Agent 进展

Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitment: an agent acts before resolving whether its memory grounding is stale, conflicting, incomplete, or corrupted. We formalize this problem as safe commitment under memory uncertainty and introduce SafeCommit, a risk controlled layer between agent reasoning and external execution. The layer constructs a calibrated set of plausible latent worlds from memory, observations, tool outputs, provenance, and policy constraints. It permits a side effectful action only when a conformal action certificate shows that the action is safe in every retained world. Otherwise, it selects a low-side-effect probe that targets the worlds blocking certification, or returns a conservative fallback. Under calibrated world coverage, the probability of an unsafe certified commit is at most the target level α; with imperfect world proposal, the bound separates calibration and representation error. A dependency-free controlled simulator illustrates the safety-utility tradeoff and reproduces all reported results with one command. The goal is to offer a concrete approach for deciding not only what an agent should do, but when the available evidence is sufficient to safely do it.

Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed. In strategic cyber-physical systems, a stronger question is whether the planning architecture remains appropriate after autonomous participants respond and physics constrains the outcome. We introduce a controlled, physics-grounded benchmark built around planning-induced control trajectories: the ordered planning operations and directives through which an execution architecture acts on other agents and the physical process. It implements predefined, sequential, hierarchical, and search executors in a smart-grid demand-response system with 40 heterogeneous prosumers and an independently simulated radial feeder. The LLM is bounded to typed policy declaration and short operator messages, while schedule construction, prosumer dynamics, and power flow remain explicit code. The protocol uses paired forced-mode counterfactuals, common random response draws, and event-level deadline feasibility. Three properties follow. Architecture materially changes outcomes: forced search is the oracle in all five baseline seeds. Execution fidelity needs more than mode agreement: objective substitution holds agreement at 1.0 while increasing voltage shortfall by 2.68x. A 144-scenario, 576-episode bank has feasible oracles from three of the four architectures. A prespecified stress-held-out ridge has mean regret 90.7 (95% interval [73.8, 108.6]) and no detectable value over fixed sequential; applying known deadline feasibility before quality prediction cuts regret to 29.0 and improves over fixed sequential by 61.1. An all-feasible ablation does not beat fixed search, localising the remaining challenge to within-feasible quality selection. A five-model extension separates stress-conditioned, state-blind, and invariant declarers; latency tails show that live feasibility should be treated probabilistically.

Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in data intelligence. Existing methods suffer from fixed linear pipelines and isolated subtask processing, which hinder joint optimization of factual accuracy, visual quality, and narrative coherence. To address these issues, this paper proposes MCTS-Report, a Monte Carlo Tree Search (MCTS)-driven framework that formulates multimodal table-to-report generation as a progressive construction process over a structured search space. The core idea is to decompose report generation into atomic actions, including chapter planning, visualization task identification, chart generation, insight organization, and narrative refinement, each executed by an LLM based on dynamic reasoning conditioned on the current report state. We use an LLM to generate step-by-step reasoning and actions during MCTS, storing the reasoning trajectory in each node for context-aware, coherent report construction. To guide the search, we design a multi-dimensional reward function that jointly evaluates numerical fact consistency (via SQL), chart quality, chart-text alignment, and structural completeness, while incorporating a diversity penalty to suppress repeated charts and a precondition check to prune invalid actions. We also construct MMRBench, a comprehensive benchmark comprising real-world tables from six domains, paired with expert-refined reference report structures and verifiable key insights. Experiments on MMRBench demonstrate that MCTS-Report significantly outperforms strong baselines across structural completeness, numerical accuracy, chart-text alignment, and insight novelty, achieving a 77.9 overall score.

