AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch

Jiazhen Ji, Shouhong Ding

Autoresearch improves machine-learning code by proposing changes, running full training jobs, and keeping changes that improve the metric. The efficiency of this loop depends not only on generating ideas, but also on the agent's ability to decide, before spending a training run, whether a proposed modification is likely to work. We study how the reliability of this pre-execution judgment changes over the course of an autoresearch trajectory. In public AutoSOTA logs (Li et al., 2026; Tsinghua FIB Lab, 2026), the fraction of helpful modifications falls from 70% in the first two iterations to 43% by iteration 6+. On 296 same-baseline modification pairs from 39 paper-derived AutoSOTA tasks, each containing one modification that improved the metric and one that did not, with measured outcomes hidden, an LLM judge given candidate rationales but no prior-attempt history reaches 79.5% accuracy on the pairs where strict consensus returns a verdict. On the full 366-pair benchmark, however, this ability weakens substantially late in the loop. As successful changes accumulate, selective accuracy - accuracy conditioned on a strict-consensus verdict - falls from 82.8% to 56.9%, while the judge remains willing to decide. We call this operational pattern the confidence cliff. Rehearse implements the loop change as a lightweight skill for autoresearch loops: propose several ideas, compare them before execution, run the most promising, and judge with a focused memory of similar past attempts and outcomes. This focused outcome memory raises late selective accuracy to 83.5%. Across 4,000 budgeted training runs over three loops, Rehearse improves the endpoint under the same training-run budget on nanochat, image classification, and time-series forecasting.

arXiv

Evaluating and Pricing Advertisements in AI-Generated Responses

John L. Turner-Smith, Zimeng Huang, Yuhan Fu, Yihang Zhang, Tonghan Wang

As search increasingly shifts toward LLM-driven answer engines, advertising is becoming embedded within the generated response itself and should therefore be evaluated for both user utility and commercial value. The key challenge is click-through intent: behavioural logs are unavailable, human annotation resists calibration, and frontier LLM judges conflate intent with linguistic fluency. These gaps compound, as principled pricing presupposes a continuous intent signal, while generating such a signal presupposes supervision that is currently unavailable. We construct the missing supervision through a psychologically grounded agent simulation framework, and distil it into a parameter-efficient evaluator that predicts click-through intent, together with the three companion dimensions of ad quality, as smooth, differentiable estimates. Validated through sign-certain behavioural perturbations, the evaluator surpasses frontier zero-shot judges on relevance sensitivity (79% versus 60-67%), tracks graded content degradation, generalises without error to 103 fictional products, and agrees with human preference in 86% of pairwise judgements across five annotators, with agreement rising in the evaluator's confidence. Upon its estimates we build the pricing layer directly, deriving the unique payment rule under which truthful bidding is optimal, demonstrating it on a best-of-k allocation, and extending the mechanism to non-monotone allocations. The same differentiable signal stands ready as a training objective for ad generation.

arXiv

Stop Shipping AI Agents on Faith: Capability Is Not Production Readiness

Fouad Bousetouane

AI agents are moving into production workflows where they retrieve information, call tools, maintain state, and act on behalf of users or organizations, but many release decisions still rely on capability signals, demos, or behavioral tests that do not show whether an agent is ready to operate under production constraints. Capability is therefore not production readiness. This paper introduces the ProofAgent Index (PAI), a governance readiness index for AI agents. PAI combines four dimensions of deployment evidence: Evaluation, Context, Compliance, and Governance. Evaluation measures observed behavior, Context measures the operating environment that shapes that behavior, Compliance measures alignment with applicable rules and controls, and Governance measures whether the organization can authorize, monitor, audit, and control the agent during operation. PAI is implemented inside ProofAgent Harness, an open source infrastructure for auditable AI agent evaluation and governance. Validation across two heavily regulated domains, healthcare and finance, shows that PAI carries held out readiness signal and separates higher risk from lower risk configurations. The results show that context engineering strongly changes reliability, capability improves behavior but does not determine readiness, and governance evidence must remain visible rather than averaged away. PAI reframes agent release from a faith based deployment decision into an auditable readiness decision.

arXiv

A Model-Driven Approach for Developing Families of Reinforcement Learning Environments

