arXiv subjects

Jiaxin Pei

Publications and source records attributed to Jiaxin Pei.

At least 19 recordsLinked to original sources

arXiv2026

MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks

Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversations or text but fails to capture how memory is used to guide future decisions. Another class focuses on agents acting in single-session tasks without the need for long-term memory. However, in realistic settings, memorization and action are tightly coupled: agents acquire memory while interacting with the environment, and subsequently rely on that memory to solve future tasks. To capture this setting, we introduce MemoryArena, a unified evaluation gym for benchmarking agent memory in multi-session Memory-Agent-Environment loops. The benchmark consists of human-crafted agentic tasks with explicitly interdependent subtasks, where agents must learn from earlier actions and feedback by distilling experiences into memory, and subsequently use that memory to guide later actions to solve the overall task. MemoryArena supports evaluation across web navigation, preference-constrained planning, progressive information search, and sequential formal reasoning, and reveals that agents with near-saturated performance on existing long-context memory benchmarks like LoCoMo perform poorly in our agentic setting, exposing a gap in current evaluations for agents with memory. MemoryArena is now released at https://memoryarena.github.io/.

cs.CL↗

arXiv2026

AI Should Facilitate Democratic Deliberation at Scale

AI systems can strengthen democracy by supporting deliberation at scale by addressing cognitive, social, platform-design, and market-driven frictions, while preserving human agency. Unlike proposals such as liquid democracy that restructure representation through vote delegation, in this position paper, we argue that AI-assisted deliberation offers a more promising path by lowering barriers to meaningful engagement without substituting machine judgment for human choice. Drawing on evidence from online deliberation platforms and experimental research, we identify four guiding principles: preserving agency and autonomy, encouraging mutual respect, promoting equality and inclusiveness, and augmenting rather than substituting active citizenship. We also address critical challenges, including alignment, sycophancy, training bias, and over-reliance on AI systems. We call on the machine learning community to develop deliberation-focused AI systems evaluated not on engagement metrics but on their capacity to facilitate informed, representative, and friction-robust discourse.

cs.HC↗

arXiv2026

ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance

Language model (LM) agents are increasingly deployed to maintain codebases over extended periods, fixing streams of related defects while carrying context from one fix to the next. Yet existing software engineering (SWE) benchmarks evaluate models one bug at a time: the repository is reset, the codebase is re-read, and a single self-contained issue is graded in isolation. This setting collapses a continuous maintenance workflow into a series of independent sessions, ignoring the cumulative dependencies that make real-world bug fixing challenging. To bridge this gap, we introduce ChainSWE, the first benchmark for evaluating agents on sequential, dependent bug fixes within a shared codebase. We collect chronological chains of 304 issues across 54 Python projects, mined from six SWE-bench-family datasets. Our evaluation across a range of agents and models reveals a consistent performance drop by up to 70% as the chain length increases.

cs.SE↗

arXiv2026

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are rarely disclosed to the public or regulators, creating a serious trust and accountability gap in the wide deployment of AI systems. In this paper, we introduce Artificial Intelligence System Prompt Assurance (AISPA), a user-centric framework for systematically auditing system prompts in AI systems. AISPA examines specific parts of a system prompt and evaluates them along eight dimensions that matter to users. We then use this framework to review 3,249 instructions from system prompts in 88 commercial AI products, classifying each instruction as either protective (of users) or problematic. Our audit surfaces four core findings. First, system prompt design varies substantially across products and developers, with some organizations averaging over 60 protective instructions per product while others average fewer than 5. Second, protective instructions are widely adopted but shallow in scope: 98.9% of products contain at least one, yet only 24% cover all eight dimensions of the AISPA taxonomy. Third, system prompts have grown steadily longer and more protective of users, suggesting that user protection is becoming a more visible concern in commercial prompt design. Fourth, despite this progress, problematic instructions remain pervasive: roughly 40% of products contain at least one instruction that works against user interests, and protective and problematic instructions frequently coexist within the same prompt. Our findings highlight the need for greater transparency, standardization, and independent oversight for system prompts in commercial AI products.

