5arXiv cs.CL (Computation and Language)·
TCA-SIR: Target-conditioned abstraction improves scientific inspiration retrieval for hypothesis generation
TCA-SIR reformulates Scientific Inspiration Retrieval (SIR) as a target-conditioned abstraction task, where a transferable principle is extracted from a candidate paper specifically relative to a target problem, rather than ranking by topical similarity. The system learns to generate these abstractions and uses their representations to predict transferability, outperforming prior SIR methods including MOOSE-Chem by more than 10 percentage points in HitRate@top4% on ResearchBench. The approach is motivated by how humans abstract and remap problem-solving principles across domains, making it particularly useful for retrieving 'remote' inspirations with low topical overlap.
Related guides (1)
Related events (8)
SAIR: Accelerating Pharma R&D with AI-Powered Structural Intelligence
SandboxAQ has published a blog post on Hugging Face describing SAIR (Structural AI for Research), a system applying AI to structural biology data for drug discovery acceleration. The post outlines how structural intelligence—likely leveraging protein structure prediction or molecular modeling—is being applied to pharmaceutical R&D pipelines. This represents an enterprise deployment of AI in the life sciences domain, combining structural biology with machine learning.
SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics
SPECTRA is a reproducible framework for generating synthetic information retrieval test collections, separating latent topical structure, surface text realization, and query intent generation to produce deterministic relevance oracles without human annotation. A Python prototype generated corpora up to 60,000 documents at roughly 12K–14K documents per second, with graded relevance labels for 96 queries. Controlled distractor experiments showed BM25 nDCG@10 degrading from 1.00 at 2% distractors to 0.43 at 36%, demonstrating the framework's utility for exposing retrieval system failure modes before expensive real-world collection construction. The authors position SPECTRA as a diagnostic complement to Cranfield/TREC-style evaluation rather than a replacement for human judgment.
NatureBench: Coding agents surpass published SOTA on only 17.8% of real scientific tasks from Nature-family papers
NatureBench introduces a 90-task benchmark derived from peer-reviewed Nature-family publications to evaluate whether AI coding agents can advance beyond reproduction toward genuine scientific discovery. Built on NatureGym, an automated pipeline that creates containerized per-task environments, the benchmark addresses environment fragmentation that has undermined prior agent-on-research evaluations. Evaluating ten frontier agent configurations under a web-search-disabled protocol, the strongest model exceeds published SOTA on only 17.8% of tasks, with failures driven primarily by wrong method choice and insufficient compute rather than task misunderstanding. Agents succeed mainly through methodological translation—recasting scientific problems as supervised prediction—rather than genuine scientific invention.
Supra Cognitive Modes: routed architecture for agent memory across factual, relational, and synthesis workloads
A new arXiv preprint introduces Supra Cognitive Modes (SCM), an agent memory architecture that routes queries to specialized retrieval and synthesis pipelines over a shared ingest substrate combining dense embeddings, knowledge graph triples, and fact-version metadata. A frozen semantic classifier dispatches queries among lexical/dense lookup, multi-hop graph reasoning, and long-form synthesis modes. The system is evaluated on three agent memory benchmarks—LoCoMo (84.87% factoid), MemoryAgentBench (61.49%), and LongMemEval (86.00%)—though the authors note that causal routing effects, efficiency gains, and statistical significance remain unestablished.
SciReasoner: Multimodal foundation model for native structural reasoning across biology, chemistry, and materials science
Researchers introduce SciReasoner, a multimodal scientific foundation model that discretizes molecular coordinates, topologies, and periodic connectivities into a unified structure-aware vocabulary for reasoning over proteins, small molecules, and inorganic crystals. The model achieves state-of-the-art performance on 67 of 86 benchmarks, with notable gains in Gene Ontology prediction (F_max 0.42→0.55), retrosynthesis accuracy (0.63→0.72), and materials phase separation. Expert evaluators rated its reasoning traces as preferred or comparable to a frontier LLM in 98% of cases, suggesting meaningful interpretability alongside accuracy gains.
G-RRM: Neuro-symbolic approach guides SAT solvers with recurrent neural reasoning models
Researchers introduce G-RRM (Guiding with Recurrent Reasoning Models), a neuro-symbolic framework that uses symbol-equivariant recurrent neural networks (SE-RRMs) to guide classical symbolic solvers—including backtracking and SAT solvers Glucose 4.1 and CaDiCaL 3.0.0—for constraint satisfaction problems. On 9×9 Sudoku, the approach achieves 33.3× speedup for backtracking and 1.70× for Glucose 4.1, but shows no significant gain for CaDiCaL due to its overhead-dominated runtime and inability to overwrite injected hints. The paper identifies two conditions for neural guidance to be effective: a large combinatorial search space and a solver architecture capable of dynamically overriding imperfect neural hints.
InMind benchmark exposes implicit-association blind spot in agent long-term memory systems
Researchers introduce InMind, a 125-task expert-verified benchmark targeting a failure mode in agent long-term memory: facts stored in memory are not retrieved when the query lacks surface-level textual overlap with the relevant memory (e.g., a nut allergy should affect a macaron recommendation but shares no keywords). Testing six vector, graph, and agentic memory systems reveals a stark gap — backbone models answer 84% of indirect queries when the relevant memory is placed in context, but retrieval systems surface the correct answer at most 14.4% of the time despite near-perfect on-demand recall. The study isolates the failure to the query-conditioned retrieval interface itself, framing routing — deciding which facts must remain visible — as the core open problem.
Analogical Deep Research: LLM agents for foresight via historical analogy retrieval
Researchers introduce Analogical Deep Research (ADR), a new task and benchmark (ADR-bench) for evaluating whether LLM agents can find and leverage structural historical analogies for foresight analysis. The paper identifies a core failure mode: agents match on surface features rather than causal mechanisms. The authors propose CANA (Causal Analogical Researcher), an agentic framework using structural decomposition and reflective feedback, achieving up to 10% improvement in analogy generation and outperforming state-of-the-art deep research agents on ADR-bench.