Xiaoran Liu, Istvan David

Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior. Virtual training environments offer a safe and cost-efficient alternative to training agents in real-world settings. However, to converge, most realistic RL problems require training in multiple, mostly similar but slightly different environments - i.e., families of environment variants. The typical development process of environment families is a labor-intensive and error-prone manual endeavor that does not scale well. To alleviate these issues, in this paper, we propose a model-driven approach for developing families of RL training environments. To obtain the family of environments, we develop an approach and prototype tool. In our approach, a hybrid genetic algorithm - a combination of population-based global search and heuristic local search - generates environment families. Mutations and constraints are expressed as model transformations and are operationalized into a search process by a state-of-the-art model transformation engine. We demonstrate the soundness of our approach in a wildfire mitigation scenario and curriculum learning - a particular learning paradigm that relies on environment families.

arXiv

HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution

Taewoo Park, Kyeonghyun Yoo, Kiseok Kim, Seunghyun Yoo, Hwangnam Kim

Recent agentic AI systems may return a heterogeneous response containing notices, requests, handoffs, and actions. Conditions can change before external use, so components from the same response need not remain supported together. Rejecting the whole response discards useful components, whereas checking components independently can leave a dependent without its prerequisite. We present Heterogeneous Admission with Localized Obligations (HALO), a runtime protocol that preserves supported components whose declared prerequisites also remain supported, rechecks each exact action before dispatch, and allows blocked actions to be replaced only by fresh candidates. HALO matched all 96 admission expectations and passed all 20 protocol tests. In structured-response replay, it retained 248/248 supported components, including 128/128 unaffected by unrelated changes, while a whole-response policy retained 0/248. Across ten cold-start PX4/Gazebo sessions, HALO blocked every tested stale route, observed no matching stale setpoint, and completed all fresh recoveries.

arXiv

A Fully Convolutional Approach to Denoising 2D Correlation Spectra

Nisar Nellikunnummel, Andi M Barbour, Lutz Wiegart, Tatiana Konstantinova, Anthony M DeGennaro

We present a fully convolutional denoising autoencoder (FC-DAE) tailored for two-dimensional representations of dynamic correlations that is applicable to many experimental techniques. Here, we demonstrate its performance on two-time intensity correlation functions ($C_2$) from X-ray photon correlation spectroscopy (XPCS). Unlike conventional denoising autoencoders that are typically restricted to fixed input sizes, the FC-DAE accepts inputs of arbitrary dimensions while preserving correlation structures across diverse dynamical regimes. The model is trained using experimentally derived $C_2$ data collected at NSLS-II beamlines, with data augmentation applied to expand the diversity of the dataset and reduce overfitting. The FC-DAE successfully recovers intricate dynamical features in low signal-to-noise conditions while maintaining structural fidelity. To assess reconstruction reliability, we employ quantitative metrics to evaluate structural fidelity and identify potential model-induced bias. Our results demonstrate that the FC-DAE provides robust denoising performance with high computational efficiency, enabling recovery of XPCS dynamics under photon-limited and low-dose measurement conditions.

arXiv

SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization

Nguyen Viet Tuan Kiet, Nguyen Huu Duc, Le Cong Bang, Tran Cong Dao, Huynh Thi Thanh Binh

Black-box combinatorial optimization requires systematically identifying high-quality solutions under a limited evaluation budget, yet the unknown objective function provides little guidance for deciding where the search should explore next. We introduce SCOPE, a general framework for Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization. Rather than directly optimizing the inaccessible objective, SCOPE learns a set of synthetic objectives conditioned on the accumulated search history, where each objective is designed to expose a distinct and potentially useful preference over candidate solutions. These objectives are then used to evolve search policies that generate diverse candidates, whose true quality is subsequently assessed through black-box evaluations. The outer loop adaptively updates and selects synthetic objectives according to how effectively their induced policies discover promising regions. In contrast, the inner loop returns a portfolio of top-performing policies to reduce the risk of relying on a single surrogate preference. This formulation reframes objective design as a mechanism for guiding policy exploration, enabling the search process to exploit observed evidence while maintaining structured diversity across discrete solution spaces. Extensive experiments across multiple benchmark problems demonstrate that SCOPE consistently improves black-box search performance under limited evaluation budgets and generalizes well across diverse combinatorial structures.

