每天知道
你的领域
出了什么

Context: Reflection is a fundamental skill in software engineering education, particularly in project-based courses where students learn through extended group work and need to develop their ability to reflect iteratively throughout their work. For students to benefit from reflection, their written reflections need to be assessed so that feedback can guide and improve their reflective practice. However, manually assessing written reflections to guide reflections is time-consuming, and often results in broad, non-specific feedback for a student to improve. Objective: This study builds on reflective writing frameworks to produce an eight-indicator scheme for assessing student reflections in software engineering. Furthermore, this study validates an automated classifier for assessing reflections against the framework, enabling scalable and structured feedback whilst reducing instructor workload. Method: We adapted existing reflection frameworks through iterative refinement to create our eight-indicator framework. Three annotators labelled student reflection texts, establishing moderate to reliable inter-rater agreement. We then trained and evaluated multiple encoder-only transformer models and compared them with decoder-only large language models using zero-shot prompting. Results: The fine-tuned RoBERTa model achieved the strongest performance, substantially outperforming decoder-only models in both accuracy and speed. The classifier demonstrated human-level agreement on most indicators whilst enabling near-instantaneous classification. We provide two model variants optimised for different assessment priorities. Conclusions: Our fine-tuned encoder-only models enable efficient automated assessment of reflective writing. The framework and automated classifier offer a means to provide timely, structured feedback on student reflections in software engineering.

Large language models (LLMs) often encounter conflicting prompts, although current instruction following benchmarks assess those meta-instructions in isolation, limiting the insights about how models process conflicting instructions. We introduce a framework PRIME(Prompt Resolution under Incompatible Meta-Instructions Evaluation) to analyze behavior of LLMs when provided with conflicting instructions. PRIME purposefully produces calibrated conflicts across response length, output format, and reasoning; classifying model responses with a deterministic behavioral taxonomy. We are evaluating five instruction tuned open weight LLMs in two distinct settings, balanced and naturally distributed. The conclusion we reach upon analysis is that conflict type is more significant in affecting behavior than model scale, and various failure modes across different categories of conflict. Our findings emphasize the value of developing conflict awareness and suggest ability of LLM to follow instructions cannot be assessed through isolated constraints alone.

Large language models have become capable reasoners and tool users that write and run code and search the literature, which makes automating the research process itself a realistic goal. We present PAPERCLAW, a harnessed multi-agent system that carries a project autonomously, from a field of study to a finished paper. PAPERCLAW curates a domain from a field's live literature, datasets, and code; brainstorms it into an idea with a pre-registered main-result contract; and drives a stoppable hypothesis map through an iterative propose, test, reflect loop that grows only from measured verdicts and halts once the evidence supports the idea, at which point it writes a venue-compliant paper. A full-lifecycle memory keeps each stage in a single living record, so a long run can be paused, inspected, and resumed without losing context. At the centre is an in-cycle research assistant with research tools and skills: it can drive the whole pipeline on its own, while the same interface lets a person step in at any stage, turning a first autonomous draft into a stronger paper through human-in-the-loop refinement. Throughout, PAPERCLAW keeps its output grounded and checkable, citing only references validated against open scholarly indexes and reporting results that genuinely ran. An evaluation with an LLM judge finds that PAPERCLAW produces strong papers both fully autonomously and with human-in-the-loop refinement.

Agent skills have become a practical way to extend large language model agents, but the growing skill ecosystem still lacks a reliable way to judge whether a skill is worth deploying. Existing evaluation methods remain largely anchored to fixed task suites, assessing skills through performance on predefined tasks and environments. As skill marketplaces expand, this paradigm becomes inadequate: fixed suites can conflate a skill's marginal contribution with backbone strength and miss its value when tasks fall outside the skill's intended scope. We introduce SkillAudit, an end-to-end framework for skill-centered assessment that takes an arbitrary agent skill as input and automatically generates a comprehensive, multi-dimensional evaluation report spanning utility, efficiency/cost, and safety. SkillAudit focuses on the skill artifact itself and constructs capability-aligned evaluation tasks directly from the skill package. The generated tasks are conducted in isolated sandbox environments to collect execution evidence, followed by automated checks with LLM-based judging to produce auditable results. To dissect the agent skills, we propose the baseline comparison principle to measure utility and efficiency/cost, and introduce a two-stage detection paradigm combining static semantic analysis with dynamic runtime verification to assess safety risks. After scanning top-ranked real-world skill packages spanning 23 occupational categories, we found that over 7% of skills are at risky status.