Agentic AI is increasingly used to coordinate planning, implementation, review, and testing in software development, yet it often offers limited transparency into its decisions and interactions. Many such systems also assume that users can effectively guide the AI's decisions and validate its outputs. This assumption poses a particular challenge for novices, who must simultaneously learn how agentic AI works, how to collaborate with it effectively, and how to evaluate its outputs critically. To address this challenge, we present AgentForge, an immersive learning system in which novices take on one of four software-engineering roles: Task Planner, Patch Author, Code Reviewer, or Test Runner, within a multi-agent code-repair workflow. In each practice session, the novices perform their chosen role while AI agents perform the remaining three. Through role-based scaffolding and metacognitive support, AgentForge clarifies role-specific responsibilities, makes agent coordination and intermediate artifacts visible, and encourages novices to monitor and evaluate their decisions. In a study with 37 novice developers, participants achieved high task-completion rates with AI-agent support. However, interaction demands differed significantly across practices: the Code Reviewer practice required more interaction turns, reroutes, and completion time ($p_{\mathrm{adj}} = .004$) and was perceived as the most challenging. Participants nevertheless reported significant gains in their understanding of software repair and agent collaboration ($p_{\mathrm{adj}} < .001$). These findings suggest that AgentForge can help novices develop practical software-engineering skills while learning to collaborate with agentic AI more critically and effectively.

When people label text for sexism, they often disagree, and not because some of them are wrong: they genuinely perceive sexism differently. Most NLP systems discard this disagreement by collapsing it into a majority vote. We propose the Multi-Agent Perspectivist Preference Optimization (MAP-PO) framework to keep these different perspectives. On the EXIST 2024 dataset of labeled English and Spanish tweets, we first cluster annotators by their labeling behavior rather than their demographic attributes. We then fine-tune one Large Language Model agent per cluster to reproduce that cluster's annotation behavior, and coordinate the agents with preference optimization that combines individual and team-level rewards. We evaluate MAP-PO in four settings defined by two languages and two backbone language models, asking whether each agent reproduces the annotations of its own cluster and whether the agents together reproduce the majority label. Two findings hold in all four settings. First, without fine-tuning the agents behave almost identically, so cluster-specific training is necessary. Second, we show that training each agent only on the labels of its own cluster pushes the agents far beyond the clusters they should represent, while adding a shared team-level training signal consistently keeps each agent calibrated to its cluster.

Large language model (LLM) agents are increasingly used as personalized assistants in high-stakes domains such as financial advising, yet it remains unclear whether they can maintain and update an individualized user model over long horizons. Existing personalized-memory benchmarks primarily test factual retention or rely on weakly constrained model-generated trajectories, leaving event-driven preference adaptation underexplored. We introduce FinPerMA, an event-grounded benchmark that evaluates personalized memory against frozen longitudinal investor trajectories. Its generation pipeline combines deterministic, theory-informed impact rules, controlled LLM narration, and automated quality screening; a Post-Shock checkpoint isolates whether an agent has integrated a material event into its persistent user model. On 2,994 questions from 276 personas, seven frontier LLMs and up to seven memory configurations remain far from saturated: no full-context configuration exceeds approximately 0.47 overall accuracy or approximately 39% on multiple-choice questions. Attribution analysis shows that summary-based memory often preserves factual details while losing the preference signals needed for personalization; simple retrieval can therefore outperform purpose-built memory systems, with the gap widening after shocks.

LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment, and multimodal, forcing the agent to preserve goals and constraints across many steps while navigating heterogeneous tools and attachments. While prior work has addressed individual failure modes such as goals drift, states loss, and context overflow, whether a single harness can manage them jointly and remain effective across backends has received less study. We present OneDayAgent, a long-horizon harness for autonomous agents. OneDayAgent turns an open-ended request into a managed execution process that decomposes tasks into bounded subtasks, maintains execution memory under context pressure, and verifies and repairs the final deliverable. We evaluate OneDayAgent on AgentIF-OneDay across 104 tasks. With the GLM-5.2 backend, OneDayAgent sets a new state of the art with an overall score of 0.821. The same harness runs across five backend LLMs from three model families, indicating the harness generalizes across backends without tuning, even as different models induce distinct execution styles under the same workflow.

Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrates fragmented personal signals, amplifies their impact through reuse, and challenges defenses designed for individual records or retrieval-based memory. To systematically investigate the safety of the persona-skill pipeline, we introduce AntiSkillBench, an end-to-end benchmark for evaluating risks and defenses across the persona-skill pipeline. It comprises: (i) a dataset of 7,500 persona-grounded dialogue traces, constructed from 50 behaviorally rich profiles spanning diverse task scenarios; (ii) an evaluation suite that measures skill-level privacy leakage and agent-level attribute disclosure and behavioral impersonation across three skill-distillation strategies; and (iii) a defense evaluation covering four configurations across online and post-hoc interventions, including active risk suppression and passive provenance protection. Experiments across three frontier agents show that persona-skill risks persist across agent backbones and distillation protocols, extending from explicit attributes to communication styles and personality traits. Existing defenses exhibit limited and distillation-dependent effectiveness, failing to generalize across risk and distillation strategies. These results highlight AntiSkillBench as a challenging benchmark for developing privacy-preserving and authenticity-aware persona skills.

Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively. Evaluating self-evolution is difficult: existing benchmarks provide limited coverage of economically valuable task domains, do not always design training and test tasks such that test-time gains can be attributed to training experience, and remain vulnerable to data contamination. We present GDPevo, an evolution-native benchmark grounded in GDP-related enterprise workflows, together with the fully automated data pipeline that generates it. Its core mechanism, rule hybridization, decomposes each enterprise workflow into atomic business rules, distributes subsets of these rules across training tasks, and recombines them in held-out test tasks so that test-time gains are attributable. GDPevo spans CRM, ERP, finance, healthcare, legal, and data-centric workflows. Its V1 release contains 120 tasks in 12 groups, with five training and five held-out test tasks per group. Full automation enables the pipeline to expand the suite to 240 tasks in 24 groups (V2) within two days, providing a practical response to contamination. Using GDPevo, we evaluate four agents, each comprising a harness and a model, under four supervision types. Self-evolution consistently improves held-out accuracy by up to 16.44 percentage points. But the best evolved agents remain far below the fully informed oracle ceiling of 91.6%, indicating that the self-evolution ability of current agents remains far from fully realized. We publicly release the pipeline, benchmark, and full evaluation results at https://github.com/Prism-Shadow/GDPevo.

A framework that persists execution state so a run can be interrupted, survive a crash, and continue must decide what a resume means for effects that already fired. Five widely deployed agent workflow frameworks answer differently, none exposes a machine-checkable contract, and behavior violates even the fragments they state. The RESUME CONTRACT states six properties over the persistence API (prefix continuation, effect exactly-once, fork determinism, checkpoint validity, consume-once, recovery determinism), plus fork-intent and liveness obligations. A TLA+ model checks a reference semantics exhaustively, unchanged at scaled bounds (7.4 million states); a 39-cell fault matrix and two companion modules yield the separating models independence requires, and consume-once splits, its consumption clause independent of all six others. A deterministic, LLM-free harness measures them at pinned releases. LangGraph 1.2.9 durably records a second resume value and never consults it, persists schema-invalid state silently, and re-executes durably recorded work after a real SIGKILL: exactly-once across interrupts, at-least-once across crashes, on one API. CrewAI 1.15.2 re-executes completed effect-bearing methods against its written claim; pydantic-graph 1.x cannot resume after a mid-node crash; no two probed frameworks share a conformance profile. Consume-once holds sequentially and fails under concurrent delivery: k processes resuming one parked interrupt fire the gated effect k times, saturation 1.0 in 36 of 40 cells, and the failure crosses hosts. REMIT, a reference sequencer whose Verus-verified recovery core is line-identical to the shipped executable, repairs the fork and validity cells. The cross-process cell is repaired at the read path, and that repair ships: an opt-in gate claims consumption in the shared store, serving one racer and refusing the rest before any node executes.