arXiv

Arm2Air: Cross-Embodiment Skeleton Transfer for 3D Relay Formation

Dohun Lee, Kyeonghyun Yoo, Seokmin Kim, Byongho Lee, Seungjoo Oh, Hwangnam Kim

Unmanned aerial vehicle (UAV) relay networks can restore connectivity after communication infrastructure is damaged. Urban relay placement is difficult because line-of-sight blockage, communication range, altitude, and three-dimensional obstacles must be considered jointly. Arm2Air transfers obstacle-avoidance skeletons from robot arms to UAV relay placement through cross-embodiment transfer. Source-domain robot-arm motions from a pretrained Neural MP model are converted into ordered skeletons that pretrain a transformer-based transfer platform, which is then adapted to the UAV domain using limited target data and Low-Rank Adaptation. The transferred skeleton initializes a relay chain that is refined for connectivity, bottleneck capacity, delay, and movement cost. On nine held-out high-clutter 3D urban maps, Arm2Air reduced median end-to-end planning runtime by 64.9 percent relative to the fastest conventional planner. On the high-obstruction group of a separate 30-map dense urban holdout, it increased bottleneck capacity by 32.6 percent, reduced capacity variance by 74.7 percent, reduced maximum hop distance by 13.2 percent, reduced hop-distance variance by 75.2 percent, and reduced relay displacement by 16.9 percent relative to IMPC-MD. With only three target-domain training maps, Arm2Air reduced relay-position root mean square error by 53.6 percent relative to training from scratch while updating 0.134 million parameters, compared with 1.383 million for Scratch and Full Fine-tuning. These results demonstrate computationally and data-efficient UAV relay placement and suggest a broader principle for transferring ordered structural priors across heterogeneous embodied tasks.

arXiv

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures

Siyuan Ma, Yiqin Luo, Zhangji, Canran Xiao, Albert Gao, Wei-Hsing Huang, Wei Wang, Qiwei Wu, Xinran Li, Jinfeng Wei, Qixin Zhang

Identical language-model answers can arise from hidden states that support different future computations, so current-answer probes do not establish a reusable internal interface. We introduce forked futures: future operations are sampled only after a prefix state has formed, and states are compared through the response distributions induced by those operations. This yields an empirical causal quotient over hidden states without requiring researcher-specified latent labels. Shared, Local, Mixture, and Distributed interfaces then compete under prequential causal description length subject to future-signature fidelity and matched capacity constraints. In the two detailed model evaluations, Shared has the lowest held-out description length, with gains of 0.216 nats on Qwen2.5-1.5B and 0.294 nats on Llama-3-8B, while maintaining tightly clustered mean future-signature distortion; a five-backbone sweep preserves the positive direction of Sharedness Gain. The figure-aligned transplantation analysis gives Shared the strongest joint target-correctness, locality, copy-preservation, and composite profile, and API-aligned paths mediate 0.749 of the target effect versus 0.150 for matched null paths. In the blind four-class model-organism test, 14/16 architectures are recovered, with one observed non-Shared to Shared error among 12 non-Shared organisms. These results support an economical reusable causal interface within the tested operation banks, while keeping the claim explicitly conditional on the candidate architectures, interventions, and held-out futures.

arXiv

CORE: In-Context Reconstruction for Unified Tabular Anomaly Detection

Yunfeng Zhao, Qingfeng Chen, Yue Tan, Shiyuan Li, Yili Wang, Yixin Liu, Shirui Pan

Tabular anomaly detection (TAD), which focuses on identifying abnormal samples that deviate from the majority in tabular data, has received growing attention. Recently, there has been an emerging trend towards unified TAD, which seeks to detect anomalies across different datasets using a single generalizable model. In unified TAD, aligning heterogeneous data remains challenging. While existing methods often rely on distance-based unified feature construction, they may obscure the semantics of the original features. Moreover, existing approaches typically formulate anomaly detection as a binary classification task, which may overlook diverse anomaly patterns from various datasets and be misled by unrepresentative synthetic anomalies. To address these challenges, we propose an in-COntext REconstruction approach for unified TAD (CORE for short). It introduces a decorrelated feature alignment module to directly align heterogeneous features into a unified representation space, which retains their semantic information. Meanwhile, CORE formulates unified TAD as an in-context reconstruction problem, eliminating the need for labeled or synthesized anomalies. Specifically, the in-context reconstruction module reconstructs each sample by leveraging contextual normal samples to capture dataset-specific distributions, such that reconstruction errors reflect its deviation from normality, facilitating unified TAD on arbitrary unseen datasets.

arXiv

LearnedCache: eBPF-Integrated Perceptron-Based Eviction Policies for the Linux Page Cache

