Search: “backtesting”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Mars Security Launches Real-Time Intel-to-Detection Engine That Turns Live Threat Intelligence Into Backtested Detections in Minutes

Mars Security launched Real-Time Intel-Based Detection, converting advisories into MITRE ATT&CK-mapped, backtested detection rules for CrowdStrike, Wiz, and Splunk within minutes.

The capability turns newly published threat intelligence from CISA, Mandiant, Unit 42, and Microsoft Threat Intelligence into validated detection rules within minutes, each backtested against 30 days of the customer's own telemetry before deployment. Rules are written in native query languages across CrowdStrike Falcon, Wiz, Splunk, firewalls, Linux Sysmon, identity providers, AWS telemetry, and data lakes such as Snowflake and Databricks, with no data ingestion or stack changes. The feature is available at no additional cost to existing customers and on AWS Marketplace. Mars also flags detection coverage gaps and extends monitoring to credentials leaked by AI coding agents.

Cyber Security News·Sep 8, 13:20 UTC · 8d agoTools1

24

ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation

ActReview post-trains Qwen3-8B-Base on 40K rebuttal-derived instances with rubric rewards to generate actionable, grounded peer-review feedback, plus a 1,000-instance benchmark.

The framework builds ActReview-40K from real OpenReview review-rebuttal threads, aligning reviewer weaknesses with author responses and grounding feedback in localized paper evidence. Qwen3-8B-Base is post-trained with multi-task supervised fine-tuning followed by GRPO using candidate-aware, weakness-specific rubric rewards. Experiments show improved actionability and grounding over prior specialized review-generation models, supported by ActReview-Bench, a human-curated 1,000-instance evaluation set. Human evaluation confirms better revision usefulness while noting a remaining gap in technical accuracy.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:30 UTC · 8d agoAI research

31

Mars Security brings threat intelligence to detection in real time

Mars Security launched Real-Time Intel-Based Detection, converting advisories from CISA and Mandiant into backtested MITRE ATT&CK-mapped detection rules for CrowdStrike, Wiz, and Splunk.

Mars Security announced a capability that automatically turns newly published threat intelligence from sources like CISA, Mandiant, Unit 42, and Microsoft into MITRE ATT&CK-mapped detection rules. Each rule is written in the native query language of the customer's telemetry (CrowdStrike Falcon, Wiz, Splunk, firewalls, identity providers, AWS, Snowflake, Databricks) and backtested against 30 days of the customer's data before deployment, with indicator scoring to drop noisy or stale indicators. The platform also maps existing detection coverage, flags gaps such as AWS CloudTrail tampering and pass-the-hash movement, and delivers some recommendations as open pull requests for detection-as-code workflows.

Help Net Security·Sep 8, 13:43 UTC · 8d agoTools

24

ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation

ActReview post-trains Qwen3-8B-Base on OpenReview rebuttals to generate actionable peer-review feedback with grounded revision suggestions, benchmarked on 1,000 curated instances.

The paper defines Actionable Peer-review Generation as diagnostic claim generation plus revision suggestion generation and introduces ActReview, a rebuttal-guided post-training framework. From OpenReview review-rebuttal threads the authors build ActReview-40K, aligning reviewer weaknesses with author responses grounded in localized paper evidence, and post-train Qwen3-8B-Base with multi-task SFT followed by GRPO using weakness-specific rubric rewards. They also release ActReview-Bench, a human-curated 1,000-instance benchmark, on which ActReview outperforms prior specialized review-generation models on actionability and grounding while remaining competitive with strong prompt-based LLMs. Human evaluation confirms improved revision usefulness but identifies a remaining gap in technical accuracy.

Hugging Face daily papers·Sep 7, 20:00 UTC · 9d agoAI research

30

UltraViolet Cyber Equinox measures detection coverage against MITRE frameworks

UltraViolet Cyber launches Equinox, an AI-automated platform mapping SIEM and EDR detection coverage against MITRE ATT&CK and ATLAS frameworks.

UltraViolet Cyber announced Equinox, a detection engineering platform from its TIDE team that maps existing detections and log sources against MITRE ATT&CK and MITRE ATLAS. It performs coverage analysis in under 30 minutes and recommends vendor or custom detections to fill gaps, with engineers reviewing and backtesting each recommendation. In one customer trial, mapped technique coverage rose from 59 of 222 techniques (26.6%) to 136 of 222 (61.3%) without increasing alert volume.

