AI Agent Benchmarks

Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced within a constrained workflow as the unit of evaluation. We introduce SQBench, a benchmark for evaluating production-oriented task delivery by language-model agents. SQBench v1.0 contains 220 standardized tasks organized into L1 atomic capabilities, L2 composite skills, and L3 business scenarios. Each task requires an agent to process input assets, use available tools, and produce an explicitly specified deliverable. The evaluation first computes functional Completion and then derives Risk Penalty and Performance from independently evidenced triggers in a 10D Risk Matrix. A Strict Pass requires Completion = 1 and Risk Penalty = 0. We evaluate 27 model configurations under a common protocol, with one run per configuration-task pair. The highest prespecified Weighted Pass@1 is 60.5%. Mean Strict Pass@1 on L3 is 18.5%, and every configuration performs worse on L3 than on both L1 and L2, indicating that delivery under domain constraints is a shared weakness within the current task set. Of 2,348 results with Completion = 1, 113 (4.8%) fail the Strict Pass criterion because of risks such as unverifiable citations, inappropriate resource use, or format violations. These results show that functional completion alone does not fully characterize delivery quality and that risk determinations should be reported separately.

Adding procedural skills to an LLM agent is typically evaluated by average improvement in task success. However, this metric hides an important cost: skills can also make agents worse. We measure both sides by comparing agents with and without skills across nearly 6,000 runs spanning two office automation benchmarks and three model harness stacks. This allows us to distinguish two outcomes. A regression is a task solved without skills but failed after skills are added. A residual failure is a task that fails both with and without skills. We find that regressions are substantial enough that the best performing skills outperform others primarily by regressing less, not by gaining more. We identify three causes of regression: (i) skill description osmosis, a skill changes an agent's behavior simply by being present in context, even when it is never invoked; (ii) grounding displacement, a skill's prescribed procedure overrides how the agent interprets its inputs; and (iii) verification displacement, where the procedure suppresses checks the agent would otherwise perform on its outputs. Analysing persistent failures reveals the same underlying pattern. Existing skills overemphasize procedural guidance the stage least often responsible for failure while under supporting grounding and verification, the dominant sources of remaining errors. After correcting evaluation artifacts and studying traces, we find many regressions and persistent failures recoverable through better grounding and verification. Procedural skills should be evaluated by decomposing their net effect into gains and regressions, not by aggregate improvement alone. We identify three regression modes skills should avoid, and find that reliability depends more on grounding and verification than on procedural skill choice.

Vision-language model (VLM) agents increasingly use tools to act on 3D scenes rather than only describe them. Existing 3D benchmarks score textual responses or single-object operations, leaving agent action on complete multi-object 3D scenes under evaluated. We present SceneActBench, a benchmark for visually conditioned action across five 3D tasks under a unified agent-environment loop. Given PNG images or sampled video frames and, where applicable, supplied 3D assets, an agent acts on a 3D environment. We evaluate each final output against hidden ground truth with task-specific geometric metrics. SceneActBench comprises five tasks built from 210 source instances, yielding 520 task cases including paired input conditions. Every task runs through one fixed agent loop to keep the comparison fair. Across eleven proprietary VLM configurations, Overall scores span 38.6-50.2, and none performs consistently well across tasks. We further analyse where and how failures manifest.

Agent benchmarks increasingly evaluate repository editing, web research, terminal use, and long-horizon interaction. Their scores support capability claims only when the evaluation protocol keeps the intended capability necessary for success. Recent reward-hacking benchmarks and system reports show that agents can instead recover public solutions, read evaluation artifacts, infer generator structure, manipulate feedback, or benefit from invalid scoring paths; existing responses do not provide a common procedure for attributing these shortcuts and quantifying their effect across benchmarks. We formulate protocol validity and introduce HackDetect, a post-hoc audit that identifies an exposure, determines how the agent used it, and assesses whether the resulting score is misleading. We quantify score inflation with the Mislead gap, defined as the exploit score minus the intended score. We audit 2,385 traces across 15 agent benchmarks and find evidence of exposures and reward hacking in 67.0% of Frontier Science traces and 66.7% of AutoLab tasks. Across paired comparisons, we measure score inflation of 0.45-1.00, showing that benchmark reports should provide evidence that scores reflect the intended capability.

LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation and production operations: live-environment fidelity (multi-turn read-write interaction with a running database); observation-space scale and complexity (causal diagnosis across thousands of time series, business logs, and concurrent activity); solution-space openness (multiple remediations with different operational trade-offs); and scenario complexity and coverage (faults cascading across internal mechanisms and operational domains). We present DBA-Bench, a benchmark addressing these gaps through production fidelity, outcome-first evaluation, and controlled scenario reproducibility. It uses instrumented PostgreSQL environments with active workloads, persistent state, and multi-source observations; defines success by measurable recovery or fault elimination under safety constraints; and restores snapshots with scenario-specific checks before each run. The benchmark contains 106 scenarios across seven task domains, with two public difficulty labels based on reference-path diagnostic depth and environmental complexity. We evaluate nine baseline groups, including six foundation-model systems, two GPT-5.5-backed database agents, and a Human DBA reference. Across 848 automated runs, Diagnosis, Outcome, and Safe Pass rates are 32.7%, 19.6%, and 12.4%; the best automated baseline reaches 17.9% Safe Pass versus 93.4% for the Human DBA reference. Automated Safe Pass falls from 19.6% on Easy scenarios to 7.6% on Hard scenarios, underscoring the difficulty of safe end-to-end remediation.

Multimodal Large Language Models (MLLMs) are emerging as core reasoning modules for embodied agents, yet it remains unclear how well general-purpose models can solve long-horizon embodied tasks from a single high-level instruction. We introduce MissionBench, a benchmark for mission-level evaluation of MLLMs in aerial 3D environments. It comprises 120 missions across five simulated 3D environments and four task families. Agents must autonomously plan, navigate, and report outcomes using only egocentric observations and its action history, without aerial-specific fine-tuning. Across 22 open- and closed-source MLLMs, the strongest model succeeds on fewer than 35% of missions compared to 84.4% human performance, highlighting the difficulty of multi-step embodied tasks. Despite large variations between model families, we observe gains from scaling, indicating that larger general-purpose models possess stronger zero-shot embodied capabilities. Our analysis shows that mission-level competence requires coordinating multiple capabilities beyond spatial perception, including multi-step planning and adaptive reasoning. This motivates closed-loop evaluation and highlights both the promise and risk of scaling-driven improvements for embodied AI.

Large language model (LLM) agents increasingly perform commercial tasks that involve retrieving external content, such as images, and, where appropriate, reproducing that content. LLM agents should comply with the law, including copyright law. Presently, however, we lack adequate frameworks to assess whether they do so in practice. To that end, we introduce Copyright-Bench, a benchmark designed to evaluate LLM agents' compliance with copyright law. Copyright-Bench comprises realistic commercial tasks---website development, merchandise design, and pitch deck production---that involve agents selecting between public-domain content, the use of which is legal, and copyrighted content, the use of which is infringing in this setting. The evaluation introduces prompt variations that simulate different user preferences, as well as time pressure. Comparing state-of-the-art LLM agents against a human baseline, we find that: (1) agents select copyrighted works despite the availability of public-domain alternatives; and (2) for open-weight models, violation rates increase in response to certain user preferences and simulated time pressure.

Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in 0.3-3.4% of traces, implicating only a handful of models. We present a controlled prompt-ablation study across 22 frontier models from 7 providers on 23 Cybench capture-the-flag (CTF) challenges under three prompt conditions (no anti-cheat, standard, severe). All 1,518 task traces were individually audited through a four-stage pipeline combining LLM-as-a-judge classification, programmatic verification, judge-verifier reconciliation, and human review. We find cheating is far more pervasive than previously estimated: under baseline conditions, 37.1% of passes involved cheating, 21 of 22 models cheated, and scores were inflated by up to 5x. Anti-cheat prompts reduce cheat propensity from 33.0% (baseline) to 17.8% (standard) to 8.5% (severe) without degrading, and sometimes improving, solve rates. However, even under the most restrictive prompt condition, eight models still produced cheated passes, four showed backfire effects, and cheating escalated from web search toward infrastructure probing. We introduce the "solve rate" metric (clean passes only) to distinguish genuine capability from cheated outcomes, and argue it should be standard practice in any evaluation where cheating vectors are available. Anti-cheat prompts are an effective and essentially free first layer of defense, but they are not a substitute for environmental controls.

