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 execution and memory3 papers raise it · 3 address it
Agents fail to retain, retrieve, and use past information over long interactions, limiting real-world deployment.
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversationsraises
- Scaling Agentic Data for Long-Horizon Terminal Intelligenceraises · addresses
- Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?raises · addresses
- Agent-Reflex: Teaching Language Agents to Act Reflectivelyaddresses
Real-world task ambiguity and unstated constraints3 papers raise it · 2 address it
Agents struggle with ambiguous, incomplete, or evolving requirements in live systems, unlike controlled benchmarks.
- OR-License: Evaluating LLM Agents as Real-World Operations Research Practitionersraises · addresses
- FDE-Gym: The Last Mile of AI Deliveryraises · addresses
- AgentSWE: Can Coding Agents Build the Agent You Actually Want?raises
Faithful agent development from requirements1 paper raises it · 1 addresses it
Coding agents often produce systems that appear correct but fail to meet the actual requirements.
- AgentSWE: Can Coding Agents Build the Agent You Actually Want?raises · addresses
Sequential distraction in multimodal GUI agents1 paper raises it · 1 addresses it
Omni-modal inputs cause agents to focus on irrelevant signals, leading to compounding errors.
- Focused Omni-Modal GUI Agentsraises · addresses
Open, reproducible agent stacks and evaluation1 paper raises it · 1 addresses it
Closed systems and lack of open benchmarks hinder systematic study and improvement of agent designs.
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · 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 papers77 this week
skills · tasks · ai315 papers53 this week
recursive self improvement · harness evolution · adaptive271 papers48 this week
ai agents · indirect prompt injection · adversarial319 papers39 this week
tool using agents · agent systems · multi agent216 papers37 this week
agent · agentic · llm agents172 papers36 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.AIOct 13
A dataset of formalised theorem statements from the Annals of Mathematics
Thomas Browning, Katerina Hristova, David Ledvinka, Justus Springer, Hang Lu Su +2
Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires datasets of formal statements that are both hard and trustworthy. We present AnnalsChallenge: 50 formalised theorem statements written by hand in Lean 4 using Mathlib. Each is the main result of a paper published in the Annals of Mathematics since 2020. Every formalisation was manually reviewed and then audited by AI. We release them without formalised proofs.
PDF arXiv
arXiv cs.AIOct 13
Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench
Yuxiao Hu, Qian Li, Ding Wang, Siheng Chen, Linfeng Zhang +2
Most symbolic regression methods optimize candidate equations, but improving an equation's fit does not establish whether its underlying scientific conjecture should be retained, revised, or rejected. A conjecture may admit multiple mathematical realizations, and similarly accurate equations may imply different explanations. This motivates a shift from refining individual expressions to developing and testing the conjectures that guide them. We introduce SCOPE, a framework that sustains multiple conjecture-driven research trajectories. Multiple scientist agents independently pursue conjectures through equation modeling, question formulation, and active experimentation, then exchange evidence to revise their conjectures and research directions. Their findings are consolidated into a scientific report linking models, conclusions, and evidence. Existing equation-discovery benchmarks primarily assess recovered expressions, leaving the evidence and scientific conclusions established through the investigation underexamined. We therefore introduce ClosureBench, an interactive benchmark of 60 closure-discovery tasks across five scientific domains. ClosureBench focuses on…
PDF arXiv
arXiv cs.CROct 13
Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Yan-Lun Chen, Pin-Yu Chen, Chia-Mu Yu
Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such instructions in skill files for agents to decode and follow. We evaluate Caesar and layered variants across eight models and 139 injection-task pairs, separating instruction recovery from attack success. In the primary setting with shortened skills, the variants achieve attack success rates of up to 47.5% and 40.3%, respectively. Successful decoding does not guarantee attack success, and layering has model-dependent effects. The tested skill scanners rarely flag injected skills. These findings highlight the risk of promoting decoded, untrusted content into actionable instructions.
PDF arXiv
arXiv cs.AIOct 13
Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
Dezheng Bao, Sihang Du, Renhong Huang, Zhizhang Yuan, Yifei Sun +1
Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision. However, standard broadcast-style MAD makes peer answers visible without requiring agents to engage with a particular peer claim. As a result, reliable reasoning may be suppressed by conflicting or majority responses, limiting achievable performance, while erroneous reasoning may persist and degrade final predictions without actionable feedback. We propose TrueMAD, a backbone-agnostic test-time plug-in that introduces one-to-one, free-form peer advice between answer broadcasting and self-revision. Each source agent responds to a target's current reasoning through support, rebuttal, refinement, or further questions, while the target retains control over how to revise. The same mechanism can augment standard MAD and its improved variants without parameter updates. Across AIME, GPQA-Diamond, and TruthfulQA with Qwen3-30B-A3B, TrueMAD improves agent-level and strict-majority accuracy over MAD by 3.62 and 3.52 percentage points on average, while TrueDMAD improves DMAD by 4.72 and 4.06 points, respectively. Analyses at the utterance,…
PDF arXiv
arXiv cs.CROct 13
Holding Agents Accountable with Verifiable Agent Insurance
Cheng Hua, Taro Tsuchiya, Nicolas Christin, Giulia Fanti
While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data. While prior work has focused on preventing such misbehavior, we consider how to recover after an agent misbehaves. We propose verifiable agent insurance (VAI), a framework for agent providers to commit financially to promises, a list of programmatically-specified policies that an agent is meant to follow. These promises are embedded in a smart contract on an immutable ledger (e.g., a blockchain) to prevent tampering, along with a monetary escrow. A user who detects a violation of committed promises can prompt a verifier to review agent execution traces, which are logged through the agent harness's shared tool-execution path, without instrumenting each tool separately. Upon verification of the violation, the agent provider's escrow funds are paid to the reporting user. We instantiate VAI as an end-to-end implementation on an Ethereum layer-2 network, and evaluate its coverage on three prominent agent benchmarks, two of which we re-annotated to obtain task-level policy-compliance labels. Currently, many agents do not emit user authorizations and…
PDF arXiv
arXiv cs.SECodeOct 13▲ 18
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents
Do Xuan Trong, Duc Anh Nguyen, Do Xuan Long, Ngoc-Hai Nguyen, Tongyao Zhu +10
We present SWE-MISBEHAVIOR, the first taxonomy and evaluation framework for diagnosing boundary-violating misbehaviors in coding agents. It contains 7.4K human-in-the-loop synthesized samples spanning three layers of agent action space: (i) Code Generation, (ii) File Management, and (iii) System Interaction. Across these categories, SWE-MISBEHAVIOR covers 11 distinct misbehaviors with a fully automated evaluation protocol, including coding-action violations, Create/Read/Update/Delete (CRUD) file misbehaviors, system integrity and abuse violations, and task-goal misalignment. Experiments on state-of-the-art open-source coding agents (e.g., OpenHands, smolagents) reveal substantial misaligned behaviors, including dependency misinterpretation (up to 98.5% of cases), unintended modification of user inputs (50.5%), and silent compromise of environment integrity (53%). Motivated by these findings, we further propose CODE-KIT, a lightweight adaptive framework that combines misbehavior-aware guidelines with novel tools to help agents avoid such failures. CODE-KIT reduces misbehaviors by 52% for smolagents and 34% for OpenHands, while simultaneously improving task completion performance.
PDF arXiv Code