Reasoning-enhanced large language models have achieved remarkable improvements in planning tasks, yet their deployment in embodied systems remains impractical due to prohibitive inference delays-often exceeding minutes per planning instance. The fundamental bottleneck stems from the serial nature of existing paradigms: models must complete all reasoning before any action execution, leaving execution time windows entirely unexploited. We introduce PACE (Planning with Adaptive Cognitive Effort), a framework that enables interleaved reasoning and execution through two key innovations: an Interleaved Think-Act architecture that pipelines cognitive processing with action execution, and a Dynamic Budget Allocator that adapts reasoning token budgets to available execution time windows. On the Robotouille benchmark using Qwen3-8B-AWQ, PACE achieves a 10% success rate-representing a 67% improvement over the ReAct+Think baseline-while delivering 6.9 times acceleration in thinking time compared to unconstrained reasoning. The framework hides 66.8% of thinking time within execution windows, demonstrating that strategic cognitive effort allocation can simultaneously improve both planning quality and time efficiency. These results provide evidence that time-aware architectural innovations enable reasoning models to operate in latency-sensitive embodied domains where they were previously impractical.

Post-training reinforcement learning (RL) algorithms are commonly used to align large vision-language models (LVLMs) with human intent and the requirements of visual reasoning tasks. However, existing RL-based alignment methods are often resource-intensive and encounter mismatches between training objectives and inference-time distributions. To bridge this gap, we propose a novel test-time alignment approach that leverages trajectory-guided structured sampling for dynamic inference-time refinement, achieving better alignment with visual grounding and ensuring logical consistency. Our approach begins with curating a reasoning memory bank via a trajectory learning algorithm, which decomposes complex question solving into ordered sequences of predefined reasoning patterns. It subsequently accomplishes inference-time alignment by first collecting trajectories from reasoning memory bank to establish a global structural reasoning prior, and then using an iterative Markov Chain Monte Carlo (MCMC) algorithm for localized multi-objective refinement of the reasoning trace. Experiments across multiple multimodal reasoning datasets demonstrate that our approach significantly improves accuracy without incurring prohibitive inference overhead. These results establish trajectory-guided test-time sampling as a scalable and effective alternative to traditional post-training alignment, particularly for complex visual reasoning tasks.

Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typically process heterogeneous dialogue content through a uniform summarization and retrieval pipeline, leading to either excessive token consumption or irreversible loss of fine-grained evidence. We argue that historical dialogue content should be handled differently according to its compressibility, temporal dynamics, and fidelity requirements. Based on this insight, we propose LeanMem, a lightweight long-term memory framework. LeanMem first filters out low-value content, then stores informative segments as compact profile memory, temporally structured event memory, or source-grounded record memory, depending on the nature of the information. During maintenance, only dynamically evolving event memories are selectively updated, avoiding redundant consolidation of stable profiles and immutable records. During inference, LeanMem dynamically selects memory types and allocates retrieval budgets according to query-specific evidence demands, assembling relevant evidence on demand. On LoCoMo and LongMemEval-S with GPT-4.1-mini and Qwen3-8B, LeanMem improves accuracy over the strongest memory-based baseline in every setting, by up to 15.1 points, at the lowest or near-lowest construction cost, inference tokens, and latency. The code and datasets are included in the supplementary materials.

Recent works train agents by constructing large-scale multimodal environment pools. However, we find that simply increasing the number of multimodal environments does not always benefit. We further analyze the limitations in current multimodal environment distributions through a series of experiments. Based on these findings, we study how to build more effective training environment distributions from two dimensions: **diversity** and **difficulty structure**. For diversity, we propose **Ability-aware Environment Selection (AES)** to obtain diverse environment sets. For difficulty structure, we propose **Hierarchical Difficulty Curriculum (HDC)**, which organizes curriculum learning through two difficulty levels: harness weakening and state-scale progression. Experiments show that AES and HDC effectively improve multimodal agent training.

Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language models. Under pronounced task distributional shifts, however, forgetting across representative RFT algorithms escalates sharply. This stems from the implicit reward-variance regularization inherent to RFT, which proves incapable of suppressing uncontrolled optimization risk. We propose Risk-Aware Policy Optimization (RAPO), the first dual-channel framework for explicit risk governance in continual RFT. On the policy channel, Risk-Aware Policy Scaling adaptively calibrates per-sample update magnitude via rollout reliability and Fisher-inspired local predictive sensitivity; on the data channel, Risk-Aware Dynamic Bucket Sampling reorganizes training batches through dynamic risk stratification, steering optimization toward informative yet stable samples. As a plug-and-play strategy requiring no cross-task memory, RAPO generalizes to any RFT algorithm without modification. On the public MLLM-CL benchmark, RAPO reduces final forgetting by 79.8% relative to its RLOO backbone while retaining new-task competitiveness.

