Research Papers

Recent AI research from arXiv

The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multi-Step Malware

Ben Nassi, Bruce Schneier, Oleg Brodt

The rapid adoption of large language model (LLM)-based systems -- from chatbots to autonomous agents capable of executing code and financial transactions -- has created a new attack surface that existing security frameworks inadequately address. T...

Jan 14, 2026 Analyzed
8.7

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning

Zhiyuan Hu, Yunhai Hu, Juncheng Liu et al.

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting teammates...

Jan 14, 2026 Analyzed
8.7

AI builds, We Analyze: An Empirical Study of AI-Generated Build Code Quality

Anwar Ghammam, Mohamed Almukhtar

The rapid adoption of AI coding agents for software development has raised important questions about the quality and maintainability of the code they produce. While prior studies have examined AI-generated source code, the impact of AI coding agen...

Jan 23, 2026
8.7

Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection

Tianyi Niu, Justin Chih-Yao Chen, Genta Indra Winata et al.

Large Language Model (LLM) routers dynamically select optimal models for given inputs. Existing approaches typically assume access to ground-truth labeled data, which is often unavailable in practice, especially when user request distributions are...

Jan 14, 2026 Analyzed
8.7

FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation

Zimu Lu, Houxing Ren, Yunqiao Yang et al.

Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to only generate frontend web pages, masking the lack of real full-stack data processing a...

Feb 03, 2026
8.6

CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing

Shanyv Liu, Xuyang Yuan, Tao Chen et al.

Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware Strategy f...

Jan 27, 2026
8.6

MonoScale: Scaling Multi-Agent System with Monotonic Improvement

Shuai Shao, Yixiang Liu, Bingwei Lu et al.

In recent years, LLM-based multi-agent systems (MAS) have advanced rapidly, using a router to decompose tasks and delegate subtasks to specialized agents. A natural way to expand capability is to scale up the agent pool by continually integrating ...

Jan 30, 2026
8.6

Agentic Design Patterns: A System-Theoretic Framework

Minh-Dung Dao, Quy Minh Le, Hoang Thanh Lam et al.

With the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lead to unreliable and brittle...

Jan 27, 2026
8.6

Learning to Share: Selective Memory for Efficient Parallel Agentic Systems

Joseph Fioresi, Parth Parag Kulkarni, Ashmal Vayani et al.

Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution quality, recent approaches deploy multiple agent teams running in para...

Feb 05, 2026
8.6

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

Yibo Wang, Lei Wang, Yue Deng et al.

Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require annotation-intensive task construction, rely on static evaluation ...

Jan 14, 2026 Analyzed
8.6

AgentRx: Diagnosing AI Agent Failures from Execution Trajectories

Shraddha Barke, Arnav Goyal, Alind Khare et al.

AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a novel bench...

Feb 02, 2026
8.6

When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling

Niful Islam, Ragib Shahriar Ayon, Deepak George Thomas et al.

Large Language Models (LLMs) have revolutionized intelligent application development. While standalone LLMs cannot perform any actions, LLM agents address the limitation by integrating tools. However, debugging LLM agents is difficult and costly a...

Jan 21, 2026
8.6

SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents

Yifeng Ding, Lingming Zhang

Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering (SWE) tasks. However, the standard approach of repeatedly sampling trajectories from scratch is computationally expe...

Jan 29, 2026
8.6

Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity

Yingxuan Yang, Chengrui Qu, Muning Wen et al.

LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance by increasing the number of agents; however, we find that such scal...

Feb 03, 2026
8.6

Context-Augmented Code Generation Using Programming Knowledge Graphs

Shahd Seddik, Fahd Seddik, Iman Saberi et al.

Large Language Models (LLMs) excel at code generation but struggle with complex problems. Retrieval-Augmented Generation (RAG) mitigates this issue by integrating external knowledge, yet retrieval models often miss relevant context, and generation...

Jan 28, 2026
8.6

SERA: Soft-Verified Efficient Repository Agents

Ethan Shen, Danny Tormoen, Saurabh Shah et al.

Open-weight coding agents should hold a fundamental advantage over closed-source systems: they can be specialized to private codebases, encoding repository-specific information directly in their weights. Yet the cost and complexity of training has...