Multimodal Large Language Models (MLLMs) have achieved remarkable performance on 2D visual tasks, yet enhancing their spatial intelligence for real-world applications such as Autonomous Vehicles (AV) remains an open challenge. Existing geometry-aware MLLMs typically rely on auxiliary 3D models at inference time, introducing pipeline complexity and the risk of cascading failures. In this paper, we present OmniSpace, a simple yet effective plug-and-play paradigm for geometry-aware spatial reasoning from purely 2D observations. Motivated by our finding that current MLLMs are bottlenecked by weak cross-view correspondence and depth estimation, OmniSpace introduces a Camera Pose Injector, a Multi-view Epipolar Attention module, and a 3D Geometric Distillation objective that jointly address these two limitations by transferring geometric knowledge into the model. Extensive experiments show that OmniSpace surpasses existing methods on planning benchmarks (nuScenes, Bench2Drive), risk detection (nuInstruct), language (Omnidrive), and generalization (DriveBench).

Automated vulnerability repair has emerged as a promising direction to mitigate the growing number of software vulnerabilities. Recent advances in Large Language Models (LLMs) have further accelerated research in automated repair. However, existing frameworks remain largely restricted to memory-related vulnerabilities and locally repairable vulnerability settings, leaving generalization to unseen vulnerability types underexplored. Their evaluations are often limited to a single programming language, and largely rely on proprietary models. In this paper, we propose RAVEN, a scalable, efficient and autonomous framework that integrates an agentic retrieval-augmented generation (RAG) pipeline with controlled iterative repair in a unified framework. The framework utilizes open-source LLMs in a fully locally deployable setting with limited GPU requirements, while building a multi-faceted retrieval pipeline to retrieve historically relevant vulnerability fixes and guide the patch generation. In addition, RAVEN introduces a dedicated Curator Agent that retrieves cross-file dependencies from the target repository, to fix complex vulnerabilities that cannot be addressed using local vulnerable code alone. We evaluate RAVEN on 160 real-world CVE vulnerabilities across diverse vulnerability types, two programming languages, unseen CWE categories, and out-of-distribution settings. RAVEN achieves an overall repair success rate of 83.13%, outperforming all existing state-of-the-art repair frameworks, while also demonstrating strong generalization capabilities and maintaining the repair cost negligible.

Modern web applications increasingly combine three ingredients that are hard to test: output from large language models, multi-market internationalization, and browser-driven front-ends over external data sources. We report on a production rental-search assistant whose automated suite grew to 1,553 test cases in six weeks. The suite passed continuously, yet user-facing defects continued to reach production. We studied all 252 bug-fix commits in the project and classified each by the boundary, or seam, it escaped through. About 44 percent of the fixes fall in four seams that component-level unit tests cannot observe: the live browser runtime, the non-default market, the end-to-end flow, and the whole-system level. A fix without a guard at the seam let one defect ship twice. We present the four-seam framework, the measured defect distribution, and the practices we adopted, including a simple way for a team to find the seam that carries the most fixes.

