Papers

Field

Top tools here

All tools

QwenPaw+1266% downloads · 39k/wk+1266.0%
billion-context+259% downloads · 1.1M/wk+258.8%
jcode+233% downloads · 25.5k/wk+233.1%
oh-my-claudecode+47% downloads · 7.7k/wk+47.4%
TanStack AI+68% downloads · 1M/wk+67.7%

Top tools here

Open problems in Agents

Long-horizon task completion with exploration and verification3 papers raise it · 2 address it
Agents struggle to accumulate evidence, adjust strategies, and verify results over long, realistic workflows.
- Scaling Agentic Data for Long-Horizon Terminal Intelligenceraises · addresses
- MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environmentsraises · addresses
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises
Faithful agent development from natural-language requirements1 paper raises it · 1 addresses it
Coding agents often fail to deliver agents that truly meet the specified requirements rather than just appearing to.
- AgentSWE: Can Coding Agents Build the Agent You Actually Want?raises · addresses
Realistic evaluation of agent learning from experience1 paper raises it · 1 addresses it
Existing benchmarks often test reasoning with known rules rather than learning novel, counterintuitive rules through interaction.
- Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?raises · addresses
Detecting when past context matters in long conversations1 paper raises it · 0 address it
Agents cannot reliably identify when historical context is relevant, leading to missed or incorrect responses.
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversationsraises
Open-source, reproducible GUI agent stacks2 papers raise it · 2 address it
Frontier GUI agents are often closed, limiting systematic study and community collaboration.
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses
- MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environmentsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Market

FirstWorkSeries A · Oct 21$15M
Asymptote LabsSeed · Oct 20$5.5M
LumilabPre-seed · Oct 20undisclosed
GreptileSeries B+ · Oct 19$50M
VesslaPre-seed · Oct 19$3.3M