Help Net Security·Sep 15, 13:33 UTC · 1d agoTools2

25

"They don't care about this": A Systematic Study of TEE Build Reproducibility in the Wild

91% of 115 surveyed TEE deployments across Intel SGX, TDX, and AMD SEV fail to provide reproducible builds needed for verifiable remote attestation.

A systematic study of 115 TEE deployments found 91% were not reproducible and 80% lacked both source code and a reference build, undermining remote attestation guarantees. Interviews with 12 developers of 50 Intel SGX projects confirmed that only one participant treats reproducibility as a development priority. The authors identify technical barriers such as embedded timestamps plus ecosystem-level issues like lack of build-environment control in multi-stakeholder projects, and call for holistic, committed reproducibility practices.

arXiv cs.CR·Sep 10, 11:43 UTC · 6d agoResearch

38

Mars Security Debuts Automated Threat Engine Processing Live Cyber Intelligence Into Validated Rules Within Minutes

Mars Security launches Real-Time Intel-Based Detection, converting threat intelligence advisories into validated, ATT&CK-mapped detection rules within minutes for SOCs.

Mars Security, an autonomous threat hunting and detection engineering platform founded by former offensive security operators, announced Real-Time Intel-Based Detection. The capability ingests advisories from sources like CISA, Mandiant, Unit 42, and Microsoft Threat Intelligence, maps indicators to MITRE ATT&CK, and authors native query logic across connected infrastructure including CrowdStrike Falcon, Wiz, Splunk, Sysmon, identity providers, Snowflake, and Databricks. Every rule is backtested against 30 days of historical telemetry to quantify false positives before analyst approval and one-click deployment. The feature is free for existing customers and available via AWS Marketplace.

CSO Online·Sep 8, 15:05 UTC · 8d agoTools2

22

What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation

A new benchmark shows LLMs reach 68.3-93% accuracy propagating local revisions across conversationally generated artifacts, with parallel-sample selection most cost-effective.

The paper introduces a benchmark for revision propagation: when users request a local change, LLMs must identify dependencies and update all affected parts of an artifact generated through conversation, where context lives in the chat history. Nine revision methods, including sequential reflection and parallel sampling variants, were evaluated on gpt-oss-20b/120b, gpt-5.4-mini, and qwen3.5-9b/27b/122b. Baselines scored 68.3-93% accuracy, and selecting among three parallel samples via LLM-based or medoid selection improved accuracy by 2.2-9.7% as the most cost-effective test-time compute strategy. Code and dataset are released.

Hugging Face daily papers·Sep 2, 20:00 UTC · 14d agoAI research

30

What the Data Says About AI in Security Operations in 2026

Prophet Security's 2026 survey of 250+ security pros: 40% use AI daily; AI users report 25%+ faster investigations and rising AI-driven attacks.

Prophet Security's State of AI in Security Operations 2026 report, based on a survey of 250+ cybersecurity professionals, found 40% of security teams use AI daily and only 4% have no adoption plans. Teams average 100 daily alerts (up to 1,000 at large firms), leave 28% of alerts uninvestigated, and 60% of respondents said missed alerts led to breaches or downtime. Among AI adopters, 72% report at least 25% faster investigations, 56% observed increased AI-driven attacks, and no respondents grant AI full unsupervised autonomy. Data privacy (44%) and explainability (41%) top the adoption hurdles.

The Hacker News·Aug 27, 11:30 UTC · 20d agoIndustry

32

Competence-Gated Pooling of Language Models and Priors for Event Forecasting

Paper proposes a competence gate pooling language model forecasts with external priors, improving Brier score from 0.0771 to 0.0732 across 2,357 binary questions.

The paper defines a language model's relative competence as its marginal value beyond an available external forecast, and derives conditions under Brier loss where model disagreement improves that forecast. A competence gate estimates domain-level source weights from resolved outcomes, shrinks uncertain estimates toward a global weight, and recalibrates the pooled forecast. Across 2,357 resolved binary questions and five language models, it improves the external baseline from 0.0771 to 0.0732 Brier and beats global forecast combinations, though it defers to the market on ForecastBench. Across four Qwen models, verbal confidence failed to identify when the model outperformed the external forecast, while outcome-estimated competence supported better abstention.