Large Language Models (LLMs) achieve remarkable reasoning capabilities through reinforcement learning (RL) post-training. However, existing RL post-training commonly relies on uniform data sampling, which ignores the semantic structure of the training data and the changing capability of the training policy. To address these limitations, we propose Adaptive Data Scheduling (ADS), a dual-level data scheduling framework for pacing RL post-training that replaces uniform sampling with an adaptive distribution over semantic clusters and policy-boundary sample selection. At the cluster level, ADS organizes samples according to semantic patterns and maintains an adaptive inter-cluster distribution to solidify current training progress. At the sample level, ADS performs intra-cluster scheduling to continuously sample policy-boundary samples, which provides informative relative advantages. Experimental results across three LLMs and seven reasoning benchmarks demonstrate that ADS improves average accuracy by 5.2% over Group Relative Policy Optimization (GRPO). Notably, ADS consistently improves RL methods with different objective designs, highlighting its potential as a general data scheduling strategy for LLM RL post-training. The source code is available at: https://github.com/Richard-zrx/ADS.

Large Language Models (LLMs) provide a new opportunity to study how language shapes exploratory cognition because conversational strategies can be systematically manipulated at inference time. We introduce CURIOBOT, a framework that operationalizes Berlyne's collative variables, novelty, complexity, conflict, and uncertainty, as adaptive linguistic interventions for conversational tutoring. Across 270 tutoring conversations spanning multiple model families, domains, and topic complexity levels, curiosity-oriented interventions consistently increased exploratory learner behaviors, producing up to 2.4x more conversational turns under fixed time budgets. To measure these effects, we further introduce a learner-centered evaluation framework capturing exploratory questioning, conversational agency, productive struggle, and observable curiosity. Learner-side gains persisted even when tutor-side instructional quality remained unchanged, suggesting that curiosity functions as a partially independent interaction-level mechanism. More broadly, our results demonstrate that LLM-mediated dialogue can serve as a scalable experimental framework for studying how language shapes exploratory learning behavior.

In the rapidly evolving field of software development, code stylometry analyzing unique stylistic signatures of programmers plays a crit-ical role in authorship attribution and cybersecurity. Recent advancements in artificial intelligence, particularly Large Language Models (LLMs) like GPT-3.5 and GPT-4, have introduced new dimensions to this field, challenging traditional stylometry techniques. This study investigates the effectiveness of LLMs in altering code stylometry while preserving functionality and evaluates the impact of various prompt engineering strategies. Through comprehensive experiments, we assess how well these models can obscure stylistic signatures to avoid detection by a Random Forest classifier trained for authorship attribution. The results reveal significant differences in effectiveness between single-shot and multi-shot methods and highlight the importance of detailed, structured prompts. Additionally, functionality preservation checks demonstrate the challenges in maintaining code integrity post-modification. This research provides critical insights into the robustness of authorship attribution techniques against advanced AI capabilities, informing future cybersecurity and software engineering developments

Generative models have revolutionized the process of materials discovery, yet they often fail to satisfy underlying physical causality. Through an analysis of Large Language Models (LLMs) augmented with knowledge graphs derived from current literature, we uncover a phenomenon termed contextual tunneling, where models "over-anchor" on narrow, retrieved evidence while suppressing global physical reasoning. To address this problem, we introduce ARIA, a causal-aware framework that conditions knowledge use on mechanistic completeness. ARIA routes each query through a three-tier cascade: (i) direct causal reasoning when complete evidence chains of Process-Structure-Property (PSP) are available, (ii) physics-informed analogical transfer for sparse or novel material systems, and (iii) explicit parametric fallback when external evidence is incomplete. As a proof of concept, we construct a Knowledge Graph (KG) containing 2,839 extracted PSP relations from peer-reviewed articles in the materials literature and evaluate ARIA on forward prediction and inverse design tasks for two-dimensional (2D) materials. ARIA mitigates contextual tunneling, improves over unaugmented and naive KG-augmented baselines, and provides further gains when an online literature search is used for evidence enrichment. Crucially, ARIA produces auditable causal traces, enabling physically grounded and trustworthy AI-assisted materials discovery.