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%

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

Topics in this field

coding agents · code generation · coding agent303 papers77 this week
skills · tasks · ai315 papers53 this week
recursive self improvement · harness evolution · adaptive271 papers48 this week
ai agents · indirect prompt injection · adversarial319 papers39 this week
tool using agents · agent systems · multi agent216 papers37 this week
agent · agentic · llm agents172 papers36 this week

Active contributors · 90 days

Activity · 12 weeks

Recent papers

All papers in Research

arXiv cs.AIOct 13
A dataset of formalised theorem statements from the Annals of Mathematics
Thomas Browning, Katerina Hristova, David Ledvinka, Justus Springer, Hang Lu Su +2
Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires datasets of formal statements that are both hard and trustworthy. We present AnnalsChallenge: 50 formalised theorem statements written by hand in Lean 4 using Mathlib. Each is the main result of a paper published in the Annals of Mathematics since 2020. Every formalisation was manually reviewed and then audited by AI. We release them without formalised proofs.
PDF arXiv
arXiv cs.AIOct 13
Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench
Yuxiao Hu, Qian Li, Ding Wang, Siheng Chen, Linfeng Zhang +2
Most symbolic regression methods optimize candidate equations, but improving an equation's fit does not establish whether its underlying scientific conjecture should be retained, revised, or rejected. A conjecture may admit multiple mathematical realizations, and similarly accurate equations may imply different explanations. This motivates a shift from refining individual expressions to developing and testing the conjectures that guide them. We introduce SCOPE, a framework that sustains multiple conjecture-driven research trajectories. Multiple scientist agents independently pursue conjectures through equation modeling, question formulation, and active experimentation, then exchange evidence to revise their conjectures and research directions. Their findings are consolidated into a scientific report linking models, conclusions, and evidence. Existing equation-discovery benchmarks primarily assess recovered expressions, leaving the evidence and scientific conclusions established through the investigation underexamined. We therefore introduce ClosureBench, an interactive benchmark of 60 closure-discovery tasks across five scientific domains. ClosureBench focuses on…
PDF arXiv
arXiv cs.CROct 13
Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Yan-Lun Chen, Pin-Yu Chen, Chia-Mu Yu
Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such instructions in skill files for agents to decode and follow. We evaluate Caesar and layered variants across eight models and 139 injection-task pairs, separating instruction recovery from attack success. In the primary setting with shortened skills, the variants achieve attack success rates of up to 47.5% and 40.3%, respectively. Successful decoding does not guarantee attack success, and layering has model-dependent effects. The tested skill scanners rarely flag injected skills. These findings highlight the risk of promoting decoded, untrusted content into actionable instructions.
PDF arXiv
arXiv cs.AIOct 13
Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
Dezheng Bao, Sihang Du, Renhong Huang, Zhizhang Yuan, Yifei Sun +1
Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision. However, standard broadcast-style MAD makes peer answers visible without requiring agents to engage with a particular peer claim. As a result, reliable reasoning may be suppressed by conflicting or majority responses, limiting achievable performance, while erroneous reasoning may persist and degrade final predictions without actionable feedback. We propose TrueMAD, a backbone-agnostic test-time plug-in that introduces one-to-one, free-form peer advice between answer broadcasting and self-revision. Each source agent responds to a target's current reasoning through support, rebuttal, refinement, or further questions, while the target retains control over how to revise. The same mechanism can augment standard MAD and its improved variants without parameter updates. Across AIME, GPQA-Diamond, and TruthfulQA with Qwen3-30B-A3B, TrueMAD improves agent-level and strict-majority accuracy over MAD by 3.62 and 3.52 percentage points on average, while TrueDMAD improves DMAD by 4.72 and 4.06 points, respectively. Analyses at the utterance,…