Clinical development is sequential decision-making under uncertainty, where a sponsor must plan a portfolio of experiments from heterogeneous evidence. We study this setting by framing oncology clinical development as an offline decision-making problem in which an agent predicts the next six-month trial portfolio of an oncology drug program from information available at the decision date. To support this, we construct a temporal dataset that combines 31.7k heterogeneous public data records, including trial registries, regulatory reviews, sponsor filings, utilization data, and epidemiology, into 881 offline decision episodes across 45 historical programs. We compare four offline objectives: behavioral cloning, reward-weighted behavioral cloning, learned-reward training, and value-based implicit Q-learning against four frontier LLM agents that share a common date-gated retrieval scaffold across held-out drug, sponsor, drug-class, and temporal splits. Models trained offline outperform the non-fine-tuned baselines, particularly in the post-August 2025 contamination-clean holdout. Reward-weighted behavioral cloning performs the best, obtaining 46.2% indication F1 and 14.2% strict F1 against 25.0% and 2.1%, respectively, for the best-performing tool agent on each metric. These results suggest that structured offline learning can teach agents to plan clinical experiments.

Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existing systems reduce memory updating to a binary Write/Hold decision, which cannot distinguish whether new information should be added, ignored, used to revise an outdated belief, rejected as unreliable, or deferred for verification. These choices may share the same binary label while producing fundamentally different memory states. We introduce TARL, a memory state update framework that maps each statement to one of five executable actions. TARL identifies the affected memory, resolves its temporal scope, compares source reliability, and updates accepted, pending, and rejected ledgers. It is further trained by comparing the memory states produced by alternative update operations, encouraging the model to select the operation that leads to the correct result. We also introduce TARL-Mem, a benchmark with fine-grained action labels and next-state targets. Across in-domain, cross-source, temporal, counterfactual, and sequential evaluations, TARL improves action prediction and state recovery, reduces memory pollution, preserves conflicting evidence, and limits cumulative corruption. The complete model implementation is provided in the supplementary material.

Geospatial reasoning, i.e., computing distances, containment, and other spatial relations over real-world entities, is central to navigation and logistics, yet large language models (LLMs) struggle with the required geometric and topological computation despite storing considerable geographic knowledge. Existing benchmarks localize these failures only partially: they are synthetic or smallscale, largely monolingual, and offer limited control over geographic coverage. We introduce MultiGlobeQA, a multilingual benchmark of 46,060 question-answer pairs spanning 14 spatial-function families and 15 answer formats, with execution-based ground truth over three knowledge graphs. It covers 201 countries and territories via income- and density-stratified sampling, with parallel questions in English and 16 additional high- and low-resource languages. Across parametric, reasoning, and agentic settings, LLMs collapse on tasks requiring grid indexing and shape computation, while topological relations and directions fare best. Retrieval and tool use yield considerable gains, yet performance plateaus below two thirds even when gold facts are supplied, indicating that computation, not access to knowledge, is the bottleneck. Models also underperform on low-income regions, a gap that gold facts widen rather than close.

The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes. Tools play a central role as the primary interface through which agents interact with external environments, yet existing methods rarely focus on ensuring robust tool use across diverse runtime conditions. To address this problem, we propose ExpG, a mechanism that builds and refines adaptive guidance capturing each tool's capability boundaries and best practices, thereby enabling agents to use tools more robustly and effectively. ExpG consists of three phases: (1) experience acquisition, which analyzes tool invocation quality from historical execution trajectories, producing structured learnable experiences through multi-aspect attribution; (2) experience distillation, which keeps the experience pool effective by filtering unhelpful experiences, selecting representative ones with an equivalence-class-based method, and summarizing them into generalizable guidance; and (3) experience reuse, which applies the guidance adaptively during future task solving. Extensive experiments show that ExpG brings consistent improvements across the tool selection, tool calling, and response generation tasks, enabling smaller agents to outperform larger ones that do not use ExpG. Moreover, ExpG achieves particularly strong gains in challenging settings, suggesting a promising path toward more robust tool use. Our code, experiments, and results are available.

Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly. We formalize this threat as adaptive transcript privacy and introduce DP-MemView, a differentially private interface that privately selects public response-conditioning views and exposes those views---rather than raw memory---to the response LLM. Each private selection is charged to every protected attribute whose memory group intersects the read set. Per-attribute ledgers block any selection that would exceed its cap and return a fixed generic view instead. Under an explicit interface contract, we prove pure B_a-DP for the entire adaptive transcript. We also extend the result to stores that differ across multiple protected groups and bound how much observing the transcript can change an adversary's prior odds. We evaluate the online and preallocated modes with three response LLMs on a controlled adjacent-store benchmark and a public-corpus transfer track. Both modes keep transcript distinguishability near chance while preserving target-required personalization and overall response quality. Further diagnostics show that removing key safeguards causes mismatched output support, missing ledger charges, revealing side channels, or growing long-horizon leakage.

Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions. We present AgentPanel, a multi-agent forum for human--AI collaboration in scientific exploration. Heterogeneous agents asynchronously discuss scientific questions in a forum-style environment, while researchers can submit questions, browse and organize candidate ideas, engage agents in follow-up interactions, and optionally generate post-hoc summary reports. We evaluate AgentPanel in terms of idea quality, exploration breadth, interaction effectiveness, candidate-selection efficiency, and practical utility. Offline experiments show that AgentPanel outperforms a centralized multi-agent debate baseline. A human study with 20 participants further shows that users value AgentPanel for perspective diversity and exploration support. In experience-based comparisons with commonly used LLM tools, 65% of participants favored AgentPanel for both breadth of research directions and overall suitability for early-stage exploration. The platform is publicly available at https://agentpanel.cc/.

Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and generate patches. Yet most existing agents remain largely static after deployment, even though software development is a dynamic, feedback-rich process in which repositories evolve, dependencies change, tests fail, and repair attempts leave reusable experience. This tension has motivated a growing body of work on self-evolving coding agents, where the agent improves its future behavior by updating its framework, memory, skills, tools, models, or collaboration structures from prior coding interactions. In this survey, we provide a systematic synthesis of this emerging area. We first define self-evolving coding agents and distinguish them from conventional coding agents and general self-evolving agents. We then develop an object-centered taxonomy that characterizes what evolves in these systems, and complement it with two orthogonal perspectives: when evolution occurs and what software-specific evidence drives it. Across the literature, we find that executable feedback, repository-level context, and coding trajectories give software engineering a distinctive role as a natural domain for agent self-evolution, but also introduce new challenges in feedback reliability, benchmark overfitting, safety, maintainability, cost, and generalization. By organizing existing work around these dimensions, this survey aims to clarify the conceptual boundaries of self-evolving coding agents and provide a foundation for designing more adaptive, reliable, and software-aware agentic systems. The papers we collect can be found at https://github.com/zhouhao1024/Awesome-Self-Evolving-Coding-Agents.

Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks predominantly focus on single-turn full-page generation from scratch, overlooking the iterative workflow of real-world frontend engineering, where developers repeatedly reconstruct missing regions and modify localized elements within existing codebases. To bridge this gap, we introduce MT-Web2Code, the first multimodal coding benchmark for multi-turn Macro-Level Regional Reconstruction and Micro-Level Localized Modification, which contains 102 tasks spanning 16 vertical domains. To construct deterministic repair trajectories without costly turn-level human annotation, we develop a scalable Reverse-Corruption Trajectory Engine that iteratively injects structural and stylistic defects into golden pages. We further propose a dual-axis evaluation protocol that measures target-region fidelity and the preservation of unaffected content, where regional reconstruction is assessed by a 5-dimensional VLM-based rubric and localized modification by deterministic pixel-grounded alignment. Experiments on 13 frontier coding agents reveal that current agents struggle to faithfully reconstruct target regions while preserving unaffected content, lack fine-grained visual-code alignment for localized edits, and suffer from error snowballing over multiple turns. Beyond benchmarking, our deterministic evaluation metrics provide fine-grained feedback signals that may facilitate future research on training iterative UI coding agents. Our evaluation code and data will soon be released.