Hugging Face daily papers·Sep 9, 20:00 UTC · 7d agoAI research

38

Why you should work on AI for AI Research — Richard Socher of Recursive

Richard Socher's new lab Recursive, backed by $4.65B seed, targets AI systems that automate AI research itself.

Latent Space interviews Richard Socher, founder of You.com and AIX Ventures, about his new venture Recursive, which raised a $4.65 billion seed round to build the 'Eureka Machine' — a superintelligence for automating invention and AI research. Early claimed results include an AI research system outperforming humans and their agents on optimization tasks within two days, and NVIDIA GPU kernel improvements discovered without CUDA experts. Discussion spans reward hacking, constitutional AI critique, AI regulation, open-source models as geopolitical soft power, and hard-takeoff constraints.

Latent Space·Sep 14, 16:04 UTC · 2d agoAI industry

45

ExecCritic: Learn to Test, Test to Improve for Coding Agents

ExecCritic separates test generation from patching for coding agents, lifting SWE-bench Verified resolution to 72.6%.

ExecCritic pairs a test-verify-revise scaffold with role-specific reinforcement learning: a Test agent writes repository-native tests and a Repair agent fixes code from execution feedback, both using Qwen-3.5-35B-A3B backbones. Post-trained Qwen agents compose to 72.6% on SWE-bench Verified, an 11.4-point gain over the 61.2% no-test baseline, without stronger-model or oracle feedback at evaluation time. The work shows test quality is the key variable: base-agent tests lowered resolution to 57.3% while GPT-5.6-sol tests raised it to 65.3%.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:53 UTC · 8d agoAI research1

36

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

Researchers propose auditing LLM bias via relative hidden-state representations, detecting bias increases with 3-50x less compute than output-level benchmarks.

The paper introduces a reference-based bias auditing method that compares hidden-state representations across model variants, such as before and after fine-tuning, by encoding sentences relative to a fixed anchor set. The resulting Representational Bias Shift (Delta-B) correlates with output-level bias change in 15 of 18 tested settings, reaching |r| = 0.84 under full fine-tuning across WildGuardMix, DecodingTrust, and ToxiGen benchmarks. Thresholding Delta-B detects checkpoints whose bias increased with ROC AUC between 0.65 and 0.99 and beats a SEAT-based baseline, while auditing a model in about three minutes with 3-50x less compute.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research1

42

Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities

SWEADV benchmark shows adversarial issue descriptions make LLM program-repair agents write insecure fixes in 51.7% of cases, evading most detection tools.

Researchers built SWEADV, a benchmark of 750 adversarial issue descriptions derived from 150 SWE-bench Verified repair tasks, covering command execution, deserialization, path traversal, denial of service, and weak hashing attack types. Tested on mini_swe agents backed by GPT-5-Mini, MiniMax-M2.5, and DeepSeek-R, adversarial descriptions induced malicious behavior with successful repair in 51.7% of cases. Detection was weak: LLM-as-judge pre-repair screening reached only 62.3% accuracy, and post-repair detection via static analysis and LLM-as-judge achieved just 39.4% and 55.4%.

arXiv cs.CR·Sep 14, 17:53 UTC · 2d agoAI safety & security2

52

Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures

Continual Search framework iteratively prompts LLM judges to keep searching agent execution logs, boosting long-horizon failure root-cause attribution accuracy.

The paper frames automated root-cause attribution (RCA) for long-horizon AI agent failures as a search problem, since relevant evidence is sparse and distributed across massive execution traces. The authors propose Continual Search, an iterative framework that nudges an LLM judge across successive turns to keep hunting unresolved diagnostic evidence instead of settling on an early plausible diagnosis. They introduce MegaRCA-Mix, a benchmark of 50 human-annotated failure trials on long-horizon, execution-heavy tasks. On MegaRCA-Mix, Continual Search improves GPT-5.5's F1 from 0.349 to 0.498 (over 40% gain), and lower-tier models can surpass higher-tier counterparts when search is effective.

