PutnamBench
PulseAugur coverage of PutnamBench — every cluster mentioning PutnamBench across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New AI framework HOA achieves perfect scores on multiple Olympiads
Researchers have developed HOA, an open framework designed to enhance the problem-solving capabilities of AI agents across various Olympiad tasks. HOA coordinates multiple agent sessions, incorporating feedback from ind…
-
New LEVER algorithm optimizes AI proof search for cost and quality
Researchers have developed LEVER, a novel proof search algorithm designed to optimize proofs not just for correctness but also for user-defined objectives like simplicity, purity, and computational cost. LEVER integrate…
-
New AI framework boosts theorem proving with mutation-enhanced skill evolution
Researchers have developed SkillEvoLean, a novel framework for enhancing large language model agents in formal theorem proving. This method employs mutation-enhanced skill evolution, which updates both a high-level solv…
-
LeanPolish pipeline enhances AI-generated Lean proofs with verified edits
Researchers have developed LeanPolish, a symbolic pipeline for the Lean 4 programming language, to generate verified proof edits for improving language model-generated proofs. This system releases 33,402 accepted edits …
-
Multi-agent systems advance automated proof discovery in math and software verification · 5 sources tracked
Researchers have developed advanced multi-agent systems for automated proof discovery in formal mathematics and software verification. One framework, FORALL-LEAN-AGENT, enhances auditable reasoning by combining isolated…
-
New MCTS framework for AI theorem proving highlights need for proof auditing
Researchers have developed a novel three-role Monte Carlo Tree Search (MCTS) framework for formal theorem proving using large language models. This approach treats the Lean 4 compiler as a reward oracle, using its outpu…
-
Mistral AI releases Leanstral 1.5 for advanced formal verification
Mistral AI has released Leanstral 1.5, an open-source model designed for formal verification tasks. This model, which has 6 billion active parameters and is available under the Apache 2.0 license, demonstrates significa…
-
Pythagoras-Prover achieves state-of-the-art in efficient formal proving
Researchers have introduced Pythagoras-Prover, a new family of theorem provers designed for efficiency in formal reasoning tasks. These models utilize curriculum training and augmented formalization techniques to overco…
-
DeepSeek V4 powers Goedel-Architect to math competition win at low cost
A new framework named Goedel-Architect, powered by DeepSeek V4, has achieved a 75.6% pass rate on the PutnamBench mathematics competition. This framework offers a significant cost advantage, costing only $294 compared t…
-
New framework ECP formally solves math answer-construction problems
Researchers have developed a new neuro-symbolic framework called Enumerate-Conjecture-Prove (ECP) designed to tackle answer-construction problems in formal mathematics. This framework combines general large language mod…
-
AI frameworks boost formal theorem proving with new techniques
Researchers have developed new frameworks to enhance formal theorem proving capabilities using large language models. Goedel-Architect utilizes a blueprint generation and refinement strategy, achieving state-of-the-art …
-
LLMs optimized for efficient formal theorem proving in Lean
Two new research papers explore methods to improve the efficiency and effectiveness of large language models (LLMs) in formal theorem proving within the Lean environment. The first paper introduces an action routing age…