Large language models (LLMs) and agents are now widely used tools in code development, with data typically sent to third-party cloud-based models. Their adoption in research using personal data is constrained by governance requirements that typically prohibit data transmission to external services. Locally deployable open-weight models offer an alternative since sensitive data never leave the local environment. We introduce an open-source framework for evaluating the efficacy of AI agents powered by open-weight LLMs on one of the most persistent bottlenecks in research on longitudinal population studies: data preparation. The framework comprises: a curated ground-truth dataset (cleaning scripts preparing six sweeps of data from a British cohort study), task definitions encompassing tasks such as category harmonization and multi-wave merging, and automated routines for evaluating the LLM-produced R code and outputted data. We benchmark LLMs across the (consumer grade) deployment spectrum to assess their efficacy in 20 data preparation tasks (creation of 102 variables). Current state-of-the-art, 31-35B parameter models almost saturated our benchmark ('average task completion' up to 87.9%). The performance of open-weight LLMs running on consumer-grade hardware shows promise of a viable path toward AI-assisted data preparation in governance-restricted research settings. Our framework is publicly available at: https://github.com/UCL-ARC/RRBench.

Large language models (LLMs) are increasingly used as tutors and thought partners, helping users reason through problems. While guidance from AI assistants can scaffold thinking and foster learning, such benefits depend on how they help--for instance, intervening too early or too frequently may hinder true learning and cognitive engagement. Yet how AI systems navigate intervention decisions during problem-solving remains poorly understood. Here, we introduce Int-Bench, a simulation-based benchmark for evaluating LLM interventions during learning. Int-Bench simulates a "student" solving a problem while a "teacher" monitors the student's reasoning and decides whether, when, and how to intervene. Across three domains--code debugging, mathematics, and brain teasers--we evaluate LLM teachers on the frequency and timing of interventions, as well as their impact on both immediate task success and generalization to new problems. We also compare LLMs to humans, finding that LLMs intervene more frequently and earlier than humans. Moreover, in contrast to humans, they tend to provide complete solutions rather than targeted hints. These findings suggest that current LLM assistants often optimize for short-term success rather than supporting the reasoning processes needed for deeper learning and long-term success.

The recent emergence of vibe-coding workflows is changing what coding agents are expected to do. Instead of merely completing code under fully specified instructions, agents are increasingly expected to transform incomplete product intent into working software by combining various abilities including planning, requirement clarification, tool use, debugging, and repository-level construction. Yet existing benchmarks have not fully caught up with this shift, evaluating agents on static, fully specified tasks. In this paper, we introduce ICAE-Bench, a benchmark for evaluating coding agents under interactive project-building settings. The basic idea is to start from a fuzzy product requirement, simulating the dynamic paradigm with an automated User Agent. To make this setting both realistic and evaluable, ICAE-Bench introduces three key designs. First, to avoid the ambiguity of unconstrained fuzzy requirements, each task derives ambiguity from a precise real open-source repository with executable behavior. Second, to ensure high-quality and reproducible user simulation, ICAE-Bench grounds interaction through User Agent Data, allowing the User Agent to reveal hidden constraints without inventing new requirements or leaking implementation artifacts. Third, to evaluate open-ended repositories fairly, ICAE-Bench uses standardized black-box tests together with multi-dimensional diagnostics, including functional correctness, semantic and API similarity, structural fidelity, design quality, and interaction quality.

Scientific research involves complex information-seeking and reasoning workflows across heterogeneous sources. However, existing benchmarks primarily emphasize general-domain retrieval or static scientific question answering, and therefore fail to assess key capabilities required in realistic scientific research workflows. We introduce SciExplore, a benchmark designed to evaluate scientific information-seeking and reasoning capabilities of LLMs and agents. SciExplore comprises four task types covering 103 expert-curated tasks across more than ten scientific disciplines: scientific database navigation, ambiguous literature retrieval, missing reference completion, and cross-source structured knowledge synthesis, which probe progressively higher-level abilities from entity-level reasoning and document-level identification to evidence-level grounding and domain-level synthesis. We evaluate over ten state-of-the-art LLMs and autonomous agents on SciExplore, revealing substantial performance gaps with performance degrading sharply as task complexity increases and extremely low accuracy on the most challenging structured synthesis tasks. These results highlight significant limitations of current models and agents in realistic scientific information-seeking scenarios.

