https://agentflare.org/scholar/index.html Academic literature digests en Fri, 16 Oct 2026 01:27:01 GMT https://agentflare.org/scholar/llm-agents-planning-literature-digest.html https://agentflare.org/scholar/llm-agents-planning-literature-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Foundational work established LLMs as planners for embodied and tool-using agents, while critical studies exposed limits in autonomous plan generation. Recent preprints focus on reinforcement learning, grounding, world models and evaluation environments. https://agentflare.org/scholar/retrieval-augmented-generation-research-digest.html https://agentflare.org/scholar/retrieval-augmented-generation-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Retrieval-augmented generation has moved from a fine-tuning recipe to a broad engineering field. Current work covers evaluation, graph indexing, iterative retrieval, multimodal reading, and attacks on the retrieval path. https://agentflare.org/scholar/ai-alignment-safety-research-digest.html https://agentflare.org/scholar/ai-alignment-safety-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Surveys and taxonomies define alignment, while critiques of RLHF and defense-in-depth analyses probe technique limits. Recent preprints turn to auditing misaligned models, safety bounds under time limits, and the role of trust in human-AI decisions. https://agentflare.org/scholar/rlhf-research-digest.html https://agentflare.org/scholar/rlhf-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Foundational work covers assistant training, theory, AI feedback and critiques. Recent preprints focus on reward hacking, personalized and group-conditioned alignment, safety, and evaluator bias. https://agentflare.org/scholar/multimodal-foundation-models-research-digest.html https://agentflare.org/scholar/multimodal-foundation-models-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Foundational work frames vision-language and large multimodal models as general-purpose systems and begins to evaluate them holistically. Recent preprints extend the idea to spatial audio, microscopy, plasma physics and geometry. https://agentflare.org/scholar/mechanistic-interpretability-research-digest.html https://agentflare.org/scholar/mechanistic-interpretability-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Foundational work defines circuits, causal abstraction and identifiability. Recent preprints apply sparse autoencoders, activation analysis and refusal directions to safety, uncertainty, robotics and looped language models. https://agentflare.org/scholar/tool-use-in-language-models-research-digest.html https://agentflare.org/scholar/tool-use-in-language-models-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Foundational work set up self-taught tool use, large-scale tool datasets and function-calling benchmarks. Recent preprints focus on distilling agents, adversarial safety training and agents that build their own tools. https://agentflare.org/scholar/web-agents-navigation-benchmarks-research-digest.html https://agentflare.org/scholar/web-agents-navigation-benchmarks-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Foundational benchmarks span real-world traversal, deterministic website replicas, multi-shop tasks and large-scale evaluation. Recent preprints add hybrid search-and-operate tasks, misleading charts, evolving web apps, and cheaper agent decision-making. https://agentflare.org/scholar/long-context-language-models-research-digest.html https://agentflare.org/scholar/long-context-language-models-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Early work showed models use long inputs unevenly. Current work targets better training recipes, retrieval and memory alternatives, and cutting the serving cost of long inputs. https://agentflare.org/scholar/chain-of-thought-reasoning-research-digest.html https://agentflare.org/scholar/chain-of-thought-reasoning-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Foundational work showed that step-by-step prompts elicit reasoning in large models. Recent preprints probe what those chains encode, how to verify and distill them, and how to compress them into latent states. https://agentflare.org/scholar/code-generation-with-llms-research-digest.html https://agentflare.org/scholar/code-generation-with-llms-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar Foundational work covers surveys, planning, fine-tuning and test-based evaluation. Recent preprints move toward verifier-grounded reinforcement learning, algorithmic diversity benchmarks, and training and decoding for diffusion language models. https://agentflare.org/scholar/mixture-of-experts-architectures-research-digest.html https://agentflare.org/scholar/mixture-of-experts-architectures-research-digest.html Wed, 14 Oct 2026 00:00:00 GMT Scholar 10 foundational papers with 3,521 combined citations, plus the latest arXiv preprints.