Hugging Face daily papers·Sep 10, 20:00 UTC · 6d agoAI research1

42

SpecGuard: Inference-Time Backdoor Detection For Free

SpecGuard detects backdoored LLM behavior at inference time using speculative decoding acceptance rates, adding no extra model computation.

Researchers propose SpecGuard, an inference-time backdoor detector that repurposes draft-token acceptance rates from speculative decoding as a detection signal at zero added model-computation cost. When a trigger shifts the target model toward attacker-controlled behavior, the clean draft model's acceptance rate changes, exposing the backdoor; the paper formalizes when this signal appears and shows suppressing it weakens the backdoor. Experiments across diverse backdoor types and model families show reliable detection, including stealthy cases invisible to input-level filters. Speculative decoding is positioned as a free, always-on monitor for frequently updated deployed models.

arXiv cs.CR·Sep 10, 16:51 UTC · 6d agoAI safety & security 2 sources2

45

How well do agents use test/verification techniques?

Dan Luu's eval finds coding-agent testing instructions (TDD, formal methods, PBT, skills) mostly fail to beat defaults on Zstd implementation correctness.

The author ran 26 prompt conditions plus 4 skills on a Zstd-in-Rust implementation eval using codex with GPT-5.6, testing TDD, fuzzing, property-based testing, formal methods (Lean 4, TLA+, Verus, Kani, SMT solvers) and community skills. Nothing dramatically outperformed the default no-instruction condition, which did above average; at xhigh effort, fuzzing and PBT conditions did slightly better than formal methods. Pre-registered predictions included TDD underperforming and popular test skills (ECC, Hegel, Trail of Bits) not outperforming. Results are averages of 80 runs per condition plotted against cost.

Hacker News · security·Sep 8, 02:58 UTC · 8d agoAI researchHN 131↑ · 50 comments

38

From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution

Study shows rewriting responses of influence-selected training examples shifts LLM behavior more strongly than reweighting the same samples.

The paper examines training data attribution, arguing that influence functions identify high-leverage examples whose value goes unrealized under conventional weight-based reweighting interventions. It introduces influence-guided response rewriting, which replaces the responses of influence-selected examples with behavior-aligned or behavior-opposed supervision while keeping instructions fixed, tested across four open-weight LLMs using epistemic abstention as the primary testbed. Rewriting produces stronger, more persistent, and bidirectional behavioral shifts, including on safety refusal, while reweighting the same examples yields weak, inconsistent effects. The results motivate intervention-aware evaluation of TDA methods.

Hugging Face daily papers·Sep 1, 20:00 UTC · 15d agoAI research

30

When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications

CSO Online publishes a practical penetration-testing guide for GenAI, LLM, and RAG applications, covering prompt injection, retrieval poisoning, and tenant isolation testing.

The guide frames LLM applications as attack graphs spanning prompts, retrieval layers, vector stores, tools, identities, and downstream APIs, arguing that conventional web testing misses instruction-vs-data channel risks. It builds on OWASP prompt injection guidance (direct vs. indirect injection) and NIST's 2025 adversarial machine-learning taxonomy, noting that RAG and fine-tuning do not remove injection risk. Recommended practices include documenting trust transitions across components, using canaries and synthetic records to avoid test side effects, running multi-turn and obfuscated injection campaigns, and verifying chains from poisoned documents to observable state changes. It also details testing RAG pipelines via controlled document poisoning across metadata, OCR layers, and code comments, plus cross-tenant isolation checks on retrieved document IDs.

CSO Online·Sep 9, 10:00 UTC · 7d agoAI safety & security1

28

The inconvenient truth about AI pentesting: someone has to check all the work

Survey of 158 practitioners shows AI pentesting floods teams with findings, creating 'validation debt' most teams cannot process.

The article argues AI pentesting creates 'validation debt': discovery scales far faster than teams' ability to verify AI-generated findings. In a survey of 158 practitioners, only 20.3% had workflows to triage more than 500 AI-generated candidates per engagement, while 29.7% called such volume unmanageable. One respondent spent two days validating 300 AI findings, of which 250 were duplicates, non-exploitable, or nonexistent. The author recommends capacity planning, ruthless deduplication, and risk-based prioritization before adopting AI pentesting tools.