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its core is a unified evaluation framework for constructing and running distribution-informed coding-agent tasks across four work domains - Code, Web, Office, and Security. Rather than adapting public issue text, every task is reverse-engineered from a real commit, pull request, or business scenario and rewritten as a short, colloquial, role-played request, so that a task's prompt is not recoverable by web-searching the underlying issue, pull request, or commit thread. Because the dataset is released openly - task directories, environment images, evaluation harness, tests, and reference solutions - contamination resistance rests on this construction together with dataset versioning rather than on secrecy. The four subsets - repository-level engineering, front-end development, office and business workflows, and red-/blue-team security - probe complementary facets of real work, each with its own verification style. All are packaged in a uniform task-directory format and run, under a uniform and reproducible protocol, on two agent harnesses (CodeBuddy Code and Claude Code); the full open release makes the benchmark reproducible end to end and directly auditable, since any third party can re-run each task and inspect its content. Because each subset uses a different scoring instrument, scores are not comparable across subsets and the suite reports no suite-wide average. We report a cross-model leaderboard across several model families.

We introduce ARBIGRAPH, a benchmark generator for evaluating whether tool-assisted language agents can retain, update, compose, and discard task-relevant context across extended reasoning workflows. ARBIGRAPH represents each task as a natural-language problem with an executable Python solver, and composes tasks through typed intermediate states, instantiated here as scalar and list values. This design enables controllable task graphs whose length, dependency structure, distractor count, and value type can be varied while preserving exact automatic verification. We instantiate ARBIGRAPH with math, GSM-style word-problems, and Python-tracing task categories, and evaluate a Qwen3.5-27B tool-assisted agent across four topologies. The results show high accuracy on isolated tasks but substantial degradation on more complex dependent tasks: accuracy drops by up to 33.3% on branching chains of dependent math tasks. This shows that ARBIGRAPH exposes failures that are not visible from single-task evaluation alone. Our code, generated datasets, and evaluation results are available at https://github.com/pavelgolikov/ArbiGraph.git

As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inherently dynamic: users rarely specify their intent upfront, instead disclosing, revising, and reshaping it as the conversation unfolds. Despite this, LLMs are still predominantly evaluated or trained in single-turn, fully-specified settings, leaving open a fundamental question: how well do LLMs track and act on user intent as it evolves over the course of a conversation? To study this, we introduce a framework that transforms static, single-turn tasks into dynamic multi-turn conversations in which the user's intent evolves across turns--incrementally revealed, revised, and at times redirected mid-conversation--while preserving each task's original evaluation protocol, enabling existing benchmarks to be reused as controlled testbeds without new annotation. Across multiple tasks, we surface a consistent phenomenon: strong static-setting performance does not transfer to the evolving-intent setting, with substantial drops across model families. Our findings point to a fundamental gap: today's LLMs do not yet faithfully track and act on the user's evolving intent, a capability invisible to static evaluation yet critical for future collaborative agents.

We introduce Frontier Financial Judgement, a challenging new benchmark developed in collaboration with professional equity analysts to assess agents' ability to replicate expert human judgements. Rapidly identifying new information, evaluating its implications and determining its valuation impact is one of the most time-consuming and challenging aspects of real-world equity coverage. This is becoming ever more difficult and important as AI rapidly increases the quantity of new information to process. The strongest agent we evaluate on Frontier Financial Judgement matches all expert labels in only 52.4% of cases. We also find significant divergence in estimated false-positive rates among frontier agents, ranging from ~1% for GPT-5.6 Sol to ~32% for Claude Sonnet 4.6. To construct the benchmark and make it representative of real-world settings, we combine human-designed and labelled synthetic articles with live news articles and historical documents, creating 656 items for assessment. The resulting task requires agents to distinguish genuinely new, valuation-relevant financial information from stale, immaterial or misleading news under realistic conditions. We find substantial trade-offs among agent accuracy, cost, false positives and reliability that continue to hinder the reliable deployment of news-flow filtering in practice.