Attention mechanisms have demonstrated remarkable empirical success in identifying relevant information from large collections of tokens, yet the theoretical principles underlying this behavior remain poorly understood. We study a stylized softmax-attention model in which a query vector is learned by stochastic gradient ascent from a collection of informative and nuisance tokens. Exploiting the symmetry of the model, we derive a population objective and characterize the limiting ordinary differential equation governing the learning dynamics. Using tools from stochastic approximation and dynamical systems theory, we establish a rigorous connection between the stochastic learning algorithm and its deterministic limit. Our main result shows that, under suitable high-dimensional scaling assumptions and standard step-size conditions, the learned query converges almost surely to the one-dimensional signal subspace spanned by the latent informative direction. Equivalently, the query asymptotically recovers the latent signal up to the intrinsic sign ambiguity. These results provide a rigorous theoretical foundation for understanding attention mechanisms as signal extraction procedures in high-dimensional noisy environments and offer a dynamical-systems perspective on how attention discovers relevant information in the presence of substantial noise.

Because large language models (LLMs) are impressively successful in predicting text, it appears that they must have access to a 'world model' representing causal and definitional structure. However, the dominant formalisms of modern causal inference — Judea Pearl's interventionist approach and the Neyman-Rubin potential outcomes framework — struggle to illuminate how LLMs learn causal structure. I resolve this puzzle by arguing that LLMs employ a specific inductive approach based on a difference-making logic — sometimes called variational induction. I demonstrate how central aspects of this logic are realized during training, where LLMs require enormous amounts of text data from a wide range of contexts to identify difference- and indifference-makers within word sequences. Furthermore, I analyze specific architectural features of LLMs — such as token embeddings and self-attention — to determine their roles in variational induction. The difference-making logic of LLMs fundamentally parallels the experimental method, where causal relations are derived by systematically varying individual circumstances to determine their influence on a phenomenon.

In open-ended generation, LLMs frequently fall into the "likelihood trap", marked by repetitive degeneration and vocabulary dullness, creating a discrepancy between machine-generated and human-written text. While post-hoc tail truncation (e.g., Top-$p$, Min-$p$) avoids sampling from the unreliable tail, it can over-sample from the uncalibrated head and misalign generation with human lexical preferences; fixed scalar repetition penalties likewise ignore variation in logit scale across inference steps, potentially disrupting semantic coherence. To address both limitations, we propose Variance-Calibrated Modulation (VCM), a training-free pre-decoding intervention that reshapes the probability distribution before truncation through two dynamic mechanisms: (1) Contextual Searchlight via PMI, which suppresses global stopwords while elevating context-evoked tokens, and (2) Adaptive Self-Debiasing, which uses real-time logit standard deviation for scale-invariant penalization. Across open-ended generation, factual QA, and mathematical reasoning, VCM consistently mitigates the likelihood trap. With negligible computational overhead, VCM integrates with existing decoding strategies, improving diversity, coherence, and, particularly at higher decoding temperatures, reasoning accuracy.

Alignment tuning is meant to make harmful-request refusal robust, yet this safety behavior can be erased by a small set of benign fine-tuning examples. This is a deployment risk for open-weight models because a checkpoint can pass refusal tests at release time and later lose refusal under low-cost downstream fine-tuning. Prior work has established these refusal failures, but existing studies do not show how to detect this fragility in the aligned model itself before an attack or fine-tuning intervention is run. We introduce Skin-Deep, a geometric diagnostic that detects alignment fragility directly from the aligned model's hidden-state activations before such an intervention is run and compresses the layer-wise safety geometry into a single scalar, the Geometric Fragility Score (GFS). Applied to twenty-one instruction-tuned models spanning six alignment recipes and 3B--32B parameters, Skin-Deep reveals a recurring low-rank safety subspace across model families. Direction ablations show that removing directions in this subspace weakens harmful-request refusal, providing causal evidence that the recovered geometry underlies refusal behavior. Crucially, GFS identifies, before any fine-tuning, the initially safe model that retains the most refusal after small-scale LoRA fine-tuning. These results establish GFS as a practical pre-deployment diagnostic for flagging fragile refusal behavior without running an attack.

Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucinated computer-processable rules. This paper introduces P4IR, a two-stage framework that uses supervised fine-tuning (SFT) to instill domain knowledge in an LLM, followed by Group Relative Policy Optimization (GRPO) to improve the accuracy of the generated intermediate representations in the form of high-level code skeletons. The framework achieved reductions of up to 23.8% and 38.6% in tree edit distance and token-level Levenshtein distance respectively, relative to the SFT baselines. Comparative analysis demonstrates that this approach in a zero-shot setting outperforms leading LLMs in both code structure and semantics, specifically Claude Opus and Sonnet 4.5, GPT-5.2, Qwen-3-Max, and GLM-4.7, evaluated via few-shot prompting. Additionally, the GRPO stage produced a small yet statistically significant reduction in false positives. By combining SFT with GRPO to optimize directly for domain-specific objectives, this approach offers a path toward more accurate and reliable LLM-based ACC systems.

As LLM-powered scams proliferate, black-box forensics for conversational LLM agents offers a path to accountability for systems hidden behind anonymous endpoints. Identifying the base model behind a chatbot endpoint (attribution), without model parameter access or knowledge of the hidden system prompt, would let investigators trace AI-enabled scams back to the providers whose models power them. Detecting when two endpoints run the exact same system prompt (fingerprinting), even one novel and unseen, would link individual scams into criminal networks and expose silent API changes. We conduct an empirical investigation of both capabilities. Our attribution classifiers identify the base model behind an agent with 98% accuracy from a few turns of non-adversarial conversation. Attribution of system prompts, while possible, requires retraining on a large amount of data for each prompt; system prompts in the wild are unbounded and ever-changing, making this approach costly. To tackle this more open-ended setting, our cross-encoder fingerprinting method achieves an AUC of 0.768 and an F1 of 0.703 on entirely unseen system prompts, and aggregating 50 interaction conversations from each target agent boosts AUC to 0.943. Conversational agents with unseen system prompts can thus be fingerprinted with robust accuracy from a few turns of ordinary conversation.

Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget. We show that this context-management layer is a safety-critical failure surface: in-context governance constraints that agents reliably obey while visible can be silently removed by compaction, causing the same agent to perform prohibited tool actions later in the session. We call this failure mode Governance Decay. We introduce ConstraintRot, a benchmark of long-horizon agent scenarios with deterministic tool-call grading, and measure compaction-induced violations across seven model families. Across 1,323 episodes, violation rises from 0% with the policy in full context to 30% after compaction, reaching 59% for some models; when the constraint survives the summary, violation remains 0%, but when it is dropped, violation reaches 38%. We further study a Compaction-Eviction Attack, in which adversarial in-context content biases the summarizer to omit a legitimate policy, and show that optimized injections defeat every evaluated model. Finally, we propose Constraint Pinning, a simple training-free mitigation that quarantines governance constraints from lossy compaction and restores violation to 0% in our benchmark. These results identify context management as a first-class governance surface for deployed LLM agents.

LLM-as-a-judge has become the dominant approach to scalable evaluation in NLP pipelines, yet judges themselves carry systematic biases that raw accuracy hides: they favor responses placed in slot A (position bias), they prefer longer responses regardless of quality (verbosity bias), and their reliability degrades sharply in lower-resource languages. We introduce BabelJudge, an open-source benchmark and reliability audit framework that measures all four failure modes — position bias, verbosity bias, order inconsistency, and cross-lingual degradation — on any judge model, without requiring human preference labels. The key insight is gold-labelling by degradation: starting from a high-quality reference response and applying a controlled perturbation yields a pairwise item whose gold label is known by construction, eliminating annotation cost. We evaluate Qwen2.5-7B-Instruct-4bit across English, Hindi, Arabic, and Swahili and find that our composite bias-penalised reliability score drops from 0.714 in Hindi to 0.550 in Swahili, a gap that raw accuracy (0.835 vs. 0.660) understates. Swahili order consistency collapses to 0.480, meaning judge verdicts are near-random under slot-order swaps — a failure mode invisible to accuracy alone. We further extend the framework to agentic evaluation via nine trajectory-level perturbations (argument corruption, tool swaps, hallucinated calls, missing steps) and three new metrics: tool accuracy, hallucination detection rate, and trajectory-length bias. BabelJudge is released as a Python package supporting 11 judge backends. Code: https://github.com/Shreyaskc/BabelJudge