Zejia Qi

Any device that runs Linux uses the Linux page cache, a central pillar in OS and application performance, serving to reduce extraneous disk access. Many page cache eviction policies have been developed but remain bound by the rigidity of heuristics. Promising research has been done on neural cache eviction policies, but only in the field of user-space applications such as CDNs. We present LearnedCache, a set of machine-learning-based page cache eviction policies that run live inside the Linux kernel through the cache_ext eBPF framework. LearnedCache trains a lightweight perceptron per workload on kernel trace data collected using eBPF to predict whether eviction candidates will be reused within a bounded horizon and deploys it through two eBPF policies. The resulting policies consistently compete with and outperform both external heuristic policies and the kernel's own, improving application throughput by up to 44% versus standard kernel policies.

arXiv

Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance

Jose Blanchet, Peter Glynn, Wenhao Yang

Stochastic gradient descent (SGD) is foundational to large-scale statistical learning and stochastic optimization. However, in some modern statistical learning problems, stochastic gradients can exhibit infinite-variance behavior. Consequently, classical inference methods for SGD that rely on a finite-variance assumption break down. We develop a model-agnostic methodology for constructing confidence regions from SGD iterates in both the finite- and infinite-variance regimes. We first show that Polyak--Ruppert averaging has an asymptotic directional scale no larger than that of the fastest-rate final iterate, analogous to its lower asymptotic variance in the finite-variance setting. Accordingly, we focus our inference methodology on the Polyak--Ruppert averaged estimator. Specifically, we establish a joint central limit theorem for this estimator and an empirical second-moment normalizer from the same iterates. This joint limit yields a self-normalized statistic in which the leading tail-dependent scaling terms cancel. We then use subsampling to estimate the relevant quantiles, avoiding explicit estimation of nuisance parameters including tail indices, slowly varying functions, or stable-law parameters. The resulting confidence regions are straightforward to implement and asymptotically valid in both the finite- and infinite-variance regimes. Empirical studies show reliable coverage in various settings, supporting the proposed method as a practical tool for uncertainty quantification in stochastic optimization.

arXiv

Revisiting the Adversarial Robustness of Graph-Based Traffic Forecasting

Qingzhao Zhang

Traffic forecasting by graph-based AI is a critical component of intelligent transportation systems, motivating security research on robustness to malicious sensor readings. We argue that prior robustness evaluations are largely shaped by unrealistic threat models and untargeted objectives, so both attacks and defenses must be revisited. We study a practical adversary with limited model knowledge and the ability to monitor and manipulate only a few road sensors. More importantly, practical attacks can be localized to specific links or routes, causing incorrect estimated arrival times or unnecessary rerouting while leaving the broader network largely unaffected. This targeted setting remains underexplored, and defenses such as adversarial training do not transfer well from the norm-bounded attacks they train on to structurally different, physics-aware attacks that mimic genuine congestion. We therefore reframe robustness as a detection problem, introducing a learned physics-informed detector whose output is fed to a hardened forecaster as an input feature and trained against adaptive attacks with the forecaster fixed. We evaluate across a variety of model architectures and benchmarks. The physics-aware attack multiplies target-link error several-fold while the network-wide error barely moves, and adversarial training, tuned to norm-bounded perturbations, barely dents it. Our detection--mitigation defense improves even on adversarial training hardened against the physics-aware attack itself, on $13$ of $15$ model--dataset settings and by the widest margin on a held-out attack, at near-zero clean cost. The results emphasize the need to examine abstracted AI adversarial attacks under application-specific constraints to assess their true security impacts.

arXiv

World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models

XiangCheng Zhang, Yilun Du

Building generalizable agents for diverse applications remains a fundamental challenge. While imitation learning-based policies succeed in specific training environments, they often fail to generalize to novel scenes and tasks. In this work, we propose World Action Planner, a robot planning system that leverages the reasoning capabilities of Vision-Language Models (VLMs) and the physical grounding of a multi-task pose-image conditioned world model. Our system enables an agent to propose initial action plans and iteratively refine them via optimization and search, reasoning over imagined world model rollouts. We demonstrate that our approach achieves superior performance across compositional tasks, new layouts, and zero-shot generalization scenarios, significantly outperforming state-of-the-art end-to-end policy models such as VLAs and WAMs. Project website at worldactionplanner.github.io