Large language models (LLMs), and the agents built on top of them, are now benchmarked heavily on whether they can finish a task — fix a bug, drive a browser, operate a GUI. A complementary social ability, namely how well a model understands and forecasts the way real social events unfold, has barely been measured. We introduce SocietyBench, an end-to-end benchmark that takes a one-line event topic, collects Web news and social-media posts across five platforms, distills them into a date-indexed timeline that keeps factual events and a public-opinion layer separate, and then turns every cutoff date on that timeline into an audited bank of forecasting questions. Questions are scored on two orthogonal 100-point axes: probability calibration and temporal accuracy. Before any model sees a timeline, a three-phase procedure replaces every named entity and shifts every date by a per-event constant, turning a real arc into a counterfactual social world — structurally identical to what happened, but stripped of the surface labels a model could match against pre-training memory. On five heterogeneous events and 125 prediction points in Chinese and English editions, the strongest of six frontier LLMs reaches only 75.0 out of 100, against a trivial anchor of 50. The two axes come apart: a model can be calibration-strong but time-weak, or the reverse. Three agent frameworks built on a shared base model fail to improve on that base, and two model-free heuristics trail every LLM. Per-event gaps reach 21.4 points on a single axis, which is our main argument for evaluating on several events rather than one. All anonymized timelines, question banks, ground truth, and scoring code are released.

Multi-agent studies commonly place AI agents in predefined games, markets, or roles, making it difficult to distinguish endogenous economic organization from behavior inherited from the scenario. We ask whether economic relations emerge when agents receive executable mechanisms for work, transfer, elections, and allocation but no prescribed social or economic strategy. We define AI Agent Economics as systems of production, allocation, consumption, exchange, and institutions that alter agents' future feasible actions. We develop a two-stage framework comprising a no-production boundary test and 24 independent six-agent worlds across GPT and DeepSeek. Without productive tasks, agents communicate and govern resource provision but show no substantive inter-agent transfer activity. With verified work and scarce task access, transfers, loans, access promises, vote-for-access exchanges, and allocation strategies emerge. Holding the election interface fixed, executable allocation authority increases differentiation while reducing failed allocation and prolonged exclusion. When energy becomes symbolic, continuation support disappears, yet competition over task access persists. These findings show that organization follows executable rights and resource consequences rather than role labels or prompt language, and motivate governance audits of the mechanisms that actually constrain agents' future actions.

Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS). Yet tutoring is long-horizon, since a learner improves over days and weeks rather than in a single turn, and no benchmark evaluates an agent tutor across a sustained relationship. We introduce EduClaw-Bench, a benchmark that places an agent tutor in a continuous 30-day relationship with a simulated learner grounded in knowledge tracing (KT), whose knowledge-concept mastery, from a KT model trained on real-student data, drives its answers and is probed for learning gain across 55 scenarios. Each agent is scored on three primary axes (learning gain, responsiveness, and helpfulness) and two curriculum-design axes (Gagné and Rosenshine), with helpfulness and the curriculum axes judged by a cross-family panel of three LLM judges. Evaluating 10 agent adapters over three base-model tiers yields two findings that single-tier, single-session evaluation cannot reach. First, tutoring quality belongs to the base model and the agent harness together rather than either alone. Second, almost no combination sustains good tutoring over the full horizon. A calibration check ($\text{ECE}=0.049$) and a live-classroom field study confirm that the simulated learner and its measurements track reality. Our work is a step toward trustworthy AI tutors for future education.

Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: sequential chunk-wise updates can overwrite early critical evidence with later irrelevant content, and serial inter-chunk dependencies limit parallelism and cause latency to increase with context length. To address these issues, we propose PI-Mem (Parallel-Iterative Memory), a mechanism that processes all chunks in parallel and iteratively refines a shared memory over a bounded number of turns. In each turn, PI-Mem reads all chunks in parallel conditioned on the current memory, selects new or complementary evidence from each chunk, and merges the selected evidence into a compact shared memory for the next turn. To discourage redundant turns, we optimize the workflow through reinforcement learning with an auxiliary turn-efficiency reward, enabling the model to adaptively exit once sufficient evidence has been accumulated. We evaluate PI-Mem with Qwen3.5-35B-A3B and Qwen2.5-7B on the HotpotQA benchmark across context lengths up to 3.6 million tokens and find that it outperforms the recurrent-memory baseline by +6.25 and +7.81 absolute points while achieving 6.1$\times$ and 2.1$\times$ inference speedups, respectively. These results demonstrate that PI-Mem breaks the accuracy--efficiency trade-off in long-context reasoning and provides a scalable approach to complex multi-hop question answering over extremely long documents.

Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool and orchestrating the order of calls. However, correctly filling the parameters of a tool call is equally critical for successful execution and has received far less attention. In domains such as cloud networking, even frontier models correctly complete fewer than half of tool calls. Inspired by recent analyses showing that LLM hidden states encode rich information about model predictions, we discover that while the model generates a parameter value, its hidden state contains a strong correctness signal: a simple linear probe can accurately predict whether the value will be correct. Based on this observation, we propose a unified probe-guided framework with two complementary approaches: probe-filtered bootstrapped training (PBT), which uses the probe to filter reliable self-generated calls for fine-tuning, and probe-guided reranking (PGR), which uses the probe to select better candidates during inference. To support systematic evaluation, we release ParamBench, a benchmark built from real cloud-network APIs that categorizes every instance into five difficulty levels according to parameter nesting depth, cross-parameter dependencies, and the reasoning required to derive values from earlier calls. Extensive experiments across 5 open models on ParamBench and 6 external benchmarks demonstrate that our method substantially improves parameter generation, raising the average exact match from 19.7% to 59.6%.

AI for Research (AI4Research) leverages AI to automate and improve scientific workflows. While experimental design is a critical stage of the research process, prior work has focused primarily on code implementation and execution, overlooking the importance of this stage, and no benchmark exists to evaluate AI's ability to conduct systematic experiment design. To bridge this gap, we propose SCOPE, a Scientific COmprehensive Planning Evaluation Benchmark constructed from 300 high-quality latest papers across 19 research domains from top-tier venues (e.g., ICML, NeurIPS, and ICLR),evaluating LLMs on two dimensions: High-Level planning completeness (main, ablation, and analysis experiments) and Low-Level configuration accuracy and rationality (datasets, baselines, and metrics). Benchmarking reveals three findings: (1) most LLMs cannot directly design high-quality experiments; (2) all LLMs exhibit a performance bottleneck in low-level configuration; and (3) search mode does not improve design quality. Furthermore, to address these challenges, we propose OptED, a novel agentic workflow to optimize LLM-based experimental design, that enhances LLM-based experimental planning through stage isolation, tool augmentation, and rule-based constraints, effectively alleviating the configuration bottleneck.

Large Language Model (LLM) agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how errors arise and propagate across intermediate reasoning stages. We present DiagChain, a diagnostic benchmark for evidence-grounded attack chain reconstruction that enables stage-wise evaluation of LLM agents. DiagChain includes MAIN-69, a suite of 69 scenarios spanning multiple operating systems, evidence noise levels, and chain lengths. It further introduces Evidence-Centric Retrieval-Augmented Generation (ECRAG), which couples evidence retrieval with an evolving structured representation of the reconstructed chain. Five complementary metrics are introduced to assess distinct stages of the reconstruction process and support systematic failure diagnosis. Based on evaluations using 6 LLMs, DiagChain reveals that even the strongest configuration succeeds on only 39.6% of the 849 reference steps in MAIN-69. Our analysis further shows that smaller models struggle with the more basic task of incorporating retrieved evidence into their outputs, whereas larger models can proceed to later steps, where correctly ordering that evidence becomes the main bottleneck. These results validate the importance of diagnostic evaluation beyond end-to-end accuracy and provide actionable insights for improving evidence-grounded cybersecurity agents.