cs.AI↗

arXiv2026

Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing

Teachers, conference chairs, and public readers all judge writing from limited evidence, seeing only a finished document and not the process that produced it. Final text alone cannot reveal whether a document was produced through human typing, AI generation, or mixed human-AI collaboration. Existing process-tracking tools help, but many are tied to host-document histories, provide coarse activity records, and offer limited control over the writing environment. Humanly is a writing platform that makes the writing process itself the evidence. Users configure writing environments for personal documents or assigned tasks and draft in a workspace that records writing activity and in-platform AI assistance. Humanly can package a completed session into a sealed writing certificate with configuration-aware anomaly behavior review. It can support writing scenarios such as course assignments, peer review, and personal certification. Our user study shows that Humanly is helpful across roles, and a red-teaming study shows that the Humanly Typing Detector distinguishes human hand typing from automated typing.

cs.CL↗

arXiv2026

Interactive Task Alignment as a POMDP

Current benchmarks for language models primarily evaluate execution on fully specified tasks. However, real user tasks are often ambiguous. Users arrive with incomplete, exploratory, or even inconsistent goals, requiring the assistant to first determine the intended task before carrying it out. We study this problem as task alignment: the ability to align with a user on their intended task. We introduce a general framework for converting specified tasks into underspecified interactions, formalized as a POMDP in which the model must infer a latent task from partial and evolving user intent. We validate our user simulator post hoc with a human user study. Across shopping, coding, and professional work settings, we find that while models often perform well once the task is specified, models still struggle with task alignment: current models act prematurely, interact ineffectively, and fail to resolve ambiguous requests. Models on average recover the user's intended task only 22-32% of the time under ambiguity. In a human study in the same setting, humans reach 48%, outperforming all evaluated models. We show that post-training with supervised fine-tuning and reinforcement learning improves task alignment, but models still lag behind humans in resolving uncertainty through interaction. Together, our results suggest that current models still lack key interaction abilities required for reliable agency.

cs.AI↗

arXiv2026

Stop Automating Peer Review Without Rigorous Evaluation

Large language models offer a tempting solution to address the peer review crisis. This position paper argues that today's AI systems should not be used to produce paper reviews. We ground this position in an empirical comparison of human- versus AI-generated ICLR 2026 reviews and an evaluation of the effect of automated paper rewriting on different AI reviewers. We identify two critical issues: 1) AI reviewers exhibit a hivemind effect of excessive agreement within and across papers that reduces perspective diversity. 2) AI review scores are trivially gameable through paper laundering: prompting an LLM to rewrite a paper could significantly increase the scores from AI reviewers, demonstrating that LLM reviewers are easy to game through stylistic changes rather than scientific results. However, non-gameability and review diversity are necessary but not sufficient conditions for automation. We argue that addressing the peer review crisis requires a science of peer review automation -- not general-purpose LLMs deployed without rigorous evaluation.

cs.AI↗

arXiv2026

ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration

Conversational agents are increasingly embedded in human collaborative work, yet they remain fundamentally passive and reactive: they respond to explicit user requests rather than proactively recognizing moments when a team would benefit from timely intervention as human collaborators often do. This reactive design substantially limits the use of agents as active participants in multi-user collaboration, where disagreements, ambiguous goals, forgotten constraints, underspecified plans, discussion loops, and imbalanced participation can gradually undermine group progress. To move agents from passive assistants toward active participants in multi-user collaboration, we introduce ProACT, a breakdown-aware agent framework grounded in theories of common ground, collaborative planning, and coordination work. ProACT observes the speaker-attributed conversation history, determines whether the current turn contains a collaboration breakdown requiring intervention, decides whether the agent should stay silent or speak, and, when speaking is needed, routes the case to a targeted collaboration skill. We further introduce the first multi-user collaboration benchmark for evaluating proactive agents across project planning, product design, research collaboration, logistics, education, and resource-constrained decision making. Across 3,244 turn-level examples and five LLM backbones, ProACT consistently improves collaborative appropriateness, non-interruptiveness, conciseness, and judged intervention quality over direct chat.