Recently funded

Topics in this field

coding agents · code generation · coding agent303 papers72 this week
skills · tasks · ai315 papers46 this week
recursive self improvement · harness evolution · adaptive271 papers41 this week
ai agents · indirect prompt injection · adversarial319 papers38 this week
tool using agents · agent systems · multi agent216 papers34 this week
agent · agentic · llm agents172 papers34 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.MAOct 13
Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
Yiqing Peng, Hehai Lin, Zixuan Wang, Dongyi Zhang, Zhengjie Zhu +5
Large language model (LLM)-based multi-agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but can create a bottleneck at a single coordination locus, whereas decentralized coordination offers local autonomy but must achieve effective collaboration through distributed decisions and experience. These trade-offs motivate a systematic study of the space between the two regimes. We introduce Degrees of Freedom (DoF), a continuous configuration framework that quantifies the size of the decision space delegated to downstream agents. DoF controls the granularity of delegated work and the target probability that each task unit is assigned to the branches. Its endpoints recover the two coordination regimes. Across multiple task domains, DoF reveals a hierarchy of organizational effects. Delegated granularity and within-regime routing produce structured but bounded profile reallocations, whereas task domain and retained experience are associated with stronger differences between the centralized- and decentralized-branch profiles. The resulting performance landscape is task-dependent: different domains favor…
PDF arXiv
arXiv cs.AIOct 13
Coupled Harness--Model Evolution for Scientific Equation Discovery
Pengze Li, Jiaquan Zhang, Encheng Su, Yunbo Long, Zihang Zeng +6
Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library of executable computational tools and the model's tool-use policy. The tools supply the solving capability, from diagnosing structure in the data to fitting candidate equations; the policy plans and orchestrates their use. Yet existing systems adapt only one part, keeping either the toolset or the model fixed, which leaves the corresponding failures uncorrectable. We develop a coupled evolution framework that improves both parts from the same verifiable fit-error signal. In the tool-evolution phase, an agent grows an executable tool library from a small set of generic numerical operations by diagnosing its own failures: it authors a new tool when a capability is missing and revises its selection rules when the right tool went unused. In the policy-evolution phase, a small open model (roughly 3B active parameters) is fine-tuned on successful tool-use trajectories collected with the frozen library, on training formulas screened to be disjoint from all evaluation benchmarks. Ablations show the two phases…
PDF arXiv
arXiv cs.AIOct 13
Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants
Yewon Han, Jisu Jeon, Suhyun Choi, Juan Yeo, Minsoo Jo +3
Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, including those that affect bystanders. Yet existing safety evaluations do not distinguish whom a response would harm, and score only whether a model refuses. Pooling all harms into one refusal rate hides two failures: a model may protect one target but not another, and it may refuse without understanding the risk, or understand it and comply anyway. We present STOU, a benchmark of 2,902 egocentric video-audio and video-text queries whose potential harm targets the user (Self), co-present individuals (The Others), or society at large (Others). Our evaluation decouples safety understanding from refusal behavior: beyond refusal, we score whether the model recognizes the user's intent, the presence and target of harm, and its downstream consequences. Across 10 open and closed source omnimodal and multimodal LLMs, we find that refusal varies systematically with the harm target, and that models often recognize a harm yet still assist with it. These results show that refusal rates alone cannot certify an assistant as safe, and that safety…
PDF arXiv
arXiv cs.CROct 13
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge
Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical screen must catch nearly every attack while keeping the review load manageable. We present SkillScreen, a compact decision model trained to score skill maliciousness directly from SKILL$.$md in a single forward pass. On MaliciousSkillBench, SkillScreen flags 20-25% of benign skills at 99% recall on unseen attack families, substantially fewer than the word-level classifier and prompted LLM judges tested. Under the same training protocol, it also generalizes better than a fully fine-tuned encoder to unseen sources. Yet unfamiliar benign sources sharply increase false positives, showing that recognizing new attacks does not ensure reliable screening of new skill collections. Our results demonstrate the value of task-trained decision models for high-recall skill screening. Project page: https://jerroldh.github.io/SkillScreen-webpage/
PDF arXiv
arXiv cs.AICodeOct 13▲ 22
Evidence-First Agentic Verification
Reza Sanayei, Razvan-Gabriel Dumitru, Sunjie Hou, MohammadHossein Rezaei, Haris Riaz +5
Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across the environment state and the execution trace. A judge may overlook this evidence or accept unsupported claims, including an agent's own reports of success. When rubric verdicts serve as reinforcement-learning rewards, such errors can reinforce undesirable behavior. We introduce Sauron, an evidence-first agentic verifier that investigates both state and trace and relies on a claim only after independently validating it against its source. Bounded queries and joint investigation of related criteria reduce context use and redundant work, and each verdict carries an auditable receipt of its supporting evidence. Across 2,586 human-labeled criteria from 100 personal-assistant episodes, Sauron achieves the highest F1 of five verifiers on all eight backbones tested while costing less than Gandalf, the strongest baseline. With GPT-5.6 Sol, it reaches 0.96 F1 versus Gandalf's 0.92 at 23% lower cost, with a wider margin on process criteria. On a paired fault-injection suite covering 13 families, several of which simulate reward hacking,…
PDF arXiv Code
arXiv cs.AIOct 13
Upstream Influence, Downstream Re-Anchoring in LLM Agent Chains
Chun-Yu Hsu, Lun-Wei Ku, Chung-Chi Chen
People act on evaluative judgments produced by LLM agents, and in multi-agent systems those judgments pass through several agents before reaching a person. We show that a workflow's information architecture---source access, handoff format, and which model reads the untrusted content---governs how much of a coordinated manipulation reaches the end. On 32 Taiwan~2025 recall cases, ten authentic Threads comments shown to one agent move its stance by $+0.171$ toward the injected position, and a mirrored set moves it the other way. Passing that judgment down a chain removes more than half of the shift by the third agent; keeping the comments in front of every agent sustains more of it. The reduction is not attrition in transit: each receiver discounts the inherited stance in proportion to how far it sits from its own reading of the evidence, returning to what that evidence implies for the case rather than to neutrality---consistent with partial re-anchoring. Handoff format is a second lever: a stance relayed without its reasoning is largely discounted. Susceptibility at the exposed seat varies fourfold across models, while the chain's arrangement does not matter at all. None of this…
PDF arXiv

