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+116% downloads · 13.1k/wk+116.3%
browser-harness+67% downloads · 3.4M/wk+67.0%
oh-my-claudecode+47% downloads · 7.7k/wk+47.4%

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 test agents' ability to autonomously search, access, and integrate evidence from the live, open Web.
- Deep Search in Real-World Web Environmentsraises · addresses
Net value of agent memory over direct retrieval1 paper raises it · 2 address it
Many memory systems underperform naive retrieval, and the trade-offs between memory benefits and memory tax are unclear.
- Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
- REMORY: Learning Residual Memory for Context Compactionaddresses
Efficient context compaction for long-horizon agents2 papers raise it · 2 address it
Textual summaries alone may not preserve all necessary information for subsequent decisions, and cache management is costly.
- REMORY: Learning Residual Memory for Context Compactionraises · addresses
- Cache Engineering for Agentsraises · addresses
Structural requirements for decision-native models1 paper raises it · 2 address it
Current decision models often fail to respect null-awareness, permutation invariance, option scalability, and cacheability.
- Jeva: System One Models from First Principlesraises · addresses
- LEV: Thinking Fast and Deep with Looped Decision Modelsaddresses
Reliable no-thinking behavior in LLMs1 paper raises it · 1 addresses it
Existing proxies for no-thinking are unreliable, and explicit controls cannot consistently enforce answer-only output.
- Thinking Inertia: LLMs Keep Thinking When Told Not Toraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Market

Tutor IntelligenceSeries B+ · Nov 2$75M
42AISeed · Nov 2$62.5M
Keling AIStage not given · Oct 31$3B
Phinity LabsStage not given · Oct 31$5.2M
Kling AIStage not given · Oct 30$3B