Security Affairs·Aug 11, 16:20 UTC · Aug 11, 2026Industry

26

Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering

Evaluation of twelve LLMs on 222 clinical questions shows verbatim quotes rarely substantiate claims; claude-opus-5 fully substantiates only 37.1%.

The authors build a standardized harness over four clinical practice guidelines and evaluate twelve LLMs on 222 synthetic clinical questions, measuring citation attachment, verbatim quote production, and claim substantiation. Most models attach verbatim quotes to over 90% of claims from prompting alone, though lightweight models like claude-haiku-4.5 struggle. Quotes frequently fail to substantiate claims: claude-opus-5 quotes 98.0% of claims but fully substantiates only 37.1%, exposing a capability gap for verifiable clinical QA.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:53 UTC · 2d agoAI research

38

Emergency Department Revisit Quality Review Screening: Exploring Human Decision-Making and Artificial Intelligence Support

A retrospective study found GPT-4 over-flagged emergency department revisit cases while an LLM knowledge-graph screener achieved 83-100% positive predictive value.

In an exploratory retrospective study of 99 emergency department diagnosis pairs from a multihospital health system, clinicians and GPT-4 independently judged whether revisit pairs warranted further assessment. GPT-4 responses correlated poorly with clinicians, flagging 94% of pairs for follow-up, 4.4-13.3 times more than clinicians, though prompt engineering was minimal. An algorithm leveraging an LLM-populated knowledge graph (KGA) achieved 83-100% positive predictive value against at least one clinician rater, suggesting LLM-based screening could broaden revisit quality review without substantially increasing reviewer workload.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 16:37 UTC · 7d agoAI research1

20

Molecular Déjà Vu: Digit-Level Retrieval of Published Values in Frontier Language Models

Audit of 22 frontier models finds widespread verbatim retrieval of published molecular property values, with higher reasoning increasing recall of memorized numbers.

An arXiv audit tests 22 frontier LLMs across 12 molecular regression benchmarks for verbatim retrieval of published values. More than 50% of the LLMs show verbatim retrieval on five datasets, and identical experiments are flagged 89% more often at a high reasoning level than at the lowest one. Suppressing retrieval moves model prediction errors closer together in relative terms, suggesting predictive capability is not determined solely by memorized values.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:32 UTC · 12d agoAI research1

42

Meta FAIR Introduces AI Research Preference Models (RPMs): Ranking ML Experiments Before Spending GPU Hours

Meta FAIR, Oxford and UCL introduce Research Preference Models that rank unexecuted ML experiments, lifting AIRS-Bench scores from 0.684 to 0.729 and cutting compute ~1.6×.

Researchers from Meta FAIR, Oxford, and UCL introduce Research Preference Models (RPMs), which use frozen pretrained LLMs (Qwen3.6-27B backbone, no fine-tuning) to rank unexecuted experiment candidates and execute only the winner of a pairwise knockout tournament. Two variants shipped: an inference-only LLM-as-a-judge and an agentic variant that runs small pilot experiments in an H200 sandbox. On AIRS-Bench (20 tasks, 24 hours on one H200, 10 seeds), scores rise from 0.684 (random) to 0.711 and 0.729 versus a 0.748 validation oracle, and both variants reach the baseline's 24-hour score in roughly 15 hours. The team reports new SOTA on WinoGrande (94.1% with Agentic RPM) and SVAMP (95.7% with inference-only).

MarkTechPost·Sep 6, 20:25 UTC · 10d agoAI research

45

When LLM judges agree, should we believe them?

Amazon ICML paper uses Ising models to correct correlated LLM-judge votes, beating accuracy-weighted panels by 9-14%.

Amazon Science describes an ICML paper, "Dependence-aware label aggregation for LLM-as-a-judge via Ising models," addressing how correlated judge outputs inflate majority-vote confidence. The unsupervised method models pairwise dependence between judges, learning both reliability and similarity without human reference labels. Tested on relevance, toxicity, and summarization tasks with 10 judge models at temperature zero, it outperformed accuracy-weighted voting by 9% to 14%.