Modern AI systems depend on specialized accelerator kernels, whose development is complicated by increasingly diverse operators and hardware. LLMs and agentic systems promise to automate this work, but existing evaluations do not show whether their performance transfers across operator sources and hardware platforms, or what such transfer costs. We present KernelGenBench, the first unified multi-source and multi-chip infrastructure for evaluating LLM- and agent-generated Triton kernels. With a common Triton target spanning six hardware platforms, it provides the broadest cross-vendor hardware coverage among existing kernel-generation benchmarks. We report two controlled analytical views: KernelGenBench-MS (Multi-Source) covers 210 operators from PyTorch ATen, production vLLM operators, and proprietary cuBLAS routines, while KernelGenBench-MC (Multi-Chip) evaluates a semantically stable 110-operator subset across six hardware platforms. Our evaluation consumed over 15 billion tokens. Agentic execution improved correctness, but no method dominated across sources and platforms: vLLM posed the strongest correctness challenge, cuBLAS set the highest performance ceiling, and AutoKernel accuracy fell from 87% on NVIDIA to 25% on Iluvatar CoreX. These improvements were costly: specialized agents averaged 4.99 million tokens per successful operator, rising to 6.25 million for CUDA Optimized Skill. The results establish operator source, hardware platform, and agentic scaffold as distinct dimensions of kernel-generation capability, and show that success in a familiar source-hardware setting is not a reliable proxy for deployment readiness.

LLM-based game agents often perform poorly on more complex tasks. This work examines whether these failures are linked to limited spatial reasoning and evaluates whether causal prompt augmentation and multi-step planning can improve win-rates while managing response latency. Using the open-source Qwen3 model family, we conduct experiments across varying model scales, reasoning modes, and planning horizons. We further introduce a focused GVGAI benchmark consisting of three custom games with five difficulty levels to isolate spatial navigation. The evaluation follows two paradigms: an initial ``positioning experiment'' to test an agent's ability to find its exact coordinates, and a study of game-play success. Our results show that while larger models with an enabled thinking mode identify their positions more accurately, overall performance in coordinate matching remains limited for smaller models. Win rates decrease as game levels and layout complexity increase, validating the benchmark's difficulty scaling. Integrating causal context into the prompts tends to improve the agents' success rates, particularly for bigger models. While enabling thinking mode and longer planning horizons significantly improve performance, multi-step planning further reduces mean per-step response times, offering a practical trade-off between reasoning depth and execution speed.

As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating complex workspace workflows. In this paper, we introduce DocOps, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy that deconstructs document operations inspired by real-world practices into atomic dimensions and escalating workflow complexities. Based on DocOps, we systematically evaluate representative closed- and open-source models across various agentic harnesses, revealing that even the most advanced frontier configurations still exhibit profound limitations when handling highly coupled, long-range tasks. Furthermore, a fine-grained analysis of existing agents' manipulation behaviors uncovers 3 key failure modes: long-term state tracking collapse, shallow semantic verification, and destructive editing of structural metadata. Ultimately, our work exposes the capability boundaries of agents in maintaining global document consistency, shedding light on the future design of robust, non-destructive agents for complex digital ecosystems.