Papers

Top tools here

All tools

QwenPaw+1266% downloads · 39k/wk+1266.0%
billion-context+259% downloads · 1.1M/wk+258.8%
jcode+233% downloads · 25.5k/wk+233.1%
oh-my-claudecode+47% downloads · 7.7k/wk+47.4%
TanStack AI+68% downloads · 1M/wk+67.7%

Topics in this field

coding agents · code generation · coding agent303 papers72 this week
skills · tasks · ai315 papers46 this week
recursive self improvement · harness evolution · adaptive271 papers41 this week
ai agents · indirect prompt injection · adversarial319 papers38 this week
tool using agents · agent systems · multi agent216 papers34 this week
agent · agentic · llm agents172 papers34 this week

Recently funded

Market

FirstWorkSeries A · Oct 21$15M
Asymptote LabsSeed · Oct 20$5.5M
LumilabPre-seed · Oct 20undisclosed
GreptileSeries B+ · Oct 19$50M
VesslaPre-seed · Oct 19$3.3M

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.MAOct 13
Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
Yiqing Peng, Hehai Lin, Zixuan Wang, Dongyi Zhang, Zhengjie Zhu +5
Large language model (LLM)-based multi-agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but can create a bottleneck at a single coordination locus, whereas decentralized coordination offers local autonomy but must achieve effective collaboration through distributed decisions and experience. These trade-offs motivate a systematic study of the space between the two regimes. We introduce Degrees of Freedom (DoF), a continuous configuration framework that quantifies the size of the decision space delegated to downstream agents. DoF controls the granularity of delegated work and the target probability that each task unit is assigned to the branches. Its endpoints recover the two coordination regimes. Across multiple task domains, DoF reveals a hierarchy of organizational effects. Delegated granularity and within-regime routing produce structured but bounded profile reallocations, whereas task domain and retained experience are associated with stronger differences between the centralized- and decentralized-branch profiles. The resulting performance landscape is task-dependent: different domains favor…
PDF arXiv
arXiv cs.AIOct 13
Coupled Harness--Model Evolution for Scientific Equation Discovery
Pengze Li, Jiaquan Zhang, Encheng Su, Yunbo Long, Zihang Zeng +6
Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library of executable computational tools and the model's tool-use policy. The tools supply the solving capability, from diagnosing structure in the data to fitting candidate equations; the policy plans and orchestrates their use. Yet existing systems adapt only one part, keeping either the toolset or the model fixed, which leaves the corresponding failures uncorrectable. We develop a coupled evolution framework that improves both parts from the same verifiable fit-error signal. In the tool-evolution phase, an agent grows an executable tool library from a small set of generic numerical operations by diagnosing its own failures: it authors a new tool when a capability is missing and revises its selection rules when the right tool went unused. In the policy-evolution phase, a small open model (roughly 3B active parameters) is fine-tuned on successful tool-use trajectories collected with the frozen library, on training formulas screened to be disjoint from all evaluation benchmarks. Ablations show the two phases…
PDF arXiv
arXiv cs.AIOct 13
Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants
Yewon Han, Jisu Jeon, Suhyun Choi, Juan Yeo, Minsoo Jo +3
Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, including those that affect bystanders. Yet existing safety evaluations do not distinguish whom a response would harm, and score only whether a model refuses. Pooling all harms into one refusal rate hides two failures: a model may protect one target but not another, and it may refuse without understanding the risk, or understand it and comply anyway. We present STOU, a benchmark of 2,902 egocentric video-audio and video-text queries whose potential harm targets the user (Self), co-present individuals (The Others), or society at large (Others). Our evaluation decouples safety understanding from refusal behavior: beyond refusal, we score whether the model recognizes the user's intent, the presence and target of harm, and its downstream consequences. Across 10 open and closed source omnimodal and multimodal LLMs, we find that refusal varies systematically with the harm target, and that models often recognize a harm yet still assist with it. These results show that refusal rates alone cannot certify an assistant as safe, and that safety…
PDF arXiv
arXiv cs.CROct 13
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge
Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical screen must catch nearly every attack while keeping the review load manageable. We present SkillScreen, a compact decision model trained to score skill maliciousness directly from SKILL$.$md in a single forward pass. On MaliciousSkillBench, SkillScreen flags 20-25% of benign skills at 99% recall on unseen attack families, substantially fewer than the word-level classifier and prompted LLM judges tested. Under the same training protocol, it also generalizes better than a fully fine-tuned encoder to unseen sources. Yet unfamiliar benign sources sharply increase false positives, showing that recognizing new attacks does not ensure reliable screening of new skill collections. Our results demonstrate the value of task-trained decision models for high-recall skill screening. Project page: https://jerroldh.github.io/SkillScreen-webpage/
PDF arXiv
arXiv cs.AICodeOct 13▲ 22
Evidence-First Agentic Verification
Reza Sanayei, Razvan-Gabriel Dumitru, Sunjie Hou, MohammadHossein Rezaei, Haris Riaz +5
Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across the environment state and the execution trace. A judge may overlook this evidence or accept unsupported claims, including an agent's own reports of success. When rubric verdicts serve as reinforcement-learning rewards, such errors can reinforce undesirable behavior. We introduce Sauron, an evidence-first agentic verifier that investigates both state and trace and relies on a claim only after independently validating it against its source. Bounded queries and joint investigation of related criteria reduce context use and redundant work, and each verdict carries an auditable receipt of its supporting evidence. Across 2,586 human-labeled criteria from 100 personal-assistant episodes, Sauron achieves the highest F1 of five verifiers on all eight backbones tested while costing less than Gandalf, the strongest baseline. With GPT-5.6 Sol, it reaches 0.96 F1 versus Gandalf's 0.92 at 23% lower cost, with a wider margin on process criteria. On a paired fault-injection suite covering 13 families, several of which simulate reward hacking,…
PDF arXiv Code
arXiv cs.AIOct 13
Upstream Influence, Downstream Re-Anchoring in LLM Agent Chains
Chun-Yu Hsu, Lun-Wei Ku, Chung-Chi Chen
People act on evaluative judgments produced by LLM agents, and in multi-agent systems those judgments pass through several agents before reaching a person. We show that a workflow's information architecture---source access, handoff format, and which model reads the untrusted content---governs how much of a coordinated manipulation reaches the end. On 32 Taiwan~2025 recall cases, ten authentic Threads comments shown to one agent move its stance by $+0.171$ toward the injected position, and a mirrored set moves it the other way. Passing that judgment down a chain removes more than half of the shift by the third agent; keeping the comments in front of every agent sustains more of it. The reduction is not attrition in transit: each receiver discounts the inherited stance in proportion to how far it sits from its own reading of the evidence, returning to what that evidence implies for the case rather than to neutrality---consistent with partial re-anchoring. Handoff format is a second lever: a stance relayed without its reasoning is largely discounted. Susceptibility at the exposed seat varies fourfold across models, while the chain's arrangement does not matter at all. None of this…
PDF arXiv

