Add opportunity triage queue#2
Closed
carlluvmath wants to merge 9 commits into
Closed
Conversation
- Insight Agent: cross-paper reasoning discovers contradictions, method transfers, assumption challenges, ignored limitations, paradigm exhaustion (123 insights from 2790 papers) - Insight Ranker: paradigm-breaking score 1-10 with rationale - Research Bridge: gathers evidence from knowledge graph, formats enriched proposal, launches EvoScientist to generate complete research plans - Taxonomy Expander: auto-expand classification tree (71→470 nodes) - Abstraction Agent: cross-domain pattern discovery - Evidence Graph: entity-relation knowledge graph (47K entities, 277K relations) - Multi-provider LLM client: tabcode (Responses API) + kimi + minimax with round-robin failover - Dashboard: Insights tab with paradigm score badges, filter/sort, "Generate Full Plan" button, proposal preview modal - Removed old opportunity/gap system (matrix gap filling) - SYSTEM.md: full architecture and end-to-end task documentation - HANDOFF.md: architecture + remaining task (plan→execution→paper) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Comprehensive survey of latent communication between LLM agents (2024-2026), including LatentMAS, Interlat, Vision Wormhole, Coconut, and Google Thinking States. Identifies key gap: no existing work supports tool use in latent communication. Proposes hybrid latent-token architecture with 3 concrete experiments and compute estimates. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Introduce a repository-managed CLA gate so unsigned contributors are blocked before merge while maintainers can approve signers with a simple default-branch registry. Made-with: Cursor
Full cross-domain survey covering: 6G semantic communication, neural compression, federated learning, robot communication, brain-computer interfaces, information bottleneck theory, multi-modal alignment, diffusion models, VAE systems, and neuroscience. Identifies 5 unified principles across all domains and 5 unexplored research directions. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Covers: native training methods, compression approaches, transmission protocols, tool use gap, evaluation benchmarks, limitations, and open source implementations. Focused on LLM agent latent communication mechanics rather than cross-domain breadth. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Integrates LatentCompress experimental data (512B=91% on GSM8K, 16B→57% comm accuracy, 4x compression with 99.95% retention) with 3 proposed directions: large-scale compressor training, native latent pretraining, and hybrid latent-token tool use. Formatted for research lab proposal. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement prioritized opportunity triage and surface it in the pipeline and web UI so high-value opportunities can be reviewed consistently. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Capture the triage queue work and current validation state so the branch handoff stays readable. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
11 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Refs #1
Test plan
python -m pytest -q tests/test_opportunity_engine.py tests/test_web_app.py🤖 Generated with Claude Code