Papers

Field

Top tools here

All tools

jcode+233% downloads · 25.5k/wk+233.1%
billion-context+259% downloads · 1.1M/wk+258.8%
LMDeploy+181% downloads · 13.5k/wk+180.6%
Vercel AI SDK400 releases this week
ONNX Runtime+35% downloads · 37.1M/wk+35.2%

Top tools here

Open problems in Frontier LLMs

Evaluating long-horizon agents in real-world web environments1 paper raises it · 1 addresses it
Current benchmarks do not capture the complexity of open, dynamic, and interactive web tasks, limiting the assessment of agent capabilities.
- Deep Search in Real-World Web Environmentsraises · addresses
Net value of agent memory over direct retrieval1 paper raises it · 1 addresses it
Memory systems often underperform naive retrieval, and their trade-offs between gains and losses (memory tax) are poorly understood.
- Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
Benchmark difficulty distribution mismatch and coverage gaps1 paper raises it · 1 addresses it
Benchmarks may misrepresent intended difficulty or miss key regions, leading to misleading evaluations of model progress.
- Your Benchmark Is an Empirical Measure Over Difficultyraises · addresses
Structural requirements for decision-native models1 paper raises it · 2 address it
Current decision models often lack null-awareness, permutation invariance, option scalability, and cacheability, limiting their robustness.
- Jeva: System One Models from First Principlesraises · addresses
- LEV: Thinking Fast and Deep with Looped Decision Modelsaddresses
Inferring user habits from weak longitudinal evidence1 paper raises it · 2 address it
Agents struggle to extract and apply user habits from sparse or noisy historical interactions, limiting personalization.
- HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memoryraises · addresses
- Vela: User Behavior as Supervision Sparks LLM Intelligenceaddresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Market

Kuaishou Keling AIStage not given · Oct 31$3B
Phinity LabsStage not given · Oct 31$5.2M
Kling AIStage not given · Oct 30$3B
CohereSeries B+ · Oct 29$7B
VinciSeries B+ · Oct 29$250M