arXiv

AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers

Jungang Zou, Alex Ziyu Jiang, Qixuan Chen

Coding and computation remain major bottlenecks in Markov chain Monte Carlo (MCMC) workflows, especially as modern sampling algorithms have become increasingly complex and existing probabilistic programming systems remain limited in model support, extensibility, and composability. We introduce \textbf{AI4BayesCode}, an extensible LLM-driven system that translates natural-language Bayesian model descriptions into runnable, validated MCMC samplers. To improve reliability, AI4BayesCode adopts a modular design that decomposes models into modular sampling blocks and maps each block to a built-in sampling component, reducing the need to implement complex sampling algorithms from scratch. Reliability is further improved through pre-generation validation of model specifications and post-generation validation of generated sampler code. AI4BayesCode also introduces a novel recursively stateful coding paradigm for MCMC, allowing modular sampling components, potentially developed by different contributors, to be composed coherently within larger MCMC procedures. We develop a benchmark suite to evaluate AI4BayesCode for sampler-generation. Experiments show that AI4BayesCode can implement a wide range of Bayesian models from natural-language descriptions alone. As an open-ended system, its capability can continue to expand with improvements in the underlying AI agent and the addition of new built-in blocks. The software is available at https://ai4bayescode.com/.

arXiv

A Systems Engineering Framework for Vision-Language-Enabled UAV Triage and Disaster Response

Swapnil Saha, Bhuvan Rajanasiriyur Jagadeesha, Karishma Patnaik, Neelakshi Majumdar

Recent advances in Vision Language Models (VLMs) have created new opportunities for disaster response, where responders must interpret large volumes of sensor data under time pressure. Current VLM applications include social media monitoring for situational awareness, generation of draft action plans, and translation of technical alerts into public-facing messages. While these efforts can accelerate information flow, they remain largely limited to decision-support roles. Such approaches can increase operator burden because humans must still translate outputs into coordinated actions across teams and robotic assets. This study explores the viability of embedding VLMs as coordination agents within the human-UAV loop. The proposed architecture integrates natural language interaction, mission-level task coordination, software-in-the-loop implementation, and communication aligned with the Incident Command System (ICS). Rather than functioning solely as advisory tools, VLMs facilitate communication between human operators, mission control logic, and UAV task execution. The framework was developed using a Model-Based Systems Engineering (MBSE) approach, with use case and block definition diagrams representing system roles, internal structure, and component interactions. Three key elements, the VLM Coordinator Agent, UAV Mission Control, and Task Allocator, were implemented within an integrated simulation and control environment. A preliminary human-factors evaluation with seven participants showed reduced perceived workload across mental demand, effort, and frustration, along with high ratings for AI trust and communication clarity. By integrating MBSE, software-in-the-loop testing, and human-factors evaluation, this work advances scalable human-autonomy teaming for high-stakes disaster response, with broader implications for aerospace autonomy and civil safety.

arXiv

Is Solving Better Than Evaluating GenAI Solutions?

Ethan Dickey, Marios Mertzanidis, Alexandros Psomas

As Generative AI (GenAI) tools become increasingly capable of generating solutions to computing assignments, the computing education community is exploring pedagogical approaches that emphasize solution evaluation, verification, and critique alongside traditional solution generation. However, evidence regarding the impact of such evaluation-centered tasks on student learning remains limited, particularly in upper-division, theory-heavy courses. We conducted a randomized A/B crossover study (N=220) in a junior-level algorithms course to compare evaluating GenAI-generated solutions with traditional problem solving. Across six assignments, student working groups either solved challenging algorithmic problems directly or evaluated often-flawed GenAI-generated solutions, with roles reversed midway through the semester. We found no statistically significant differences between groups in midterm scores, final exam scores, overall course grades, or exam problems structurally aligned with the homework interventions. Students received significantly higher homework scores when evaluating GenAI-generated solutions, but this localized advantage did not translate into downstream summative gains. Survey data further indicated that most students reported no change in study habits in response to the intervention; however, those who reported adapting their study strategies rated the GenAI-evaluation assignments as significantly more helpful. These findings suggest that GenAI evaluation redistributes student effort from open-ended solution construction toward verification, diagnosis, and judgment, but does not automatically produce stronger conceptual transfer. We conclude that GenAI-evaluation activities can be incorporated into algorithms coursework without broad performance losses, but meaningful learning gains may require deliberate scaffolding that pushes students beyond simple error diagnosis.