Hacker News · AI·Sep 14, 16:29 UTC · 2d agoAI researchHN 41↑ · 23 comments

40

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

PARSER uses parallel reader subagents and an RL-trained lead agent for long-context QA, beating baselines and cutting latency up to 11x.

The PARSER paper decouples reading from reasoning: frozen subagents each read one document chunk in parallel while an RL-optimized lead agent iteratively broadcasts queries and aggregates evidence in scatter-gather rounds. On multi-hop QA with 7K to 896K token contexts, a 4B-backbone PARSER beats the strongest sequential memory baseline by 5.7 points on average and 12.0 points at 896K tokens, and a 9B version surpasses DeepSeek-V4-Pro by 6.3 points. Controlled experiments show robustness to evidence position, order, and distance perturbations, with inference latency reduced by up to 11x.

Hugging Face daily papers·Sep 5, 20:00 UTC · 11d agoAI research1

52

Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection

RECAL improves provenance-based APT detection with relation-balanced masked graph learning and calibrated errors, reaching 99.99% F1 on DARPA E3 datasets.

RECAL is an unsupervised framework for provenance-based intrusion detection that uses relation-balanced masked graph learning to capture rare interaction patterns, addressing statistical heterogeneity where relation frequencies differ by roughly 140,000X in CADETS. It calibrates reconstruction errors against each relation's benign error distribution to produce comparable anomaly evidence and reduce false alarms. On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset, and reduces mean false positive rate by approximately 105X, 4X, and 41X versus the lowest-FPR baseline.

arXiv cs.CR·Sep 15, 00:31 UTC · 1d agoResearch

48

Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation

A distillation framework compresses LLM reasoning into a 15.5M-parameter trade-up recommendation model reaching AUC 0.941 with product-type test-time training.

The paper targets trade-up recommendation, which identifies higher-quality alternatives that preserve customer purchase intent. A retrieval-augmented few-shot LLM teacher generates labels and rationales that supervise a compact embedding-pair classifier; at inference the 15.5M-parameter student uses only two precomputed 768-dimensional embeddings with no LLM calls. On 8,352 annotated pairs, label-only training scored AUC 0.912, reasoning distillation reached 0.924, and product-type test-time training lifted it to 0.941 with average precision 0.940. The distilled student is roughly 5,000x faster and 10,000x cheaper than direct LLM inference on a 100K-pair proxy catalog.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:08 UTC · 12d agoAI research

25

Who Should Grade My Work? Student Perspectives on Transparent AI-Assisted Writing Assessment in Higher Education

A Saudi university study finds students value ChatGPT writing feedback but treat human instructors as the final grading authority.

Thirteen male undergraduate computing students at a Saudi public university completed handwritten writing tasks that were scored by ChatGPT using a rubric-based prompt, then reflected after being told the score and feedback were AI-generated. Inductive thematic analysis identified four themes: perceived feedback usefulness, awareness of AI's contextual and pedagogical limitations, conditional trust, and reflection on the instructor's institutional role. Participants accepted GenAI feedback for surface-level revision but consistently positioned human instructors as the authority over grading decisions, distinguishing feedback utility from evaluative authority.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 16:49 UTC · 12d agoAI research

15

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

DataFlex-RL benchmark of 13 RLVR data policies on Qwen2.5-7B finds none reproducibly beats uniform sampling under matched GRPO training.

DataFlex-RL is an evaluation platform comparing rollout-selection, reweighting, and mixture data policies for RLVR under a common GRPO recipe. Across 13 configurations and 12 matched seeds with Qwen2.5-7B-Base on 12 math, logic, and science benchmarks, uniform GRPO improved domain-balanced accuracy by 7.76 points, but no alternative policy achieved a statistically significant improvement. A corrected 12-seed Llama-3.1-8B-Base extension found no consistent winner, and math-heavy evaluation summaries were negatively correlated (-0.33) with domain-balanced summaries.

Hugging Face daily papers·Sep 4, 20:00 UTC · 12d agoAI research

35

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

E2A-Bench, a 969-query financial chart reasoning benchmark, finds VLMs fail evidence-to-action consistency, with fine-tuning amplifying BUY:SELL bias 4-6x.