Recently funded

Topics in this field

retrieval augmented generation · knowledge graphs · retrieval augmented291 papers37 this week
language models llms · large language models · language models314 papers33 this week
generative recommendation · sequential recommendation · personalized180 papers28 this week
memory construction · persistent memory · long term memory293 papers26 this week
deep research · scientific literature · citations163 papers20 this week
typed decision models · typed decision model · typed decisions160 papers20 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.CLSep 26
C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text
Qing Yang, Zixiang Luo, Zhenyu Mao, Zezheng Wu, Xinghe Cheng +4
Large Language Models (LLMs) increasingly participate in writing by modifying or extending human drafts, causing machine involvement to vary in both form and extent. Yet most Machine-Generated Text (MGT) detectors are evaluated only on fully human-written versus fully AI-generated text. Because human--AI collaboration can weaken or redistribute cues associated with machine generation, strong performance under this binary setting may overstate detector reliability. This mismatch remains underexplored in Chinese: detection cues are shaped by tokenization and language-specific text distributions, yet controlled resources spanning production settings, domains, and generators remain limited. To fill this gap, we present a Chinese Human-AI Collaborative Text Detection Benchmark (C-HAT-Bench), a unified benchmark that links $5,000$ human-written source texts from five domains to more than $240,000$ variants produced using six generative models under Prefix-Conditioned Continuation as a reference setting and three collaborative production modes. We evaluate $21$ detectors through four protocols spanning zero-shot and pretrained supervised document-level detection, boundary localization,…
PDF arXiv
arXiv cs.MASep 26
Self-Evolving Multi-Agent Symbolic Discovery for Financial Fundamental Analysis
Kelvin J. L. Koa, Filip Orestav, Shengqiong Wu, Michael J. Wooldridge, Ke-Wei Huang
While symbolic regression (SR) has been successfully used in science to discover new equations, its use in financial valuation is hindered by several limitations. Whereas the natural sciences provide objectively correct relationships, financial valuation constitutes a distinct class of symbolic discovery problems, as it admits multiple valid perspectives, operates under non-stationary market conditions, and involves noisy, continuous performance signals. In this work, we propose Multi-Agent Fundamental Analysis with Symbolic Adaptive learning (MUFASA), a hierarchical multi-agent framework for symbolic discovery in finance. MUFASA introduces (1) disentangled equation discovery via specialized agents representing distinct valuation perspectives, (2) a meta-coordinator that performs hierarchical-level reasoning over market context information, and (3) a memory mechanism that reasons over statistical performance summaries (e.g., accuracy, stability, and tail risk) to guide learning under noisy feedback. Experiments across datasets from multiple countries show that MUFASA achieves state-of-the-art performance on the valuation task compared to classical finance methods, financial large…
PDF arXiv
arXiv cs.LGSep 26
Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach
Jianna Hur, Sagar Samtani
Modern semiconductor production relies on a globally distributed, multi-tier supply chain in which financial stress at one firm spreads with a delay and eventually affects the revenue, inventory, and profitability of the companies that design AI chips. Most firms see only their direct partners, and prior predictive research has mainly targeted market-based risk measures, so few tools forecast how supply chain stress will appear in reported financials. In this study, we propose a heterogeneous graph patch transformer that forecasts these quarterly changes one and two quarters ahead. Learning from a 15,186-company network over 60 quarters, the proposed model fuses quarterly fundamentals with macro-trade, event, and disaster signals through learned gates, carries risk across supplier, customer, ownership, and headquarters relations through typed, direction-specific propagation, and encodes the propagated histories with patch-based tokenization. In preliminary experiments on 116 focal semiconductor firms, the proposed model achieves the lowest error on every target at both horizons, and its profitability advantage widens at the two-quarter horizon. These forecasts can help supply…
PDF arXiv
arXiv cs.CLSep 26
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Mohan Li, Chengyu Yu, Francesco Sovrano, Marc Langheinrich, Martin Gjoreski
Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional shift is not yet fully understood. Prior work shows that aligned models can fail under jailbreak prompts, alternative encodings, and cross-lingual transfer, yet these failures are usually studied as attacks rather than controlled probes of alignment generalization. Moreover, existing evidence is largely grounded in natural language variation already represented during pretraining, leaving unresolved whether alignment generalizes with semantic content or remains tied to superficial surface patterns. In this paper, we study this question using synthetic semantic-preserving transformations that are rule-based and invertible, preserving task-relevant meaning while shifting inputs beyond standard linguistic variation. Across four open-weight and four commercial models, under both fine-tuning and in-context learning, we use these transformations as a probe of alignment generalization and identify an empirical pattern we term Alignment--utility asymmetry: once models can operate effectively on transformed inputs, task utility is often substantially…
PDF arXiv
arXiv cs.AISep 26
Dude, Where's My State? Execution Information Requirements for Stateful Agents
Nikita Mehrotra, Ashish Tiwari, Priyanshu Gupta, Sumit Gulwani
Long-running agents must preserve information that later steps depend on. We introduce the Execution Information Requirement (EIR), a lower bound on the information that must remain accessible for correct completion under specified task and access conditions. We develop LACUNA, a framework that generates tasks with known dependencies and varies information demand, retention, and recovery separately from the difficulty of individual operations. Across four models, restoring a missing result raises accuracy on affected recall steps to 100%, compared with 0% for equal-length irrelevant information. Sufficient storage alone does not ensure success: retention policies can discard required results, errors can propagate through later computations, and agents can stop before recovery is complete. We also introduce VESTIGE, which uses agent execution traces to construct semantic graphs and measure information demand for real tasks. Across 72,562 software-agent trajectories, VESTIGE reveals a steeper distance-related decline in solution-relevant rereading for failed runs (RR 0.951 per distance doubling), while adjusted peak demand alone is not associated with failure. Together, these…
PDF arXiv
arXiv cs.AISep 26
What Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation
Arshia Eftekhari zadeh
When a language model explains an answer it has already given, does it reuse the computation that produced the answer or reconstruct a story from the answer alone? Attribution, transportability and recoverability are each compatible with causal use without establishing it. We propose an evidence standard: pair each positive statistic with a variable specific null that removes the tested variable's identity while matching relevant nuisance dimensions as far as possible, and audit unmatched dimensions. We apply this standard to a known cause. A cue naming a wrong option raises the rate of choosing that option by 64 to 68 percentage points across three models. Explanations mention the cue in 1.8 percent of items or fewer in three of four models tested. Three estimator classes yield favorable statistics, but none establishes causal sensitivity to the cue contrast under its own control in the three-model analysis. In the strongest case, a recovered cue direction reaches $R^2$ of 0.95 and exceeds a geometry matched random direction in all three seeds, while a direction fitted by the same pipeline with cue labels scrambled reproduces 61 to 76 percent of its effect at comparable realized…
PDF arXiv