Activity · 12 weeks

Fields · AI · updated 38m ago

Agents

LLM agents: planning, tool use, multi-agent systems, computer/web agents and agent benchmarks.

447papers this week−21.3% vs last week

All papers · 2.6k With code · 127

Newest Most relevant

2.4k papers this month

Open problems in Agents

Long-horizon task completion with exploration and verification3 papers raise it · 2 address it
Agents struggle to accumulate evidence, adjust strategies, and verify results over long, realistic workflows.
- Scaling Agentic Data for Long-Horizon Terminal Intelligenceraises · addresses
- MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environmentsraises · addresses
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises
Faithful agent development from natural-language requirements1 paper raises it · 1 addresses it
Coding agents often fail to deliver agents that truly meet the specified requirements rather than just appearing to.
- AgentSWE: Can Coding Agents Build the Agent You Actually Want?raises · addresses
Realistic evaluation of agent learning from experience1 paper raises it · 1 addresses it
Existing benchmarks often test reasoning with known rules rather than learning novel, counterintuitive rules through interaction.
- Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?raises · addresses
Detecting when past context matters in long conversations1 paper raises it · 0 address it
Agents cannot reliably identify when historical context is relevant, leading to missed or incorrect responses.
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversationsraises
Open-source, reproducible GUI agent stacks2 papers raise it · 2 address it
Frontier GUI agents are often closed, limiting systematic study and community collaboration.
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses
- MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environmentsraises · addresses

Named by an AI from these papers' abstracts.