External skills can improve action-oriented LLM agents without changing model weights, but persistent skill updates are risky when they are distilled from sparse or noisy trajectories. A plausible reflection may encode a useful procedure, a spurious shortcut, or a rule that the target executor cannot reliably follow. We propose Hypothesis-Driven Skill Optimization (HDSO), a train-free framework in which both the skill curator and the agent executor are frozen inference endpoints. The curator observes executor traces, proposes a falsifiable hypothesis with an explicit validation plan, instantiates the hypothesis as a candidate skill package, validates the package through paired control/treatment executions, reviews behavior differences, and consolidates only supported candidates into an approved repository. The executor consumes approved skills through progressive disclosure, preserving the executor-only path when no skill is selected. On ALFWorld, HDSO improves executor-only baselines by +6.9 Avg. SR points for Qwen3-8B and +4.0 points for Qwen3.6-27B. Under 20% randomly flipped success/failure feedback during skill discovery and validation, HDSO preserves a +7.1-point gain for Qwen3-8B. Transfer and heterogeneous-pair diagnostics further show that validated repositories can be useful beyond the run that produced them, but cross-model curation succeeds only when curator diagnosis, executor capability, and validation evidence align. HDSO provides an auditable skill lifecycle for frozen action agents rather than an unconstrained memory accumulation procedure.

Generative music systems can now produce impressive audio from text prompts, but audio outputs are difficult to inspect, edit, and diagnose as musical structure. We introduce Libretto, an agent-facing framework for symbolic music generation and revision. Libretto uses an LLM-native grammar with explicit onset slots, voices, and bar-level organization, then evaluates each piece in a corpus-calibrated statistical space over rhythm, harmony, melody, texture, form, and variation. The same structural axes support retrieval, diagnosis, copy-risk control, and iterative self-revision. Across gap filling, reference-guided full-piece generation, gradual morphing, and educational music generation, Libretto turns symbolic music from a raw token sequence into a measurable and editable object for language-model agents.

Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-world software engineering tasks. Existing benchmarks evaluate these agents almost exclusively on outcome correctness: whether generated code passes tests or resolves issues. We argue that this outcome-only lens is insufficient: an agent that arrives at a correct solution through reckless trial-and-error, without planning, verification, or graceful recovery, is fundamentally less reliable than one that follows sound engineering discipline. We introduce RigorBench, the first benchmark designed to measure process discipline in AI coding agents. RigorBench evaluates these harnesses across five pillars: Planning Fidelity, Verification Coverage, Recovery Efficiency, Abstention Quality, and Atomic Transition Integrity. A composite RigorScore aggregates these dimensions into a single metric via a weighted sum. We curate a suite of 30 tasks spanning five categories - Plan-Then-Build, Verify-Or-Die, Doom Loop Gauntlet, Know When to Fold, and Don't Break the Build-and evaluate leading harnesses in a controlled with/without experimental design against baseline coding assistants. Our results show that structured process discipline not only improves process quality scores by an average of 41% but also raises downstream outcome correctness by 17%, providing the first quantitative evidence that how agents code matters as much as what they produce. We release the full benchmark, scoring rubrics, and trajectory analysis tools as open-source artifacts.