Large language model agents are increasingly deployed in settings where the value of an action depends on what other agents do. This creates a strategic reliability problem: the same game may be described as a business negotiation, a friendly compromise, a diplomatic exchange, or an abstract payoff matrix, and the model may choose different actions even when the incentives are unchanged. This paper introduces \emph{Same Game, Different Story}, a benchmark for strategic robustness: invariance of model-induced action distributions under payoff-preserving language changes. The empirical analysis uses a deliberately narrow, literature-calibrated comparison from Lorè and Heydari's peer-reviewed study: business framing versus friend-sharing framing across GPT-3.5, GPT-4, and LLaMa-2 in four social-dilemma games, with 300 initializations per retained model-game-context cell. The retained design comprises 24 of the source study's 60 cells, representing 7,200 decisions. Because trial-level files were not available from the article, the analysis is presented as a secondary calibration based on reconstructed published rates, not as new model runs. As a conservative sensitivity analysis, effect magnitudes are attenuated by 30% toward the null: action shifts are multiplied by 0.70, and non-robustness, defined as one minus the robustness score, is multiplied by 0.70. Under this attenuation, pooled strategic robustness is 0.783 with a 95% bootstrap interval from 0.774 to 0.790, and friend-sharing framing raises cooperation by 0.307 with a 95% bootstrap interval from 0.297 to 0.316 relative to business framing. The analysis supports the narrower claim that social-relational framing can change strategic choices even when incentives are held fixed, without extending the analysis to a broader suite of contextual or cross-benchmark comparisons.

As pathogen genomic surveillance scales, the bottleneck is shifting from data generation to analysis. We present BioSecBench-Surveillance, a verifiable benchmark of 100 evaluations testing whether AI agents can infer the right analysis pipeline from raw sequencing data and surveillance context. Each evaluation gives an agent only the data and context a human analyst would have, then grades its structured answer deterministically. The tasks span seven categories, from taxonomic classification to genetic-engineering detection, across diverse sample types and sequencing technologies. Across 3,962 gradable attempts from sixteen model-harness pairs, the strongest configuration cleared only about half. Opus 4.8 with PI led at 50.2 percent, with a 95 percent confidence interval of 40.1 to 60.3 percent across 83 evaluations, tied with GPT-5.5 with Codex at 50.2 percent, with a 95 percent confidence interval of 40.8 to 59.6 percent, followed by Opus 4.7 with PI at 49.6 percent, with a 95 percent confidence interval of 40.0 to 59.2 percent, and Sonnet 4.6 with PI at 48.6 percent, with a 95 percent confidence interval of 38.9 to 58.3 percent. Even when agents invoked the correct workflows, their mistakes came from the choices around them, such as which references, thresholds, filters, and normalization to apply. BioSecBench-Surveillance provides a standard for measuring whether agents can be trusted to perform genomic surveillance when the next outbreak arrives.

AI-native biotechnology companies are often designed by copying human biotech org charts into agent roles. We argue for a different abstraction: a Company World Model, defined as a persistent asset-to-value state representation with transition models, explicit value functions, planning, and updating across scientific, regulatory, BD, commercial, financial, and execution constraints. We introduce a dry-lab benchmark for testing whether AI-agent organizations should mimic departments or operate around such a world model. The benchmark contains 45 retrospective public-information decision cases with strict time cutoffs, hidden outcomes, common schemas, automatic scoring, and blinded pairwise judging. We compare human-org-mimic, stronger human-org-mimic-plus, AI-native asset-centric, and AI-native value-conversion architectures. The value-conversion architecture is a prompt-level approximation of a Company World Model: a Live Asset Value Record updated by Deal, Approval, Revenue, and Investment Arbiter loops. Under a success function defined by external BD, regulatory approval and launch, and revenue discipline, it achieved the highest automatic value-conversion score and was strongly preferred over the original baselines by value-specific blinded judges. Stress tests narrowed the claim: a stronger human baseline remained competitive, and a neutral judge did not show robust value-conversion dominance. Codex-only mechanistic ablations suggest that Revenue Room, Deal Room, and Approval Room carry useful work under the target objective. The central finding is objective-sensitive: departments may remain useful governance views, but the core AI-native operating primitive should be a shared, predictive asset-to-value state rather than a static human org chart. The study is dry-lab only and does not establish real-world drug success, clinical benefit, or revenue prediction accuracy.

World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe dominates across environments. This makes it an ideal testbed for AI coding agents acting as autonomous researchers--a setting in which the improvement direction is not specified in advance, unlike the engineering-to-spec tasks that dominate current agent benchmarks. We introduce AutoWorldModel-Bench, a closed-loop benchmark in which frontier coding agents autonomously improve a provided world-model starter under a fixed compute budget. The benchmark spans eight game environments under a unified structured-state representation--ground-truth entity state extracted from each game and consumed through a shared tensor format--which isolates dynamics modeling from perception and enables minutes-per-run iteration. Across 64 sessions, Codex-5.4 and Claude Opus 4.6 improve their starter on 63; in 91% of sessions the winning edit is a non-trivial research-style modification--a new objective, representation, rollout procedure, or architectural change--rather than a hyperparameter tweak. Our benchmark offers a setting in which frontier coding agents can be evaluated on open-ended research rather than engineering-to-spec problems.

Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user. Existing agent benchmarks often evaluate these capabilities in isolation: tool benchmarks test invocation under fixed APIs, memory benchmarks test recall or forgetting, and safety benchmarks test static policy compliance. We argue that personal-agent evaluation requires a different protocol: replaying the same temporal intervention across different persistent user-conditioned states and measuring how failures propagate across agent components. We formalize this requirement as four conditions: explicit temporal intervention, persistent state across the intervention, induced cross-dimensional effects, and variation in user-conditioned state. A focused audit of public benchmark protocols selected by explicit inclusion criteria identifies several close cases. Under our explicitly narrow operationalization, we did not find a protocol in that audited set satisfying all four conditions. This claim is scoped as a focused gap analysis with bounded literature coverage. This position paper proposes a minimal benchmark design and candidate reporting metrics for user-conditioned adaptation. The result is a concrete design requirement for future personal-agent evaluation, with metrics used as reporting tools for that requirement.

Existing AI measurement frameworks quantify cognitive capability, task automation, or catastrophic risk, but none measure autonomous agency: the extent to which a system behaves in a self-directed way. A system can saturate capability benchmarks while remaining entirely reactive, acting only when prompted and ceasing all activity when a task completes. We introduce the Autonomous Agency Scale (AAS), a behavioral framework that scores AI systems on a 0-5 lexicon across seven dimensions of agency: cognitive autonomy, temporal persistence, environmental agency, social agency, creative agency, self-awareness, and goal formation, each operationalized by falsifiable threshold tests. Every dimension is scored in two temporal bands: an Active band covering engaged, user-initiated activity, and an Ambient band covering idle periods. Ambient Level 4 is gated by the Idle-Gap Test, a counterfactual criterion (remove all triggers and observe whether internally derived activity persists) that separates self-direction from scheduled rule-following. We apply the scale to six contemporary systems spanning task agents (Claude Code, Manus, Hermes), consumer assistants (ChatGPT, Siri), and a persistent companion architecture (Airi). The two-band profile quantifies a boundary that single-score frameworks conflate: task agents reach Active composites of 2.3-2.4 while scoring 0.6-1.9 Ambient, with every idle-period behavior attributable to user-configured schedules, whereas the companion architecture, evaluated longitudinally, is the only assessed system whose idle-period behavior survives trigger removal. We discuss limitations, including single-rater provenance, developer-evaluator bias on the longitudinal assessment, and the partially operationalized self-direction boundary in the Active band.

Large language model (LLM) agents are extending electronic design automation (EDA) beyond static RTL generation toward long-horizon, tool-interactive workflows. Yet it remains unclear whether general-purpose coding agents, even with domain-specific EDA skills, can reliably execute an end-to-end RTL-to-GDS flow encompassing synthesis, physical implementation, and engineering change order (ECO) optimization. We evaluate AI agents on a PicoRV32 RTL-to-GDS flow using commercial EDA tools under two timing targets. Their performance is assessed using end-to-end design score, stage completion, and Token ROI, a cost-efficiency metric relating design quality to runtime and cost. Comparing three agent architectures and four foundation models, we derive three practical lessons. First, domain-specific skills improve agents' understanding of individual subtasks but do not ensure reliable completion of a long-horizon EDA flow. Second, agents that achieve similar design progress can still differ by up to 141 times in Token ROI, revealing substantial differences in runtime and cost efficiency. Third, low-level tool-interface mismatches are a major source of physical design failures, particularly when Tcl commands depend on the tool version or execution mode. These results suggest that robust Agentic EDA requires not only stronger models but also structured tool interfaces, persistent design context, controlled execution, and process-level evaluation.