cs.CL↗

arXiv2026

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts. Yet existing benchmarks for frontier models primarily evaluate either single-turn responses or short-horizon agent trajectories, failing to capture the challenges of sustained iterative improvement over extended time horizons. To address this gap, we introduce AutoLab, a new benchmark for ultra long-horizon closed-loop optimization. AutoLab consists of 36 realistic, expert-curated tasks spanning four diverse domains: system optimization, puzzle & challenge, model development, and CUDA kernel optimization. Each task begins with a correct but deliberately suboptimal baseline and challenges agents to improve it within a strict wall-clock budget. Evaluating 17 state-of-the-art models reveals the dominant predictor of success is not the quality of an agent's initial attempt, but its persistence in repeatedly benchmarking, editing, and incorporating empirical feedback. While claude-opus-4.6 exhibits strong long-horizon optimization capabilities, most frontier models, including several proprietary ones, either terminate prematurely or exhaust their budgets with minimal progress. These results underscore the importance of time awareness and persistent iteration in autonomous agents. We open-source the full benchmark, evaluation harness, and task artifacts, to accelerate research toward truly capable long-horizon agents.

cs.AI↗

arXiv2026

BAGEN: Are LLM Agents Budget-Aware?

While agents are increasingly spending more resources, today agent cost is mostly measured only after execution. A Budget-Aware Agent (BAGEN) should treat budget as an active control signal, rather than a passive cost metric. We first systematically define budget estimation as internal budgets (from agent computation) and external budgets (from agent actions). We then formalize budget-awareness as progressive interval estimation: at each step of a plan, an agent should predict an upper and lower bound on remaining budget, and alert when completion is unlikely. Scoring with a rollout-replay protocol, we find consistent failure patterns on four environments and five frontier agents: (1) strong agents do not necessarily have strong budget-awareness, with correlation r=0.35. (2) frontier models are consistently over-optimistic, continue spending on tasks that are unlikely to succeed, instead of alerting the user early. (3) budget-aware signal is actionable and trainable. Early stop saves 28-64% tokens on failed trajectories, and SFT+RL strengthens early stop and alert behavior. (4) precise interval calibration remains challenging, with interval coverage capping at 47% after SFT+RL. Project page: https://ragen-ai.github.io/bagen/

cs.LG↗

arXiv2026

SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent

Large language model agents have made strong progress on software engineering, yet current systems suffer from a context coupling problem: the standard code editing interface conflates code inspection, modification planning, and edit execution within a single context window, forcing agents to interleave exploratory viewing with strictly formatted edit generation. Irrelevant context accumulates and edit reliability degrades. We propose SWE-Edit, which decomposes the editing interface into two specialized subagents: a Viewer that extracts task-relevant code on demand, and an Editor that executes modifications from high-level natural language plans -- letting the main agent focus on reasoning while delegating context-intensive operations to clean context windows. On SWE-Bench Verified, this decomposition raises resolve rate by 2.1 pp and cuts inference cost by 17.9%, with consistent gains across multiple reasoning-model families (Kimi-K2, MiniMax-M2.1, GLM-4.7). We further show that effective edit-format selection can be trained into a small model rather than requiring frontier-scale capacity: GRPO training on Qwen3-8B with an adaptive find-replace/whole-file-rewrite policy improves edit success by 12.5 pp and brings an 8B open-source editor to parity with GPT-5-nano on downstream SWE-Bench resolve rate. To enable rapid editor iteration, we release PR-Edit, a lightweight evaluation whose scores correlate strongly with SWE-Bench resolve rate. We release our code at https://github.com/microsoft/SWE-Edit.