No single market strategy always wins: momentum, mean reversion, risk control,and event-driven rules can each succeed or fail as market conditions change.Rather than asking large language models to directly generate market actions,we study an executable decision paradigm where an agent selects from a library of programmatic strategies, each implemented as a code module mapping market observations to actions.We propose MetaPS, a simulation-guided framework for adaptive programmatic strategy selection. MetaPS rolls out candidate strategies in simulated or backtested markets, identifies states where particular strategies lead to better future outcomes, and converts these state--strategy pairs into supervised fine-tuning data. During inference, the simulator is no longer queried: MetaPS observes only the current market state and candidate strategy context, selects a suitable strategy program, and the selected program produces the final action. Experiments on multi-stock trading and a controlled goods-exchange sandbox show that MetaPS consistently improves across model scales from 0.8B to 9B parameters. It outperforms fixed-strategy baselines, direct decision-making agents, and prompted API-based LLM agents; in several settings, compact fine-tuned models even surpass stronger API models. These results demonstrate that market simulations can provide scalable and targeted supervision for learning adaptive, interpretable, and executable strategy selection.

Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn interactions with external environments. Existing safety mechanisms mainly rely on external guardrails, which have a limited ability to perform fine-grained behavioral control during execution. Meanwhile, recent mechanistic interpretability methods for LLM safety are mostly confined to single-turn or jailbreak-style QA settings, limiting their ability to capture the evolving risk dynamics of multi-turn agent execution. In this paper, we investigate the safety of multi-turn coding agents from an internal perspective. We propose AgentLens (Mechanistic Subspace Intervention and Steering), a white-box defense framework that performs runtime safety detection and representation-level mitigation for coding agents. Unlike conventional agent guardrails, AgentLens detect harmful execution states from step-level hidden representations and mitigate unsafe behavior by intervening in a 10-dimensional subspace within a single layer. To support this research, we introduce the Mechanistic Agent Safety (MAS) benchmark, comprising comprehensively annotated multi-turn execution trajectories across 194 tasks using LLaMA-3.1-8B, Qwen-2.5-7B, and Gemma-2-9B. Extensive experiments show that AgentLens achieves strong safety detection performance, provides preliminary evidence for lookahead risk anticipation, and substantially reduces harmful actions of the coding agent, establishing a foundation for applying mechanistic interpretability to dynamic LLM agent safety. The code is available at: https://github.com/EddyLuo1232/AgentLens

Multi-agent reinforcement learning (MARL)-based techniques have shown promise for GUI testing. However, as the complexity of modern GUI software increases, existing MARL-based approaches (e.g., MARG and Fastbot) struggle to scale due to the inherent limitations of their underlying tabular reinforcement learning algorithms. This limits their applicability to large-scale commercial GUI software, especially web applications with vast state spaces and many interactive elements. To fill this gap, we propose WebCQ, a novel MARL-based approach for scalable web GUI testing. WebCQ incorporates QTRAN for multi-agent coordination and a lightweight synchronization mechanism, allowing it to work under asynchronous web testing scenarios. It extracts semantic and exploration features for each UI event to form an action vector. This vector is concatenated with the current state vector and fed into the policy network, enabling DQN-based decision making within a dynamic action space. We evaluated WebCQ on eight large-scale commercial websites. Under the same time budget and agent count, WebCQ explored 33.3% more states and executed 42.2% more unique actions than MARG, while triggering more failures on six of the eight websites under test. It also demonstrated strong scalability, maintaining higher action throughput during 20-hour experiments, and achieving greater performance improvements as the number of agents increased. These results show that WebCQovercomes key limitations of existing MARL-based approaches, providing a scalable and effective solution for enhancing modern web GUI testing.

LLM agents increasingly operate in large tool ecosystems, where real-world tasks require discovering relevant tools, inferring implicit sub-goals, and adapting to dynamic environments over long horizons. However, existing benchmarks rarely evaluate planning under retrieval-limited tool visibility. To address this gap, we introduce PlanBench-XL, an interactive benchmark of 327 retail tasks over 1,665 tools that tests whether agents can iteratively retrieve usable tools, invoke them to uncover intermediate evidence for subsequent calls toward the final goal. PlanBench-XL further features an optional blocking mechanism that simulates real-world unpredictability through missing, failing, or distracting tool functions, forcing agents to detect disrupted paths and adapt at runtime. Experiments on ten leading LLMs show that massive-tool planning remains challenging: while GPT-5.4 achieves 51.90% accuracy in block-free settings, it collapses to 11.36% under the most severe blocking condition. Further analysis shows that agents are especially vulnerable when failures lack explicit error signals or when recovery requires longer alternative tool-use paths. These results establish PlanBench-XL as a testbed for diagnosing agentic planning failures and highlight the need for robust adaptive planning in long-horizon tasks with large, imperfect tool environments.