PDF arXiv
arXiv cs.CROct 13
Holding Agents Accountable with Verifiable Agent Insurance
Cheng Hua, Taro Tsuchiya, Nicolas Christin, Giulia Fanti
While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data. While prior work has focused on preventing such misbehavior, we consider how to recover after an agent misbehaves. We propose verifiable agent insurance (VAI), a framework for agent providers to commit financially to promises, a list of programmatically-specified policies that an agent is meant to follow. These promises are embedded in a smart contract on an immutable ledger (e.g., a blockchain) to prevent tampering, along with a monetary escrow. A user who detects a violation of committed promises can prompt a verifier to review agent execution traces, which are logged through the agent harness's shared tool-execution path, without instrumenting each tool separately. Upon verification of the violation, the agent provider's escrow funds are paid to the reporting user. We instantiate VAI as an end-to-end implementation on an Ethereum layer-2 network, and evaluate its coverage on three prominent agent benchmarks, two of which we re-annotated to obtain task-level policy-compliance labels. Currently, many agents do not emit user authorizations and…
PDF arXiv
arXiv cs.SECodeOct 13▲ 18
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents
Do Xuan Trong, Duc Anh Nguyen, Do Xuan Long, Ngoc-Hai Nguyen, Tongyao Zhu +10
We present SWE-MISBEHAVIOR, the first taxonomy and evaluation framework for diagnosing boundary-violating misbehaviors in coding agents. It contains 7.4K human-in-the-loop synthesized samples spanning three layers of agent action space: (i) Code Generation, (ii) File Management, and (iii) System Interaction. Across these categories, SWE-MISBEHAVIOR covers 11 distinct misbehaviors with a fully automated evaluation protocol, including coding-action violations, Create/Read/Update/Delete (CRUD) file misbehaviors, system integrity and abuse violations, and task-goal misalignment. Experiments on state-of-the-art open-source coding agents (e.g., OpenHands, smolagents) reveal substantial misaligned behaviors, including dependency misinterpretation (up to 98.5% of cases), unintended modification of user inputs (50.5%), and silent compromise of environment integrity (53%). Motivated by these findings, we further propose CODE-KIT, a lightweight adaptive framework that combines misbehavior-aware guidelines with novel tools to help agents avoid such failures. CODE-KIT reduces misbehaviors by 52% for smolagents and 34% for OpenHands, while simultaneously improving task completion performance.
PDF arXiv Code

Open problems in Agents

Long-horizon task execution and memory3 papers raise it · 3 address it
Agents fail to retain, retrieve, and use past information over long interactions, limiting real-world deployment.
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversationsraises
- Scaling Agentic Data for Long-Horizon Terminal Intelligenceraises · addresses
- Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?raises · addresses
- Agent-Reflex: Teaching Language Agents to Act Reflectivelyaddresses
Real-world task ambiguity and unstated constraints3 papers raise it · 2 address it
Agents struggle with ambiguous, incomplete, or evolving requirements in live systems, unlike controlled benchmarks.
- OR-License: Evaluating LLM Agents as Real-World Operations Research Practitionersraises · addresses
- FDE-Gym: The Last Mile of AI Deliveryraises · addresses
- AgentSWE: Can Coding Agents Build the Agent You Actually Want?raises
Faithful agent development from requirements1 paper raises it · 1 addresses it
Coding agents often produce systems that appear correct but fail to meet the actual requirements.
- AgentSWE: Can Coding Agents Build the Agent You Actually Want?raises · addresses
Sequential distraction in multimodal GUI agents1 paper raises it · 1 addresses it
Omni-modal inputs cause agents to focus on irrelevant signals, leading to compounding errors.
- Focused Omni-Modal GUI Agentsraises · addresses
Open, reproducible agent stacks and evaluation1 paper raises it · 1 addresses it
Closed systems and lack of open benchmarks hinder systematic study and improvement of agent designs.
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

Fields · AI · updated 24m ago

Agents

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

493papers this week−10.0% vs last week

All papers · 2.6k With code · 125

Newest Most relevant

2.4k papers this month