Recently funded

Topics in this field

reasoning models · reasoning tasks · reasoning traces404 papers32 this week
judges · llm judges · llm judge182 papers29 this week
retrieval augmented generation · dense retrieval · retrieval quality214 papers28 this week
long term memory · memory construction · term memory255 papers26 this week
question answering · answering · responses252 papers23 this week
graph retrieval · knowledge graph · retrieval augmented generation130 papers23 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 20
Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations
Zihao Lu, Zhihang Yuan, Litu Ou, Lei Shi
Memory enables language model agents to use information beyond their context windows, but maintaining and accessing this information reliably remains difficult. Long-horizon conversational memory is especially challenging in multi-actor settings, where relevant evidence is distributed across participants and contexts, and previously established information may later be revised. We introduce EGMEMORY, a training-free agentic memory framework centered on evidence chains that preserve message-level evidence and provenance while tracking active states and their revision histories. At write time, adaptive memory inspection and an evidence-grounded propose-verify-commit protocol govern state updates. At read time, adaptive evidence navigation iteratively identifies the state and supporting evidence required for a query, using conversational structure to narrow the search space and lexical-semantic relevance to rank candidates. The system operates through prompting and tool use without memory-specific policy training. EGMEMORY achieves 68.2% on GroupMemBench and 77.9% on EverMemBench, outperforming the strongest evaluated baselines by 22.7 and 21.4 percentage points, respectively. It…
PDF arXiv
arXiv cs.SESep 20
Omni2Web: Benchmarking Audiovisual Website Development
Minghao Han, Zhenghao Xing, Xize Cheng, Yuxuan Wang, Junming Lin +5
Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor trajectories, page state, and edit history. Such requests require intent recovery beyond the explicit specifications assumed by many existing web-editing benchmarks. We introduce Omni2Web, a bilingual benchmark of 918 instances spanning 13,907 edit steps. It defines three complementary tracks: Direct Editing evaluates webpage editing from recordings, Instruction Recovery measures explicit intent recovery, and Instruction Utility tests whether recovered instructions can drive a fixed code executor. We evaluate 17 open- and closed-source models. The best models attain 51.17 on the Edit Fidelity Score (EFS) for Direct Editing and 49.14 on the Instruction Recovery Score (IRS); under the fixed executor, the strongest recovered instructions reach 51.08 EFS, still far below the 89.69 EFS obtained with oracle instructions. Step-level analyses show that correct grounding does not guarantee successful edits, while some Omni models recover instructions that the fixed coding model executes substantially better than their direct edits. Controlled…
PDF arXiv
arXiv cs.CLSep 20
Can Multimodal Large Language Models Generate and Detect Multimodal Social Media Fake News?
Jiyao Yang, Yang Liu, Zhenyue Qin, Qingyu Chen, Xiuzhen Zhang
The rapid advancement of generative AI raises concerns about the misuse of Multimodal LLMs (MLLMs) for large-scale disinformation campaigns on social media. Despite existing research on textual disinformation, a fundamental question remains unanswered: can MLLMs be exploited to fabricate realistic multimodal fake news, and can they reliably detect it? We introduce a multi-agent framework in which a story agent, an image agent, and a critic agent collaborate to produce fake social media posts that plausibly counter true news. We apply the framework to generate over 9,000 paired multimodal news posts across science, health, and entertainment domains, and benchmark 16 open- and closed-source MLLMs for automated detection. We find that most models fall substantially short of human-level accuracy and fail critically on identifying image authenticity. Our research provides a foundation for developing robust defenses against social media fake news. Code and data are available at https: //github.com/xiuzhenzhang/Multimodal.
PDF arXiv
arXiv hep-phSep 20
LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning
Bakar Chargeishvili
FORM is a domain-specific symbolic manipulation language widely used in particle physics for processing the very large algebraic expressions arising from multi-loop Feynman diagram calculations. Despite its central role in precision theoretical physics, no artificial-intelligence tooling exists, to our knowledge, for assisting physicists in writing FORM code. We show that contemporary large language models (LLMs), including frontier models with hundreds of billions of parameters, achieve a zero-percent execution pass rate on our instruction-following and tutorial-style FORM tasks without documentation in a single attempt, establishing FORM as a genuine zero-shot language for LLMs at the time of writing. We then present a verification-driven data generation pipeline that uses the FORM binary itself as an execution oracle to produce and validate a corpus of 4,633 training examples spanning deterministic computations, open-ended programs, tutorial code, and knowledge question-answer pairs. Fine-tuning a compact open-weights model (Qwen3-8B) with quantized low-rank adaptation (QLoRA) yields a specialist that, evaluated on four complementary benchmarks (840 tasks, single attempt…
PDF arXiv
arXiv cs.CVSep 20
MDL-Calibrated Significance-Gain Pair Encoding: Replication-Aware Automatic Stopping for Subword Tokenization
Azam Nouri
Byte-Pair Encoding (BPE) constructs subword vocabularies through greedy pair merging, but conventional BPE requires the number of merges or target vocabulary size to be specified externally. Significance-Gain Pair Encoding (SG-BPE) replaces frequency-only selection with a statistical criterion based on how strongly an observed pair exceeds its expected co-occurrence under an independence model. This paper introduces MDL-Calibrated Significance-Gain Pair Encoding (MDL-SG), a three-stage procedure separating discovery, replication, and utility. Candidate pairs are ranked by Significance-Gain on a discovery partition, tested for replication on a separate partition using an exact one-sided hypergeometric test with per-iteration Benjamini-Hochberg correction, and then evaluated on a utility partition using a Minimum Description Length (MDL) criterion. Merging stops automatically when no replicated candidate yields positive held-out MDL gain. On WikiText-103, MDL-SG stops at 209, 433, and 847 merges for 120K, 250K, and 500K-character tokenizer-training samples, respectively. At 500K characters, it selects a stored vocabulary of 1,017 tokens without prescribing the vocabulary size in…
PDF arXiv
arXiv cs.LGSep 20
CSC: Calibrated Simplicity for Conflict-Aware Social Bot Detection in the LLM Era
Yipeng Qian, Pengjie Zhao, Chaoxi Niu
Social bot detection is essential for protecting online platforms from misinformation amplification, coordinated manipulation, and distorted public discourse. However, large language models have made social bots much harder to detect from text alone because semantic camouflage is now cheap, fluent, and scalable. The resulting challenge is modality conflict: an account may look human-like in semantics while remaining suspicious in graph structure, profile attributes, or cross-modal consistency. Recent graph-based detectors tackle this limitation by adding graph-side complexity, such as sparse prototype selection, adaptive gating, or architecture-specific control logic, yet our experiments suggest that complexity alone is not the most reliable way to resolve such conflict. We therefore propose CSC, a calibrated-simplicity framework for conflict-aware LLM-era social bot detection. The framework combines three design choices: a simplified prototype-guided graph expert that retains useful structural biases while removing unstable graph-side heuristics, calibrated simplex-constrained fusion that aligns heterogeneous confidence spaces before late fusion, and a lightweight inconsistency…
PDF arXiv

Papers

Recently funded

Market

Tutor IntelligenceSeries B+ · Nov 2$75M
42AISeed · Nov 2$62.5M
Keling AIStage not given · Oct 31$3B
Phinity LabsStage not given · Oct 31$5.2M
Kling AIStage not given · Oct 30$3B