cs.SE↗

arXiv2026

The Last Human-Written Paper: Agent-Native Research Artifacts

Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation imposes two structural costs: a Storytelling Tax, where failed experiments, rejected hypotheses, and the branching exploration process are discarded to fit a linear narrative; and an Engineering Tax, where the gap between reviewer-sufficient prose and agent-sufficient specification leaves critical implementation details unwritten. Tolerable for human readers, these costs become critical when AI agents must understand, reproduce, and extend published work. We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with a machine-executable research package structured around four layers: scientific logic, executable code with full specifications, an exploration graph that preserves the failures compilation discards, and evidence grounding every claim in raw outputs. Three mechanisms support the ecosystem: a Live Research Manager that captures decisions and dead ends during ordinary development; an ARA Compiler that translates legacy PDFs and repos into ARAs; and an ARA-native review system that automates objective checks so human reviewers can focus on significance, novelty, and taste. On PaperBench and RE-Bench, ARA raises question-answering accuracy from 72.4% to 93.7% and reproduction success from 57.4% to 64.4%. On RE-Bench's five open-ended extension tasks, preserved failure traces in ARA accelerate progress, but can also constrain a capable agent from stepping outside the prior-run box depending on the agent's capabilities. Our code is open-sourced at https://github.com/Orchestra-Research/Agent-Native-Research-Artifact.

cs.LG↗

arXiv2026

Interactive Evaluation Requires a Design Science

AI evaluation is undergoing a structural change. Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other agents, while many evaluation practices still inherit assumptions from response-centered benchmarks (e.g., fixed inputs, isolated outputs, and outcome judgments that can be made from a single response). The field has begun to build interactive benchmarks, but the resulting landscape is fragmented: benchmarks differ in what interaction artifacts they admit, how trajectories are scored, and what claims their results support. This position paper argues that interactive evaluation should be treated as a principled evaluation paradigm, not merely a new family of agent benchmarks. Simply adopting previous evaluation paradigms does not suffice. We define evaluation as an autonomous mapping from evidence to judgments, and show that interactive evaluation changes both sides of this mapping: the evidence becomes interaction-generated trajectories, while the evaluation procedure must assess process, recoverability, coordination, robustness, and system-level performance. Building on this definition, we propose a two-axis taxonomy, derive design principles and reporting standards, examine representative scenarios, and analyze how longstanding evaluation challenges reappear at the trajectory level.

cs.AI↗

arXiv2026

Quantifying Trust: Financial Risk Management for Trustworthy AI Agents

Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve into autonomous agents deployed in open environments and increasingly connected to payments or assets, the operational meaning of trust shifts to end-to-end outcomes: whether an agent completes tasks, follows user intent, and avoids failures that cause material or psychological harm. These risks are fundamentally product-level and cannot be eliminated by technical safeguards alone because agent behavior is inherently stochastic. To address this gap between model-level reliability and user-facing assurance, we propose a complementary framework based on risk management. Drawing inspiration from financial underwriting, we introduce the \textbf{Agentic Risk Standard (ARS)}, a payment settlement standard for AI-mediated transactions. ARS integrates risk assessment, underwriting, and compensation into a single transaction framework that protects users when interacting with agents. Under ARS, users receive predefined and contractually enforceable compensation in cases of execution failure, misalignment, or unintended outcomes. This shifts trust from an implicit expectation about model behavior to an explicit, measurable, and enforceable product guarantee. We also present a simulation study analyzing the social benefits of applying ARS to agentic transactions. ARS's implementation can be found at https://github.com/t54-labs/AgenticRiskStandard.

cs.AI↗

arXiv2026

How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks

The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of tokens, three questions naturally arise: (1) Where do AI agents spend the tokens? (2) Which models are more token-efficient? and (3) Can agents predict their token usage before task execution? In this paper, we present the first systematic study of token consumption patterns in agentic coding tasks. We analyze trajectories from eight frontier LLMs on SWE-bench Verified and evaluate models' ability to predict their own token costs before task execution. We find that: (1) agentic tasks are uniquely expensive, consuming 1000x more tokens than code reasoning and code chat, with input tokens rather than output tokens driving the overall cost; (2) token usage is highly variable and inherently stochastic: runs on the same task can differ by up to 30x in total tokens, and higher token usage does not translate into higher accuracy; instead, accuracy often peaks at intermediate cost and saturates at higher costs; (3) models vary substantially in token efficiency: on the same tasks, Kimi-K2 and Claude-Sonnet-4.5, on average, consume over 1.5 million more tokens than GPT-5; (4) task difficulty rated by human experts only weakly aligns with actual token costs, revealing a fundamental gap between human-perceived complexity and the computational effort agents actually expend; and (5) frontier models fail to accurately predict their own token usage (with weak-to-moderate correlations, up to 0.39) and systematically underestimate real token costs. Our study offers new insights into the economics of AI agents and can inspire future research in this direction.