GUI agents must reason about how actions transform interface states, but end-to-end success rates entangle this ability with perception, grounding, planning, and recovery. We introduce EvoGUI, a diagnostic framework that converts normalized GUI trajectories into three complementary visual question answering probes: temporal ordering, inverse action/value prediction, and contrastive one-step successor discrimination. Their labels are derived from trajectory order and logged actions, requiring no additional task-label annotation after trajectory normalization. We instantiate EvoGUI-Bench from Mind2Web and WebLINX, yielding 3,000 instances across 120 domains, and evaluate 28 vision-language model configurations zero-shot. The strongest model reaches only 60.4 EvoGain, while model scale and GUI specialization do not reliably predict performance. These results establish EvoGUI-Bench as a scalable diagnostic complement to end-to-end GUI-agent evaluation while exposing substantial headroom in state-transition understanding. The source code is publicly available at https://github.com/Yyhhh6/EvoGUI.

Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it. We study one production system (Leni) whose architecture installs such checkpoints: verification loops (execute, observe, compare, correct) staffed by lightweight task-specialized post-trained models. We evaluate the unmodified production configuration on three public benchmarks stressing distinct failure modes: SpreadsheetBench Verified (silent computation error), BullshitBench v2 (premise confabulation), and the GAIA validation split (cascade error over long tool chains). The full system improves over its frontier base model by +11.0 percentage points on SpreadsheetBench (91.25% vs 80.25%, n=400, p<0.001), +7 to +10 percentage points on BullshitBench (98% vs 91%, n=100), and roughly +15 points on GAIA validation (75.2% pass@1, n=165; 83.0% best-of-k). Our central contribution is a decomposition of that uplift: most of it comes from scaffolding, routing, and specialist models rather than from the verification step itself, whose isolated contribution is small (+1.5 points) but concentrated at the top of the score distribution, where it converts otherwise-failing tasks. We instrument the loop end-to-end, yielding an empirical verifier confusion matrix (catch rate about 0.20, fix rate 0.75, no false-alarm regressions) that grounds a compounding-reliability model. Specialist-swap ablations suggest that the loop's value depends on who observes it: replacing the small trained verifier with the generating frontier model eliminates most rescues. A valid-premise control shows zero over-rejections in 100 expert-level questions.

Existing tool-use benchmarks report a single success rate for complex, multistep tasks. Inspired by ideas from cognitive science, we distinguish tool use from tool discovery and decompose the latter into curiosity (the model's ability to discover the parts needed to build the tool), recognition (the model's ability to discover the process of creating the tool), and efficiency (the model's use of the tool after creation). We show that this framework can be applied to existing discovery tasks, such as Voyager. In addition, we provide evidence that recognition inversely scales with model size, and we introduce and analyze a class of combinatorial games that demonstrates this. We further observe inverse scaling in a separate environment designed to emulate real-world tasks.

Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers. We introduce two full-text scientific-memory benchmarks, Public AI Memory (PAIM; 81 papers, 66 questions) and Public Transformers (PTr; 252 papers, 98 questions). We evaluate eight memory/retrieval systems, including our own proposed Theoria, plus a no-retrieval baseline. Our results show that memory leaderboards are not interpretable without the full protocol: ingestion granularity, raw-text preservation, retrieval budget, retrieval modality, rubric audit, and judge choice all affect the outcome. For example, on PAIM Graphiti wins convincingly but uses 2.6M characters of retrieved context per query, and after controlling for retrieval budget the lead disappears. On PTr, for the systems where BM25 retrieval can be added cleanly, the sparse-dense hybrid is the single most significant intervention: hybrid variants of Simple RAG, Mem0, and Theoria tie for the lead within 0.03 points. Multi-judge and human side-by-side calibration show that LLM-as-a-judge rankings are consistent across frontier judges and agree with human evaluation, with an effective resolution of roughly one point on a ten-point scale. We argue that scientific memory should be evaluated as budgeted, modality-aware context restoration rather than as an unconstrained architecture leaderboard, and we release the datasets, harness, raw outputs, judgments, and scripts to reproduce our results and serve as tools for such evaluation. Our code is available at http://gitlab.com/quantellence/research/scientific-recall-bench , and the datasets are available at http://huggingface.co/datasets/quantellence/srb-data .