Top Tweets for #agentcoma

about 13 hours ago

#agentcoma https://t.co/4Bf1ofMcLq pemium 9-letter .com domain matching the AgentCoMa (Agentic Commonsense and Math) LLM reasoning benchmark. Excellent corporate utility for automation platforms, AI testing frameworks, and enterprise software suites. #Artificialintelligence .

feel2buy's tweet photo. #agentcoma https://t.co/4Bf1ofMcLq
pemium 9-letter .com domain matching the AgentCoMa (Agentic Commonsense and Math) LLM reasoning benchmark. Excellent corporate utility for automation platforms, AI testing frameworks, and enterprise software suites.
#Artificialintelligence . https://t.co/Z0uoMlO4I8

1

3

1

0

52

about 13 hours ago

#agentcoma https://t.co/Oxnzt2jZIk " matching the AgentCoMa (Agentic Commonsense and Math) LLM reasoning benchmark. Excellent corporate utility for automation platforms, #Artificial #Intelligence, #Software #Development , #Data #Analytics , #Academic #Research #Artificial

0

1

0

14

about 13 hours ago

#agentcoma https://t.co/Oxnzt2jZIk https://t.co/Oxnzt2jZIk, clearly state: "Exact match domain for the Agentic Commonsense and Math (AgentCoMa) AI benchmarking framework. Ideal for machine learning evaluation suites."

feel2buy's tweet photo. #agentcoma https://t.co/Oxnzt2jZIk
https://t.co/Oxnzt2jZIk, clearly state: "Exact match domain for the Agentic Commonsense and Math (AgentCoMa) AI benchmarking framework. Ideal for machine learning evaluation suites." https://t.co/VUpWOsyYfO

0

1

0

20

13 days ago

#agentcoma https://t.co/Oxnzt2jZIk Coma" functions as an established tech acronym—most notably standing for Counterfactual Multi-Agent (COMA) learning, an advanced machine learning framework heavily deployed in quantitative algorithmic finance and portfolio risk modeling.

1

2

1

0

97

about 1 month ago

Come to our #ACL2026 oral on Tuesday! Learn all about #AgentCoMa and how LLMs faceplant when they combine different reasoning types 🫠 plus get a cool sticker! 🤖 🗓️ Tue Jul 7th at 11.10am 📍 Oral Session G: Mathematical, Symbolic, Neurosymbolic, and Logical Reasoning · Harbor G

LisaAlazraki's tweet photo. Come to our #ACL2026 oral on Tuesday! Learn all about #AgentCoMa and how LLMs faceplant when they combine different reasoning types 🫠 plus get a cool sticker! 🤖

🗓️ Tue Jul 7th at 11.10am
📍 Oral Session G: Mathematical, Symbolic, Neurosymbolic, and Logical Reasoning · Harbor G https://t.co/rId6Y37OPu

1

37

4

2K

4 months ago

#AgentCoMa has been accepted to #ACL2026 Main Conference! Looking forward to presenting it in San Diego this summer☀️

Hossein A. (Saeed) Rahmani @srahmanidashti

11 months ago

We have released #AgentCoMa, an agentic reasoning benchmark where each task requires a mix of commonsense and math to be solved 🧐 LLM agents performing real-world tasks should be able to combine these different types of reasoning, but are they fit for the job? 🤔 🧵⬇️

LisaAlazraki's tweet photo. We have released #AgentCoMa, an agentic reasoning benchmark where each task requires a mix of commonsense and math to be solved 🧐

LLM agents performing real-world tasks should be able to combine these different types of reasoning, but are they fit for the job? 🤔

🧵⬇️ https://t.co/gH7jn96Shy

1

66

15

27

7K

4

58

8

1

3K

11 months ago

Can LLMs combine #commonsense and #math reasoning the way humans do in everyday problem-solving? 🤔 With our new benchmark, #AgentCoMa, we put this to the test, and the results are surprising. #AgentCoMa #Reasoning #LLMs #Benchmark #Evaluation

11 months ago

We have released #AgentCoMa, an agentic reasoning benchmark where each task requires a mix of commonsense and math to be solved 🧐 LLM agents performing real-world tasks should be able to combine these different types of reasoning, but are they fit for the job? 🤔 🧵⬇️

1

66

15

27

7K

0

8

1

2

433

11 months ago

To learn more: Website: https://t.co/M5K6yrUjqd Preprint: https://t.co/qd0pIWT6Hi A big thanks to my brilliant coauthors @LihuChen, @ana_brrr, @_joestacey_, @srahmanidashti and @MarekRei! Note: We welcome submissions to the #AgentCoMa leaderboard from researchers 🚀

0

14

2

6

458

11 months ago

So why do LLMs perform poorly on the apparently simple tasks in #AgentCoMa? We find that tasks combining different reasoning types are a relatively unseen pattern for LLMs, leading the models to contextual hallucinations when presented with mixed-type compositional reasoning.

1

2

1

0

168

11 months ago

In contrast, we find that: - LLMs perform relatively well on compositional tasks of similar difficulty when all steps require the same type of reasoning. - Non-expert humans with no calculator or internet can solve the tasks in #AgentCoMa as accurately as the individual steps.

1

3

1

0

182