cs.CL↗

arXiv2026

Multi-User Large Language Model Agents

Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is designed to satisfy the objectives of one dominant user whose instructions are treated as the sole source of authority and utility. However, as they are integrated into team workflows and organizational tools, they are increasingly required to serve multiple users simultaneously, each with distinct roles, preferences, and authority levels, leading to multi-user, multi-principal settings with unavoidable conflicts, information asymmetry, and privacy constraints. In this work, we present the first systematic study of multi-user LLM agents. We begin by formalizing multi-user interaction with LLM agents as a multi-principal decision problem, where a single agent must account for multiple users with potentially conflicting interests and associated challenges. We then introduce a unified multi-user interaction protocol and design three targeted stress-testing scenarios to evaluate current LLMs' capabilities in instruction following, privacy preservation, and coordination. Our results reveal systematic gaps: frontier LLMs frequently fail to maintain stable prioritization under conflicting user objectives, exhibit increasing privacy violations over multi-turn interactions, and suffer from efficiency bottlenecks when coordination requires iterative information gathering.

cs.CL↗

arXiv2026

From Pixels to Personas: Tracking the Evolution of Anime Characters

Anime, originated from Japan, is one of the most influential cultural products in modern society and is especially popular among younger generations. The popularity of anime reflects important cultural evolutions in our society. Despite existing research on anime as a cultural phenomenon, we still have a limited understanding of how anime really evolves over the years. In this study, using a large-scale multimodal dataset of anime characters from an anime review site, we applied computational methods that integrate textual, visual, and production features of anime characters with online popularity traces. By combining LLM-extracted personality features with avatar features, we identify recurring personality archetypes and visual tropes with their temporal evolution over the past decades. We found that the target audience of anime has undergone a systematic shift from children to a maturing audience of teenagers and young adults over time. Character design has been undergoing moe-ification, with softer or sexualized female traits becoming increasingly prominent since the 2000s. Some personality archetypes are often visually predictable, yet audiences also tend to prefer less conventionalized characters. Finally, we reveal that visual signals play a more dominant role than personality traits in shaping audience preferences, with features such as moe-style faces and mechanical designs contributing greatly to popularity. These findings offer insights into the broader dynamics of anime's cultural and creative practices.

cs.CY↗

arXiv2026

Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs

Large-scale public deliberations generate thousands of free-form contributions that must be synthesized into representative and neutral summaries for policy use. While LLMs have been shown as a promising tool to generate summaries for large-scale deliberations, they also risk underrepresenting minority perspectives and exhibiting bias with respect to the input order, raising fairness concerns in high-stakes contexts. Studying and fixing these issues requires a comprehensive evaluation at a large scale, yet current practice often relies on LLMs as judges, which show weak alignment with human judgments. To address this, we present DeliberationBank, a large-scale human-grounded dataset with (1) opinion data spanning ten deliberation questions created by 3,000 participants and (2) summary judgment data annotated by 4,500 participants across four dimensions (representativeness, informativeness, neutrality, policy approval). Using these datasets, we train DeliberationJudge, a fine-tuned DeBERTa model that can rate deliberation summaries from individual perspectives. DeliberationJudge is more efficient and more aligned with human judgements compared to a wide range of LLM judges. With DeliberationJudge, we evaluate 18 LLMs and reveal persistent weaknesses in deliberation summarization, especially underrepresentation of minority positions. Our framework provides a scalable and reliable way to evaluate deliberation summarization, helping ensure AI systems are more representative and equitable for policymaking.

cs.CL↗