Papers

Top tools here

All tools

jcode+233% downloads · 25.5k/wk+233.1%
billion-context+259% downloads · 1.1M/wk+258.8%
LMDeploy+181% downloads · 13.5k/wk+180.6%
Vercel AI SDK400 releases this week
ONNX Runtime+35% downloads · 37.1M/wk+35.2%

Recently funded

Market

Kuaishou Keling AIStage not given · Oct 31$3B
Phinity LabsStage not given · Oct 31$5.2M
Kling AIStage not given · Oct 30$3B
CohereSeries B+ · Oct 29$7B
VinciSeries B+ · Oct 29$250M

Topics in this field

retrieval augmented generation · knowledge graphs · retrieval augmented291 papers37 this week
language models llms · large language models · language models314 papers33 this week
generative recommendation · sequential recommendation · personalized180 papers28 this week
memory construction · persistent memory · long term memory293 papers26 this week
deep research · scientific literature · citations163 papers20 this week
typed decision models · typed decision model · typed decisions160 papers20 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.CLSep 26
C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text
Qing Yang, Zixiang Luo, Zhenyu Mao, Zezheng Wu, Xinghe Cheng +4
Large Language Models (LLMs) increasingly participate in writing by modifying or extending human drafts, causing machine involvement to vary in both form and extent. Yet most Machine-Generated Text (MGT) detectors are evaluated only on fully human-written versus fully AI-generated text. Because human--AI collaboration can weaken or redistribute cues associated with machine generation, strong performance under this binary setting may overstate detector reliability. This mismatch remains underexplored in Chinese: detection cues are shaped by tokenization and language-specific text distributions, yet controlled resources spanning production settings, domains, and generators remain limited. To fill this gap, we present a Chinese Human-AI Collaborative Text Detection Benchmark (C-HAT-Bench), a unified benchmark that links $5,000$ human-written source texts from five domains to more than $240,000$ variants produced using six generative models under Prefix-Conditioned Continuation as a reference setting and three collaborative production modes. We evaluate $21$ detectors through four protocols spanning zero-shot and pretrained supervised document-level detection, boundary localization,…
PDF arXiv
arXiv cs.MASep 26
Self-Evolving Multi-Agent Symbolic Discovery for Financial Fundamental Analysis
Kelvin J. L. Koa, Filip Orestav, Shengqiong Wu, Michael J. Wooldridge, Ke-Wei Huang
While symbolic regression (SR) has been successfully used in science to discover new equations, its use in financial valuation is hindered by several limitations. Whereas the natural sciences provide objectively correct relationships, financial valuation constitutes a distinct class of symbolic discovery problems, as it admits multiple valid perspectives, operates under non-stationary market conditions, and involves noisy, continuous performance signals. In this work, we propose Multi-Agent Fundamental Analysis with Symbolic Adaptive learning (MUFASA), a hierarchical multi-agent framework for symbolic discovery in finance. MUFASA introduces (1) disentangled equation discovery via specialized agents representing distinct valuation perspectives, (2) a meta-coordinator that performs hierarchical-level reasoning over market context information, and (3) a memory mechanism that reasons over statistical performance summaries (e.g., accuracy, stability, and tail risk) to guide learning under noisy feedback. Experiments across datasets from multiple countries show that MUFASA achieves state-of-the-art performance on the valuation task compared to classical finance methods, financial large…
PDF arXiv
arXiv cs.LGSep 26
Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach
Jianna Hur, Sagar Samtani
Modern semiconductor production relies on a globally distributed, multi-tier supply chain in which financial stress at one firm spreads with a delay and eventually affects the revenue, inventory, and profitability of the companies that design AI chips. Most firms see only their direct partners, and prior predictive research has mainly targeted market-based risk measures, so few tools forecast how supply chain stress will appear in reported financials. In this study, we propose a heterogeneous graph patch transformer that forecasts these quarterly changes one and two quarters ahead. Learning from a 15,186-company network over 60 quarters, the proposed model fuses quarterly fundamentals with macro-trade, event, and disaster signals through learned gates, carries risk across supplier, customer, ownership, and headquarters relations through typed, direction-specific propagation, and encodes the propagated histories with patch-based tokenization. In preliminary experiments on 116 focal semiconductor firms, the proposed model achieves the lowest error on every target at both horizons, and its profitability advantage widens at the two-quarter horizon. These forecasts can help supply…
PDF arXiv
arXiv cs.CLSep 26
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Mohan Li, Chengyu Yu, Francesco Sovrano, Marc Langheinrich, Martin Gjoreski
Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional shift is not yet fully understood. Prior work shows that aligned models can fail under jailbreak prompts, alternative encodings, and cross-lingual transfer, yet these failures are usually studied as attacks rather than controlled probes of alignment generalization. Moreover, existing evidence is largely grounded in natural language variation already represented during pretraining, leaving unresolved whether alignment generalizes with semantic content or remains tied to superficial surface patterns. In this paper, we study this question using synthetic semantic-preserving transformations that are rule-based and invertible, preserving task-relevant meaning while shifting inputs beyond standard linguistic variation. Across four open-weight and four commercial models, under both fine-tuning and in-context learning, we use these transformations as a probe of alignment generalization and identify an empirical pattern we term Alignment--utility asymmetry: once models can operate effectively on transformed inputs, task utility is often substantially…
PDF arXiv
arXiv cs.AISep 26
Dude, Where's My State? Execution Information Requirements for Stateful Agents
Nikita Mehrotra, Ashish Tiwari, Priyanshu Gupta, Sumit Gulwani
Long-running agents must preserve information that later steps depend on. We introduce the Execution Information Requirement (EIR), a lower bound on the information that must remain accessible for correct completion under specified task and access conditions. We develop LACUNA, a framework that generates tasks with known dependencies and varies information demand, retention, and recovery separately from the difficulty of individual operations. Across four models, restoring a missing result raises accuracy on affected recall steps to 100%, compared with 0% for equal-length irrelevant information. Sufficient storage alone does not ensure success: retention policies can discard required results, errors can propagate through later computations, and agents can stop before recovery is complete. We also introduce VESTIGE, which uses agent execution traces to construct semantic graphs and measure information demand for real tasks. Across 72,562 software-agent trajectories, VESTIGE reveals a steeper distance-related decline in solution-relevant rereading for failed runs (RR 0.951 per distance doubling), while adjusted peak demand alone is not associated with failure. Together, these…
PDF arXiv
arXiv cs.AISep 26
What Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation
Arshia Eftekhari zadeh
When a language model explains an answer it has already given, does it reuse the computation that produced the answer or reconstruct a story from the answer alone? Attribution, transportability and recoverability are each compatible with causal use without establishing it. We propose an evidence standard: pair each positive statistic with a variable specific null that removes the tested variable's identity while matching relevant nuisance dimensions as far as possible, and audit unmatched dimensions. We apply this standard to a known cause. A cue naming a wrong option raises the rate of choosing that option by 64 to 68 percentage points across three models. Explanations mention the cue in 1.8 percent of items or fewer in three of four models tested. Three estimator classes yield favorable statistics, but none establishes causal sensitivity to the cue contrast under its own control in the three-model analysis. In the strongest case, a recovered cue direction reaches $R^2$ of 0.95 and exceeds a geometry matched random direction in all three seeds, while a direction fitted by the same pipeline with cue labels scrambled reproduces 61 to 76 percent of its effect at comparable realized…
PDF arXiv