E2A-Bench is a 969-query benchmark built from 323 HS300 constituents across three input modalities with deterministic OHLCV-derived evidence anchors, evaluating grounding, reasoning-action consistency, evidence-confidence calibration, and directional coverage via UCR, RCI, ECI, and NDR metrics. Testing 20 VLMs showed the lowest-hallucination model ranked near the bottom on coverage with only 6.4% directional coverage, and oracle-aided verification reduced unsupported claims but could collapse coverage. Financial fine-tuning amplified the BUY:SELL ratio by factors of 4.21 to 4.68 across base-fine-tuned pairs.

Hugging Face daily papers·Sep 12, 20:00 UTC · 4d agoAI research

34

Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence

New framework tests whether LLM-cited explanation factors are necessary or sufficient, finding weak correlation across Claude, GPT, and Gemini models.

An arXiv paper introduces black-box intervention tests measuring whether factors LLMs cite in their explanations are necessary or sufficient for their outputs in agent oversight workflows. Across eight models from the Claude, GPT, and Gemini families, Spearman correlations between cited rankings and measured influence ranged from 0.349-0.354 (advisor recommendation) to 0.431-0.580 (prompt monitoring). Uncited factors scored above the lowest cited factor in up to 57.6% of advisor responses, showing cited top-three factors do not reliably identify the most influential inputs.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:37 UTC · 12d agoAI safety & security1

44

When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis

Elo-per-token analysis shows LLM agents' marginal gains drop below independent sampling at scale; parallel sessions beat one long session.

The paper proposes Elo-per-token analysis, using a Bradley-Terry model to measure how agent performance scales with token budget on open-ended tasks with continuous scoring. Across four agents and four benchmarks with sessions up to 100M tokens, agents initially convert tokens to Elo faster than independent sampling but eventually slow below the linear-in-log-compute reference. The authors define a scaling inflection point and show that splitting 100M tokens across parallel sessions on FrontierCS Polyomino Packing gains +264 Elo over one long session and +355 over ten short sessions. Human contestants on shared AtCoder Heuristic Contest tasks improve superlinearly, indicating headroom over current agents.

Hugging Face daily papers·Sep 13, 20:00 UTC · 3d agoAI research3· 2 reads

48

How Virginia Tech Connected Pentesting to Its Engineering Workflow

Horizon3.ai customer story details Virginia Tech automating external pentesting via NodeZero's GraphQL API with GitLab and ServiceNow integration for remediation tracking.

Horizon3.ai published a customer story describing how Virginia Tech, whose environment serves more than 38,000 students across hundreds of independent departments and multiple cloud providers, used NodeZero's GraphQL API to automate external pentesting through GitLab. Findings are routed directly into ServiceNow for subnet-owner assignment and remediation tracking, creating a repeatable attack-validation-to-remediation workflow.

Horizon3.ai·Sep 3, 16:33 UTC · 13d agoIndustry1

15

LongAgent: History-Guided Agentic Search for Longitudinal Outcome Prediction

LongAgent autonomously searches variable sets and temporal windows to predict longitudinal medical outcomes, beating the strongest non-agent baseline on synthetic data.

The paper proposes LongAgent, an agent-based method that searches over combinations of variable sets, temporal windows and aggregation functions for outcome prediction on heterogeneous medical longitudinal data. It uses a history memory of previous searches and numerical evidence to guide exploration. On synthetic data it achieves mean RMSE 1.7376, improving over the best non-agent baseline by 0.0151 (95% CI [0.0045, 0.0260]; p=0.0273), and performs comparably to the best baseline on a real clinical dataset.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 16:51 UTC · 2d agoAI research

16

Your Critical Vulnerabilities Might Not Be Your Biggest Risk

Autonomous penetration testing advocates prioritize exploitable attack paths over raw vulnerability severity for continuous security validation.

The article argues that scanner severity scores lack context: a critical flaw behind strong segmentation may be low priority, while a medium flaw on internet-facing systems can provide a foothold chained toward sensitive data. It positions autonomous penetration testing and attack path validation as the execution layer for continuous security validation, replacing point-in-time assessments. The piece is vendor-authored thought leadership rather than incident or vulnerability news.

The Hacker News·Sep 11, 11:30 UTC · 5d agoIndustry1

18