Top tools here

All tools

jcode+233% downloads · 25.5k/wk+233.1%
billion-context+259% downloads · 1.1M/wk+258.8%
LMDeploy+116% downloads · 13.1k/wk+116.3%
browser-harness+67% downloads · 3.4M/wk+67.0%
oh-my-claudecode+47% downloads · 7.7k/wk+47.4%

Topics in this field

reasoning models · reasoning tasks · reasoning traces404 papers32 this week
judges · llm judges · llm judge182 papers29 this week
retrieval augmented generation · dense retrieval · retrieval quality214 papers28 this week
long term memory · memory construction · term memory255 papers26 this week
question answering · answering · responses252 papers23 this week
graph retrieval · knowledge graph · retrieval augmented generation130 papers23 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.CLSep 20
Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations
Zihao Lu, Zhihang Yuan, Litu Ou, Lei Shi
Memory enables language model agents to use information beyond their context windows, but maintaining and accessing this information reliably remains difficult. Long-horizon conversational memory is especially challenging in multi-actor settings, where relevant evidence is distributed across participants and contexts, and previously established information may later be revised. We introduce EGMEMORY, a training-free agentic memory framework centered on evidence chains that preserve message-level evidence and provenance while tracking active states and their revision histories. At write time, adaptive memory inspection and an evidence-grounded propose-verify-commit protocol govern state updates. At read time, adaptive evidence navigation iteratively identifies the state and supporting evidence required for a query, using conversational structure to narrow the search space and lexical-semantic relevance to rank candidates. The system operates through prompting and tool use without memory-specific policy training. EGMEMORY achieves 68.2% on GroupMemBench and 77.9% on EverMemBench, outperforming the strongest evaluated baselines by 22.7 and 21.4 percentage points, respectively. It…
PDF arXiv
arXiv cs.SESep 20
Omni2Web: Benchmarking Audiovisual Website Development
Minghao Han, Zhenghao Xing, Xize Cheng, Yuxuan Wang, Junming Lin +5
Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor trajectories, page state, and edit history. Such requests require intent recovery beyond the explicit specifications assumed by many existing web-editing benchmarks. We introduce Omni2Web, a bilingual benchmark of 918 instances spanning 13,907 edit steps. It defines three complementary tracks: Direct Editing evaluates webpage editing from recordings, Instruction Recovery measures explicit intent recovery, and Instruction Utility tests whether recovered instructions can drive a fixed code executor. We evaluate 17 open- and closed-source models. The best models attain 51.17 on the Edit Fidelity Score (EFS) for Direct Editing and 49.14 on the Instruction Recovery Score (IRS); under the fixed executor, the strongest recovered instructions reach 51.08 EFS, still far below the 89.69 EFS obtained with oracle instructions. Step-level analyses show that correct grounding does not guarantee successful edits, while some Omni models recover instructions that the fixed coding model executes substantially better than their direct edits. Controlled…
PDF arXiv
arXiv cs.CLSep 20
Can Multimodal Large Language Models Generate and Detect Multimodal Social Media Fake News?
Jiyao Yang, Yang Liu, Zhenyue Qin, Qingyu Chen, Xiuzhen Zhang
The rapid advancement of generative AI raises concerns about the misuse of Multimodal LLMs (MLLMs) for large-scale disinformation campaigns on social media. Despite existing research on textual disinformation, a fundamental question remains unanswered: can MLLMs be exploited to fabricate realistic multimodal fake news, and can they reliably detect it? We introduce a multi-agent framework in which a story agent, an image agent, and a critic agent collaborate to produce fake social media posts that plausibly counter true news. We apply the framework to generate over 9,000 paired multimodal news posts across science, health, and entertainment domains, and benchmark 16 open- and closed-source MLLMs for automated detection. We find that most models fall substantially short of human-level accuracy and fail critically on identifying image authenticity. Our research provides a foundation for developing robust defenses against social media fake news. Code and data are available at https: //github.com/xiuzhenzhang/Multimodal.
PDF arXiv
arXiv hep-phSep 20
LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning
Bakar Chargeishvili
FORM is a domain-specific symbolic manipulation language widely used in particle physics for processing the very large algebraic expressions arising from multi-loop Feynman diagram calculations. Despite its central role in precision theoretical physics, no artificial-intelligence tooling exists, to our knowledge, for assisting physicists in writing FORM code. We show that contemporary large language models (LLMs), including frontier models with hundreds of billions of parameters, achieve a zero-percent execution pass rate on our instruction-following and tutorial-style FORM tasks without documentation in a single attempt, establishing FORM as a genuine zero-shot language for LLMs at the time of writing. We then present a verification-driven data generation pipeline that uses the FORM binary itself as an execution oracle to produce and validate a corpus of 4,633 training examples spanning deterministic computations, open-ended programs, tutorial code, and knowledge question-answer pairs. Fine-tuning a compact open-weights model (Qwen3-8B) with quantized low-rank adaptation (QLoRA) yields a specialist that, evaluated on four complementary benchmarks (840 tasks, single attempt…
PDF arXiv
arXiv cs.CVSep 20
MDL-Calibrated Significance-Gain Pair Encoding: Replication-Aware Automatic Stopping for Subword Tokenization
Azam Nouri
Byte-Pair Encoding (BPE) constructs subword vocabularies through greedy pair merging, but conventional BPE requires the number of merges or target vocabulary size to be specified externally. Significance-Gain Pair Encoding (SG-BPE) replaces frequency-only selection with a statistical criterion based on how strongly an observed pair exceeds its expected co-occurrence under an independence model. This paper introduces MDL-Calibrated Significance-Gain Pair Encoding (MDL-SG), a three-stage procedure separating discovery, replication, and utility. Candidate pairs are ranked by Significance-Gain on a discovery partition, tested for replication on a separate partition using an exact one-sided hypergeometric test with per-iteration Benjamini-Hochberg correction, and then evaluated on a utility partition using a Minimum Description Length (MDL) criterion. Merging stops automatically when no replicated candidate yields positive held-out MDL gain. On WikiText-103, MDL-SG stops at 209, 433, and 847 merges for 120K, 250K, and 500K-character tokenizer-training samples, respectively. At 500K characters, it selects a stored vocabulary of 1,017 tokens without prescribing the vocabulary size in…
PDF arXiv
arXiv cs.LGSep 20
CSC: Calibrated Simplicity for Conflict-Aware Social Bot Detection in the LLM Era
Yipeng Qian, Pengjie Zhao, Chaoxi Niu
Social bot detection is essential for protecting online platforms from misinformation amplification, coordinated manipulation, and distorted public discourse. However, large language models have made social bots much harder to detect from text alone because semantic camouflage is now cheap, fluent, and scalable. The resulting challenge is modality conflict: an account may look human-like in semantics while remaining suspicious in graph structure, profile attributes, or cross-modal consistency. Recent graph-based detectors tackle this limitation by adding graph-side complexity, such as sparse prototype selection, adaptive gating, or architecture-specific control logic, yet our experiments suggest that complexity alone is not the most reliable way to resolve such conflict. We therefore propose CSC, a calibrated-simplicity framework for conflict-aware LLM-era social bot detection. The framework combines three design choices: a simplified prototype-guided graph expert that retains useful structural biases while removing unstable graph-side heuristics, calibrated simplex-constrained fusion that aligns heterogeneous confidence spaces before late fusion, and a lightweight inconsistency…
PDF arXiv