Activity · 12 weeks

Open problems in Frontier LLMs

Evaluating long-horizon agents in real-world web environments1 paper raises it · 1 addresses it
Current benchmarks do not capture the complexity of open, dynamic, and interactive web tasks, limiting the assessment of agent capabilities.
- Deep Search in Real-World Web Environmentsraises · addresses
Net value of agent memory over direct retrieval1 paper raises it · 1 addresses it
Memory systems often underperform naive retrieval, and their trade-offs between gains and losses (memory tax) are poorly understood.
- Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
Benchmark difficulty distribution mismatch and coverage gaps1 paper raises it · 1 addresses it
Benchmarks may misrepresent intended difficulty or miss key regions, leading to misleading evaluations of model progress.
- Your Benchmark Is an Empirical Measure Over Difficultyraises · addresses
Structural requirements for decision-native models1 paper raises it · 2 address it
Current decision models often lack null-awareness, permutation invariance, option scalability, and cacheability, limiting their robustness.
- Jeva: System One Models from First Principlesraises · addresses
- LEV: Thinking Fast and Deep with Looped Decision Modelsaddresses
Inferring user habits from weak longitudinal evidence1 paper raises it · 2 address it
Agents struggle to extract and apply user habits from sparse or noisy historical interactions, limiting personalization.
- HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memoryraises · addresses
- Vela: User Behavior as Supervision Sparks LLM Intelligenceaddresses

Named by an AI from these papers' abstracts.

Fields · AI · updated 3m ago

Frontier LLMs

The largest general-purpose language models, their releases, capabilities, scaling and training at frontier scale.

276papers this week−38.4% vs last week

All papers · 2.7k With code · 80

Newest Most relevant

1.7k papers this month