Jan 28, 2026
8.6

From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents

Bingsheng Yao, Chaoran Chen, April Yi Wang et al.

The emergence of Large Language Model (LLM) agents enables us to build agent-based intelligent systems that move beyond the role of a "tool" to become genuine collaborators with humans, thereby realizing a novel human-agent collaboration paradigm....

Feb 05, 2026
8.6

AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration

Jianhao Ruan, Zhihao Xu, Yiran Peng et al.

Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has driven the rise of a sub-agent-as-tools paradigm for multi-turn task solving. However, existing designs still la...

Feb 03, 2026
8.6

Learning to Compose for Cross-domain Agentic Workflow Generation

Jialiang Wang, Shengxiang Xu, Hanmo Liu et al.

Automatically generating agentic workflows -- executable operator graphs or codes that orchestrate reasoning, verification, and repair -- has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably handle....

Feb 11, 2026
8.5

Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests

Haruhiko Yoshioka, Takahiro Monno, Haruka Tokumasu et al.

The automatic generation of pull requests (PRs) using AI agents has become increasingly common. Although AI-generated PRs are fast and easy to create, their merge rates have been reported to be lower than those created by humans. In this study, we...

Jan 26, 2026
8.5

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

Yifan Wu, Lizhu Zhang, Yuhang Zhou et al.

In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgo...

Jul 09, 2026
8.4

Real-Time Detection and Repair of LLM Agent Failures

Sunny Dubey

LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the standard remedy, judging every step with a second LLM, costs more than the agent itself. We ask how m...

Aug 03, 2026
8.4

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

Gaurav Dadhich

Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outpu...

Jul 23, 2026
8.4

They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trusted Agentic CI/CD Pipeline Into an Attack Surface

Yohann Sidot

We study a five-agent CI/CD pipeline (triage -> developer -> security-scan -> review -> approve/deploy), built from five distinct production LLMs across three providers, behind an LLM firewall in shadow mode. A single untrusted input - an external...

Jul 21, 2026
8.4

Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows

Anuj Sadani, Deepak Kumar

The Model Context Protocol (MCP) has become a common interface for connecting large language model (LLM) agents to external tools, but its reliance on stateless, eager schema injection imposes a hidden per-turn overhead the MCP Tax or Tools Tax th...

Apr 23, 2026
8.4

When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime

Wei Wu

LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools, maintaining memory, and pushing results to humans. We present a longitudinal study of silent failures in one such system: a personal-assistant ag...

Jun 12, 2026
8.4

Recursive Agent Harnesses

Elias Lumer, Sahil Sen, Kevin Paul et al.

Recursive language models (RLMs) showed that recursion over model calls is an effective strategy for long-context reasoning, and production coding agents have begun to write code that spawns subagents at scale, most recently in Anthropic's dynamic...

Jun 11, 2026
8.4

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub

Ramtin Ehsani, Sakshi Pathak, Shriya Rawal et al.

AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known about how t...

Jan 21, 2026
8.3

Scaling Multiagent Systems with Process Rewards

Ed Li, Junyu Ren, Cat Yan

While multiagent systems have shown promise for tackling complex tasks via specialization, finetuning multiple agents simultaneously faces two key challenges: (1) credit assignment across agents, and (2) sample efficiency of expensive multiagent r...

Jan 30, 2026
8.3

Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals

Thamilvendhan Munirathinam

As autonomous LLM agents increasingly hold real credentials and operate infrastructure without a human in the loop, operators have no standard way to tell an agent that a resource is off-limits. Access controls either let the agent in (it has vali...

Jun 04, 2026
8.1

TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis

Pepe Alonso

AI coding agents can resolve real-world software issues, yet they frequently introduce regressions, breaking tests that previously passed. Current benchmarks focus almost exclusively on resolution rate, leaving regression behavior under-studied. T...

Mar 18, 2026
8.1

Probe-and-Refine Tuning of Repository Guidance for Coding Agents

Asa Shepard, Jeannie Albrecht

LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historically led to wrong fixes) that does not exist in the code itself. Engine...

Jun 18, 2026
8.1

Halluverse-M^3: A multitask multilingual benchmark for hallucination in LLMs

Samir Abdaljalil, Parichit Sharma, Erchin Serpedin et al.