This work investigates the safe exploration problem in reinforcement learning, where an agent must maximize cumulative performance while simultaneously satisfying safety constraints. This challenge becomes even more pronounced in long-horizon tasks, where existing safe methods face fundamental limitations due to compounding estimation errors and restricted exploration capabilities. To address this problem, we propose a method that combines a learnable world model with two complementary policies a high-level policy and a low-level policy to promote safety at both hierarchical levels. The high-level policy generates intermediate subgoals that bias exploration toward safe regions, while the low-level policy uses imagined rollouts in the learned world model to reduce unsafe behaviors when reaching these subgoals. The proposed method was evaluated on challenging long-horizon navigation and manipulation tasks with high-dimensional action spaces, where it significantly outperforms existing Safe RL baselines in both success rate and strong empirical constraint satisfaction, consistently meeting the prescribed safety budget across seeds, while prior approaches fail to effectively solve these complex long-horizon scenarios.

Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, their application to online RL remains limited by the challenge of scalable training in the absence of ground-truth data, where standard optimization techniques such as score matching are not directly applicable. In this work, we introduce a highly efficient algorithm for optimizing diffusion policies by leveraging recent advances in stochastic optimal control. Our approach is based on adjoint matching, which enables simulation-free training and circumvents the need for explicit likelihood estimation or costly backpropagation through the diffusion process. Furthermore, we propose several extensions that improve the robustness and stability of the method in practical settings. Empirical results demonstrate that our approach achieves competitive performance while significantly reducing computational overhead, making diffusion policies more viable for online RL scenarios.

A key bottleneck in training generalist policies for bimanual dexterous manipulation is the lack of large-scale, high-quality datasets. Synthetic data generation in simulation provides a scalable alternative to human video demonstrations by overcoming challenges such as morphology mismatch, missing physical interactions, and the generation of robot actions. However, existing approaches based on human teleoperation offer limited task diversity, as object-centric trajectory matching often neglects the feasibility of robot execution. Reinforcement learning (RL) enables broader scalability but is often constrained by handcrafted, task-specific rewards. In this work, we propose a systematic RL-based data generation pipeline that integrates generalizable reward design, effective domain randomization, and language-conditioned task annotations. This pipeline synthesizes diverse, high-quality datasets for dexterous bimanual manipulation and enables training of language-conditioned multi-task policies. Our experiments show that the generated data significantly improves generalization across three representative manipulation tasks.

Consistency distillation has significantly accelerated the inference of diffusion models. In this work, we reveal an intriguing asymmetry: while Logit-Normal sampling priors are highly efficacious for standard iterative generation, consistency distillation exhibits a distinctly different difficulty profile (e.g., U-shaped). We identify that the primary optimization bottlenecks reside at the boundary stages (initialization or final refinement) rather than the intermediate steps. To address the limitations of static sampling in accommodating evolving learning requirements, we propose Curvature-Adaptive Consistency Flow Matching (CACFM). By formulating distillation as a dynamic decision process, CACFM employs a lightweight Reinforcement Learning agent to actively probe Probability Flow ODE trajectories, automatically constructing an efficiency-oriented curriculum that prioritizes critical regions without manual scheduling. Integrated with a novel Flow Distribution Matching Distillation (DMD) objective, our approach achieves new state-of-the-art results on large-scale models such as FLUX and SDXL. It effectively mitigates structural deformities and preserves high-frequency details in extreme few-step regimes, achieving unprecedented visual fidelity.