arXiv

From Minds to Models: The Intersection of Psychology and LLM Behaviours

Oliver Guidetti, Reza Ryan

Large language models (LLMs) are often compared with the human mind because their decision-making is complex, non-linear and difficult to interpret. Psychological methods developed to investigate unobservable mental processes may therefore help examine LLM behaviour, particularly in government and healthcare. Building on prompt-based adaptations of the Implicit Association Test, this study tested whether ChatGPT produced sentiment differences across racial conditions in open-ended text. Fourteen base questions were crossed with eight racial categories and a race-agnostic control, producing 126 prompts. Each was submitted once to GPT-3.5T, GPT-4 and GPT-4T, yielding 378 responses. Sentiment scores were derived from categorical labels and source scores: positive labels retained the source score, negative labels were assigned its negative, and neutral responses were coded zero. A two-way ANOVA found a small main effect of racial condition, F(8, 351) = 2.04, p = .042, partial-eta squared = .044, but no effect of model, F(2, 351) = 0.07, p = .933, and no interaction, F(16, 351) = 0.23, p = .999. However, the effect was not retained in a rank-transformed sensitivity analysis, F(8, 351) = 1.53, p = .145, and Tukey-corrected comparisons found no significant pairwise differences. An uncorrected European-Indigenous Australian comparison was significant, but was selected post hoc and is reported only as hypothesis-generating. Evidence for sentiment differences was therefore weak and analysis-dependent. Sentiment scoring also cannot distinguish evaluative bias from the valence of historical content elicited by a prompt. We outline design changes needed to address these limitations and argue for interdisciplinary development of behavioural measures of model bias. Keywords: Implicit Bias, Psychological Research Methods, Artificial Intelligence, ChatGPT, Large Language Models, Sentiment Analysis

arXiv

What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering

Sandeco Macedo

Prompts stopped being isolated strings some time ago. In real systems, one model call feeds another, retrieval interleaves with generation, routers branch, and aggregators merge parallel results. Practice converged on a single structure to hold this together: the graph. Frameworks such as LangGraph, DSPy, and Prompt Flow expose it openly, and research systems already optimize it automatically. The vocabulary, however, lags behind. Graph names, variously, a reasoning topology inside one sampling strategy, a multi-agent conversation, or an orchestration artifact, while prompt engineering still evokes writing one good string. What is missing is a reference definition treating prompts as nodes of an explicit, executable, improvable graph. We build that definition through conceptual analysis over sources with persistent identifiers, complemented by primary grey literature. We reconstruct the genealogy of the idea, from dataflow graphs and build systems, through prompt chaining and the thought topologies (chain, tree, graph), to graphs compiled and optimized as artifacts. We then propose a constitutive definition of prompt graph engineering, state its four conditions (explicit structure, separation between structure and prompt content, executable semantics, and the graph as a first-class engineering artifact), and operationalize them as an inclusion and exclusion test. We draw the boundary against six neighboring concepts and apply the test to six real systems (LangGraph, DSPy, Prompt Flow, AutoGen, CrewAI, and Claude Code subagents); it includes and excludes consistently. We close with a research agenda organized along four design tension axes. The contribution is an operational definition and a shared vocabulary for a practice that industry already exercises daily without naming precisely.

arXiv

DeepResearch Agent System

Yong Huang, Yulu Huang, for the team Collaboration

The DeepResearch Agent System is a large language model system engineered for deep information retrieval, multi-step reasoning, and autonomous research tasks. Built upon a sparse activation architecture with 30 billion total parameters of which only 3 billion are activated per token, the system achieves state-of-the-art performance on multiple agent search benchmarks while delivering 3.2 times faster inference compared to dense counterparts of equivalent scale. The system supports a 128K-token context window with hierarchical attention mechanisms that yield 18.7% accuracy and 23.4% recall improvements over standard long-context approaches. A dual-mode reasoning engine provides both a ReAct paradigm for basic multi-step problem solving and an IterResearch mode for high-performance iterative research with up to 20 reasoning steps, collectively delivering a 31.2% accuracy improvement over single-pass baselines. Multi-tool coordination integrates retrieval, computation, web search, and file parsing modules to achieve 92.1% tool-use accuracy. A reinforcement learning optimization framework based on the GRPO algorithm provides token-level policy gradients that improve training stability by 35% and accelerate convergence by 42%. An automated data synthesis pipeline with seed-based expansion achieves a 92.5% usability rate. Benchmark results include 87.3% on Humanity's Last Exam, 85.3% on BrowserComp Chinese, and 91.2% on WebWalkerQA. The system is fully open-sourced, including data synthesis, training, and inference code, and supports applications in academic research, business analysis, R&D support, and education.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.