Hallucinations in large language models remain a persistent challenge, particularly in multilingual and generative settings where factual consistency is difficult to maintain. While recent models show strong performance on English-centric benchmar...

Feb 06, 2026
8.0

Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering

Fangan Dong, Zuming Yan, Xuri Ge et al.

Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationally expensive sampling strategies, limiting their practical efficienc...

Jan 27, 2026
7.8

Toward Autonomous Long-Horizon Engineering for ML Research

Guoxin Chen, Jie Chen, Lei Chen et al.

Autonomous AI research has advanced rapidly, but long-horizon ML research engineering remains difficult: agents must sustain coherent progress across task comprehension, environment setup, implementation, experimentation, and debugging over hours ...

Apr 14, 2026
7.7

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang et al.

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural language res...

Apr 08, 2026
7.7

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

Piercosma Bisconti, Matteo Prandi, Federico Pierucci et al.

Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. When models are deployed as agents, the safety-relevant object shifts ...

May 21, 2026
7.7

LLM-as-a-Verifier: A General-Purpose Verification Framework

Jacky Kwok, Shulu Li, Pranav Atreya et al.

Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as a new scaling a...

Jul 06, 2026
7.7

MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems

Qianshu Cai, Yonggang Zhang, Xianzhang Jia et al.

Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a fix. Self-evolving agents have emerged in response, but all confine...

May 21, 2026
7.7

The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents

Jiayuan Liu, Tianqin Li, Shiyi Du et al.

Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4 games over 500 rounds, expanding accessible history degrades cooper...

May 08, 2026
7.7

Context Over Content: Exposing Evaluation Faking in Automated Judges

Manan Gupta, Inderjeet Nair, Lu Wang et al.

The $\textit{LLM-as-a-judge}$ paradigm has become the operational backbone of automated AI evaluation pipelines, yet rests on an unverified assumption: that judges evaluate text strictly on its semantic content, impervious to surrounding contextua...

Apr 16, 2026
7.7

Code as Agent Harness

Xuying Ning, Katherine Tieu, Dongqi Fu et al.

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target out...

May 18, 2026
7.7

AMEL: Accumulated Message Effects on LLM Judgments

Sid-ali Temkit

Large language models are routinely used as automated evaluators: to review code, moderate content, or score outputs, often with many items passing through one conversation. We ask whether the polarity of prior conversation history biases subseque...

May 21, 2026
7.7

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

Yasmine Omri, Ziyu Gan, Zachary Broveak et al.

LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A r...

Jun 04, 2026
7.7

LLM for Large-Scale Optimization Model Auto-Formulation: A Lightweight Few-Shot Learning Approach

Kuo Liang, Yuhang Lu, Jianming Mao et al.

Large-scale optimization is a key backbone of modern business decision-making. However, building these models is often labor-intensive and time-consuming. We address this by proposing LEAN-LLM-OPT, a LightwEight AgeNtic workflow construction frame...

Jan 14, 2026 Analyzed
7.7

Recursive Models for Long-Horizon Reasoning

Chenxiao Yang, Nathan Srebro, Zhiyuan Li

Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We identify recursion as a core principle for overcoming this barrier, and propose recursive models as a minim...

Mar 02, 2026
7.7

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory

Zhenting Wang, Huancheng Chen, Jiayun Wang et al.

Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working context be...

Mar 04, 2026
7.7

Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs

Kevin Murphy

We present BLF (Bayesian Linguistic Forecaster), an agentic system for binary forecasting that achieves state-of-the-art performance on the ForecastBench benchmark. The system is built on three ideas. (1) A Bayesian linguistic belief state: a semi...

Apr 20, 2026
7.7

Recursive Agent Optimization

Apurva Gandhi, Satyaki Chakraborty, Xiangjun Wang et al.

We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to new instantiations of themselves recursively. Recursive agents implement an inference...

May 07, 2026
7.7

Artisan: Agentic Artifact Evaluation

Doehyun Baek, Michael Pradel

Artifact evaluation has become standard practice in the software engineering community to ensure the reproducibility of research results. However, the current manual process is labor-intensive, and hence, done only as a one-time assessment for a s...

Feb 10, 2026
7.7