In metric social choice, each voter ranks a set of $m$ candidates by her distance to them in an unknown metric space. The cost of a candidate is its average distance to the voters. A randomized voting rule must use only the rankings to choose a lottery over candidates. Its distortion is the worst-case ratio between the expected cost under the lottery it returns and the cost of the best candidate. Charikar, Ramakrishnan, Wang, and Wu [JACM 2024] prove an upper bound of $2.753$, establishing a constant separation from deterministic rules, for which the best achievable distortion is $3$. Independently, Frank [arXiv:2608.17863] and Ye [arXiv:2608.21202] improve the bound to $2.5$, using an equal mixture of maximal lottery and Integrated Veto. The existing arguments do not yield a better bound with any mixture of these rules.
We break this barrier with a new ingredient, a random-size stable lottery. Let $D$ be a random variable over the domain of positive integers. A random-size stable lottery $\mathrm{RSL}_D$ guarantees that the probability of a random voter preferring any fixed candidate $c$ to her favorite of $D$ i.i.d. draws from $\mathrm{RSL}_D$ is at most $\mathbb{E}[1/(D+1)]$, where the probability also averages over $D$. When $D=k$ deterministically, this reduces to the stable $k$-lottery of Charikar, Ramakrishnan, Tan, and Wang [EC 2025]; the case $k=1$ is precisely a maximal lottery. Their minimax argument for a fixed $k$ easily generalizes to a random $D$. Our main contribution is to show how stability with respect to a random $D$ can be used to bound distortion. By mixing a suitably chosen random-size stable lottery with Integrated Veto, we get distortion at most $11641/5000=2.3282$. The proof combines infinite-dimensional conic linear-programming duality, heuristic nonlinear optimization, and exact rational verification via the Bernstein basis.