Activity · 12 weeks

Fields · AI · updated 28m ago

Frontier LLMs

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

340papers this week−16.9% vs last week

All papers · 3.1k With code · 87

Newest Most relevant

1.9k papers this month

Open problems in Frontier LLMs

Evaluating long-horizon agents in real-world web environments1 paper raises it · 1 addresses it
Current benchmarks do not test agents' ability to autonomously search, access, and integrate evidence from the live, open Web.
- Deep Search in Real-World Web Environmentsraises · addresses
Net value of agent memory over direct retrieval1 paper raises it · 2 address it
Many memory systems underperform naive retrieval, and the trade-offs between memory benefits and memory tax are unclear.
- Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
- REMORY: Learning Residual Memory for Context Compactionaddresses
Efficient context compaction for long-horizon agents2 papers raise it · 2 address it
Textual summaries alone may not preserve all necessary information for subsequent decisions, and cache management is costly.
- REMORY: Learning Residual Memory for Context Compactionraises · addresses
- Cache Engineering for Agentsraises · addresses
Structural requirements for decision-native models1 paper raises it · 2 address it
Current decision models often fail to respect null-awareness, permutation invariance, option scalability, and cacheability.
- Jeva: System One Models from First Principlesraises · addresses
- LEV: Thinking Fast and Deep with Looped Decision Modelsaddresses
Reliable no-thinking behavior in LLMs1 paper raises it · 1 addresses it
Existing proxies for no-thinking are unreliable, and explicit controls cannot consistently enforce answer-only output.
- Thinking Inertia: LLMs Keep Thinking When Told Not Toraises · addresses

Named by an AI from these papers' abstracts.